summaryrefslogtreecommitdiff
path: root/arch/powerpc/mm/numa.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2010-08-05 09:03:46 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2010-08-05 09:03:46 -0700
commitcdd854bc42b5e6c79bbbc40c6600d995ffe6e747 (patch)
tree18c4dcc07bbb8aeb2b23bc812cd60cc293f36cd8 /arch/powerpc/mm/numa.c
parentbbc4fd12a635492ad9d12bb418124fa2d5f0d734 (diff)
parent42a0ae2282b512d1a8f6f020327f5f7b8f31a5ea (diff)
Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc
* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (79 commits) powerpc/8xx: Add support for the MPC8xx based boards from TQC powerpc/85xx: Introduce support for the Freescale P1022DS reference board powerpc/85xx: Adding DTS for the STx GP3-SSA MPC8555 board powerpc/85xx: Change deprecated binding for 85xx-based boards powerpc/tqm85xx: add a quirk for ti1520 PCMCIA bridge powerpc/tqm85xx: update PCI interrupt-map attribute powerpc/mpc8308rdb: support for MPC8308RDB board from Freescale powerpc/fsl_pci: add quirk for mpc8308 pcie bridge powerpc/85xx: Cleanup QE initialization for MPC85xxMDS boards powerpc/85xx: Fix booting for P1021MDS boards powerpc/85xx: Fix SWIOTLB initalization for MPC85xxMDS boards powerpc/85xx: kexec for SMP 85xx BookE systems powerpc/5200/i2c: improve i2c bus error recovery of/xilinxfb: update tft compatible versions powerpc/fsl-diu-fb: Support setting display mode using EDID powerpc/5121: doc/dts-bindings: update doc of FSL DIU bindings powerpc/5121: shared DIU framebuffer support powerpc/5121: move fsl-diu-fb.h to include/linux powerpc/5121: fsl-diu-fb: fix issue with re-enabling DIU area descriptor powerpc/512x: add clock structure for Video-IN (VIU) unit ...
Diffstat (limited to 'arch/powerpc/mm/numa.c')
-rw-r--r--arch/powerpc/mm/numa.c122
1 files changed, 89 insertions, 33 deletions
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index aa731af720c0..002878ccf90b 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -42,6 +42,12 @@ EXPORT_SYMBOL(node_data);
static int min_common_depth;
static int n_mem_addr_cells, n_mem_size_cells;
+static int form1_affinity;
+
+#define MAX_DISTANCE_REF_POINTS 4
+static int distance_ref_points_depth;
+static const unsigned int *distance_ref_points;
+static int distance_lookup_table[MAX_NUMNODES][MAX_DISTANCE_REF_POINTS];
/*
* Allocate node_to_cpumask_map based on number of available nodes
@@ -204,6 +210,39 @@ static const u32 *of_get_usable_memory(struct device_node *memory)
return prop;
}
+int __node_distance(int a, int b)
+{
+ int i;
+ int distance = LOCAL_DISTANCE;
+
+ if (!form1_affinity)
+ return distance;
+
+ for (i = 0; i < distance_ref_points_depth; i++) {
+ if (distance_lookup_table[a][i] == distance_lookup_table[b][i])
+ break;
+
+ /* Double the distance for each NUMA level */
+ distance *= 2;
+ }
+
+ return distance;
+}
+
+static void initialize_distance_lookup_table(int nid,
+ const unsigned int *associativity)
+{
+ int i;
+
+ if (!form1_affinity)
+ return;
+
+ for (i = 0; i < distance_ref_points_depth; i++) {
+ distance_lookup_table[nid][i] =
+ associativity[distance_ref_points[i]];
+ }
+}
+
/* Returns nid in the range [0..MAX_NUMNODES-1], or -1 if no useful numa
* info is found.
*/
@@ -225,6 +264,10 @@ static int of_node_to_nid_single(struct device_node *device)
/* POWER4 LPAR uses 0xffff as invalid node */
if (nid == 0xffff || nid >= MAX_NUMNODES)
nid = -1;
+
+ if (nid > 0 && tmp[0] >= distance_ref_points_depth)
+ initialize_distance_lookup_table(nid, tmp);
+
out:
return nid;
}
@@ -251,26 +294,10 @@ int of_node_to_nid(struct device_node *device)
}
EXPORT_SYMBOL_GPL(of_node_to_nid);
-/*
- * In theory, the "ibm,associativity" property may contain multiple
- * associativity lists because a resource may be multiply connected
- * into the machine. This resource then has different associativity
- * characteristics relative to its multiple connections. We ignore
- * this for now. We also assume that all cpu and memory sets have
- * their distances represented at a common level. This won't be
- * true for hierarchical NUMA.
- *
- * In any case the ibm,associativity-reference-points should give
- * the correct depth for a normal NUMA system.
- *
- * - Dave Hansen <haveblue@us.ibm.com>
- */
static int __init find_min_common_depth(void)
{
- int depth, index;
- const unsigned int *ref_points;
+ int depth;
struct device_node *rtas_root;
- unsigned int len;
struct device_node *chosen;
const char *vec5;
@@ -280,18 +307,28 @@ static int __init find_min_common_depth(void)
return -1;
/*
- * this property is 2 32-bit integers, each representing a level of
- * depth in the associativity nodes. The first is for an SMP
- * configuration (should be all 0's) and the second is for a normal
- * NUMA configuration.
+ * This property is a set of 32-bit integers, each representing
+ * an index into the ibm,associativity nodes.
+ *
+ * With form 0 affinity the first integer is for an SMP configuration
+ * (should be all 0's) and the second is for a normal NUMA
+ * configuration. We have only one level of NUMA.
+ *
+ * With form 1 affinity the first integer is the most significant
+ * NUMA boundary and the following are progressively less significant
+ * boundaries. There can be more than one level of NUMA.
*/
- index = 1;
- ref_points = of_get_property(rtas_root,
- "ibm,associativity-reference-points", &len);
+ distance_ref_points = of_get_property(rtas_root,
+ "ibm,associativity-reference-points",
+ &distance_ref_points_depth);
+
+ if (!distance_ref_points) {
+ dbg("NUMA: ibm,associativity-reference-points not found.\n");
+ goto err;
+ }
+
+ distance_ref_points_depth /= sizeof(int);
- /*
- * For form 1 affinity information we want the first field
- */
#define VEC5_AFFINITY_BYTE 5
#define VEC5_AFFINITY 0x80
chosen = of_find_node_by_path("/chosen");
@@ -299,19 +336,38 @@ static int __init find_min_common_depth(void)
vec5 = of_get_property(chosen, "ibm,architecture-vec-5", NULL);
if (vec5 && (vec5[VEC5_AFFINITY_BYTE] & VEC5_AFFINITY)) {
dbg("Using form 1 affinity\n");
- index = 0;
+ form1_affinity = 1;
}
}
- if ((len >= 2 * sizeof(unsigned int)) && ref_points) {
- depth = ref_points[index];
+ if (form1_affinity) {
+ depth = distance_ref_points[0];
} else {
- dbg("NUMA: ibm,associativity-reference-points not found.\n");
- depth = -1;
+ if (distance_ref_points_depth < 2) {
+ printk(KERN_WARNING "NUMA: "
+ "short ibm,associativity-reference-points\n");
+ goto err;
+ }
+
+ depth = distance_ref_points[1];
}
- of_node_put(rtas_root);
+ /*
+ * Warn and cap if the hardware supports more than
+ * MAX_DISTANCE_REF_POINTS domains.
+ */
+ if (distance_ref_points_depth > MAX_DISTANCE_REF_POINTS) {
+ printk(KERN_WARNING "NUMA: distance array capped at "
+ "%d entries\n", MAX_DISTANCE_REF_POINTS);
+ distance_ref_points_depth = MAX_DISTANCE_REF_POINTS;
+ }
+
+ of_node_put(rtas_root);
return depth;
+
+err:
+ of_node_put(rtas_root);
+ return -1;
}
static void __init get_n_mem_cells(int *n_addr_cells, int *n_size_cells)