---

yaml
---
r: 18051
b: refs/heads/master
c: 198e2f1
h: refs/heads/master
i:
  18049: 631264d
  18047: 0684d85
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 4dc7a0bbeb6882ad665e588e82fabe5bb4645f2f
+refs/heads/master: 198e2f181163233b379dc7ce8a6d7516b84042e7

trunk/Documentation/kernel-parameters.txt

@@ -856,6 +856,49 @@ running once the system is up.
 
 	mga=		[HW,DRM]
 
+	migration_cost=
+			[KNL,SMP] debug: override scheduler migration costs
+			Format: <level-1-usecs>,<level-2-usecs>,...
+			This debugging option can be used to override the
+			default scheduler migration cost matrix. The numbers
+			are indexed by 'CPU domain distance'.
+			E.g. migration_cost=1000,2000,3000 on an SMT NUMA
+			box will set up an intra-core migration cost of
+			1 msec, an inter-core migration cost of 2 msecs,
+			and an inter-node migration cost of 3 msecs.
+
+			WARNING: using the wrong values here can break
+			scheduler performance, so it's only for scheduler
+			development purposes, not production environments.
+
+	migration_debug=
+			[KNL,SMP] migration cost auto-detect verbosity
+			Format=<0|1|2>
+			If a system's migration matrix reported at bootup
+			seems erroneous then this option can be used to
+			increase verbosity of the detection process.
+			We default to 0 (no extra messages), 1 will print
+			some more information, and 2 will be really
+			verbose (probably only useful if you also have a
+			serial console attached to the system).
+
+	migration_factor=
+			[KNL,SMP] multiply/divide migration costs by a factor
+			Format=<percent>
+			This debug option can be used to proportionally
+			increase or decrease the auto-detected migration
+			costs for all entries of the migration matrix.
+			E.g. migration_factor=150 will increase migration
+			costs by 50%. (and thus the scheduler will be less
+			eager migrating cache-hot tasks)
+			migration_factor=80 will decrease migration costs
+			by 20%. (thus the scheduler will be more eager to
+			migrate tasks)
+
+			WARNING: using the wrong values here can break
+			scheduler performance, so it's only for scheduler
+			development purposes, not production environments.
+
 	mousedev.tap_time=
 			[MOUSE] Maximum time between finger touching and
 			leaving touchpad surface for touch to be considered

trunk/arch/i386/kernel/smpboot.c

@@ -1096,6 +1096,7 @@ static void smp_tune_scheduling (void)
 			cachesize = 16; /* Pentiums, 2x8kB cache */
 			bandwidth = 100;
 		}
+		max_cache_size = cachesize * 1024;
 	}
 }
 

trunk/arch/ia64/kernel/setup.c

@@ -696,6 +696,7 @@ static void
 get_max_cacheline_size (void)
 {
 	unsigned long line_size, max = 1;
+	unsigned int cache_size = 0;
 	u64 l, levels, unique_caches;
         pal_cache_config_info_t cci;
         s64 status;
@@ -725,6 +726,8 @@ get_max_cacheline_size (void)
 		line_size = 1 << cci.pcci_line_size;
 		if (line_size > max)
 			max = line_size;
+		if (cache_size < cci.pcci_cache_size)
+			cache_size = cci.pcci_cache_size;
 		if (!cci.pcci_unified) {
 			status = ia64_pal_cache_config_info(l,
 						    /* cache_type (instruction)= */ 1,
@@ -741,6 +744,9 @@ get_max_cacheline_size (void)
 			ia64_i_cache_stride_shift = cci.pcci_stride;
 	}
   out:
+#ifdef CONFIG_SMP
+	max_cache_size = max(max_cache_size, cache_size);
+#endif
 	if (max > ia64_max_cacheline_size)
 		ia64_max_cacheline_size = max;
 }

trunk/arch/ppc/xmon/xmon.c

@@ -99,7 +99,7 @@ static void remove_bpts(void);
 static void insert_bpts(void);
 static struct bpt *at_breakpoint(unsigned pc);
 static void bpt_cmds(void);
-static void cacheflush(void);
+void cacheflush(void);
 #ifdef CONFIG_SMP
 static void cpu_cmd(void);
 #endif /* CONFIG_SMP */

trunk/include/asm-i386/topology.h

@@ -72,7 +72,6 @@ static inline int node_to_first_cpu(int node)
 	.max_interval		= 32,			\
 	.busy_factor		= 32,			\
 	.imbalance_pct		= 125,			\
-	.cache_hot_time		= (10*1000000),		\
 	.cache_nice_tries	= 1,			\
 	.busy_idx		= 3,			\
 	.idle_idx		= 1,			\

trunk/include/asm-ia64/topology.h

@@ -55,7 +55,6 @@ void build_cpu_to_node_map(void);
 	.max_interval		= 4,			\
 	.busy_factor		= 64,			\
 	.imbalance_pct		= 125,			\
-	.cache_hot_time		= (10*1000000),		\
 	.per_cpu_gain		= 100,			\
 	.cache_nice_tries	= 2,			\
 	.busy_idx		= 2,			\
@@ -81,7 +80,6 @@ void build_cpu_to_node_map(void);
 	.max_interval		= 8*(min(num_online_cpus(), 32)), \
 	.busy_factor		= 64,			\
 	.imbalance_pct		= 125,			\
-	.cache_hot_time		= (10*1000000),		\
 	.cache_nice_tries	= 2,			\
 	.busy_idx		= 3,			\
 	.idle_idx		= 2,			\

trunk/include/asm-mips/mach-ip27/topology.h

@@ -27,7 +27,6 @@ extern unsigned char __node_distances[MAX_COMPACT_NODES][MAX_COMPACT_NODES];
 	.max_interval		= 32,			\
 	.busy_factor		= 32,			\
 	.imbalance_pct		= 125,			\
-	.cache_hot_time		= (10*1000),		\
 	.cache_nice_tries	= 1,			\
 	.per_cpu_gain		= 100,			\
 	.flags			= SD_LOAD_BALANCE	\

trunk/include/asm-powerpc/topology.h

@@ -39,7 +39,6 @@ static inline int node_to_first_cpu(int node)
 	.max_interval		= 32,			\
 	.busy_factor		= 32,			\
 	.imbalance_pct		= 125,			\
-	.cache_hot_time		= (10*1000000),		\
 	.cache_nice_tries	= 1,			\
 	.per_cpu_gain		= 100,			\
 	.busy_idx		= 3,			\

trunk/include/asm-x86_64/topology.h

@@ -39,7 +39,6 @@ extern int __node_distance(int, int);
 	.max_interval		= 32,			\
 	.busy_factor		= 32,			\
 	.imbalance_pct		= 125,			\
-	.cache_hot_time		= (10*1000000),		\
 	.cache_nice_tries	= 2,			\
 	.busy_idx		= 3,			\
 	.idle_idx		= 2,			\

trunk/include/linux/sched.h

@@ -631,7 +631,14 @@ struct sched_domain {
 
 extern void partition_sched_domains(cpumask_t *partition1,
 				    cpumask_t *partition2);
-#endif /* CONFIG_SMP */
+
+/*
+ * Maximum cache size the migration-costs auto-tuning code will
+ * search from:
+ */
+extern unsigned int max_cache_size;
+
+#endif	/* CONFIG_SMP */
 
 
 struct io_context;			/* See blkdev.h */

trunk/include/linux/topology.h

@@ -86,7 +86,6 @@
 	.max_interval		= 2,			\
 	.busy_factor		= 8,			\
 	.imbalance_pct		= 110,			\
-	.cache_hot_time		= 0,			\
 	.cache_nice_tries	= 0,			\
 	.per_cpu_gain		= 25,			\
 	.busy_idx		= 0,			\
@@ -117,7 +116,6 @@
 	.max_interval		= 4,			\
 	.busy_factor		= 64,			\
 	.imbalance_pct		= 125,			\
-	.cache_hot_time		= (5*1000000/2),	\
 	.cache_nice_tries	= 1,			\
 	.per_cpu_gain		= 100,			\
 	.busy_idx		= 2,			\