On Fri, 2010-04-30 at 14:43 +1000, Anton Blanchard wrote:
> Form 1 affinity allows multiple entries in ibm,associativity-reference-points
> which represent affinity domains in decreasing order of importance. The
> Linux concept of a node is always the first entry, but using the other
> values as an input to node_distance() allows the memory allocator to make
> better decisions on which node to go first when local memory has been
> exhausted.
>
> We keep things simple and create an array indexed by NUMA node, capped at
> 4 entries. Each time we lookup an associativity property we initialise
> the array which is overkill, but since we should only hit this path during
> boot it didn't seem worth adding a per node valid bit.
Ok, so pls dbl check my -next branch (I'm pushing a new one out today
hopefully) and respin :-) 1 and 2 seem to be already there and 3 doesn't
apply (non-trivial).
Thanks !
Cheers,
Ben.
> Signed-off-by: Anton Blanchard <an...@samba.org>
> ---
>
> Index: linux-2.6/arch/powerpc/include/asm/topology.h
> ===================================================================
> --- linux-2.6.orig/arch/powerpc/include/asm/topology.h 2010-04-29
> 15:58:58.000000000 +1000
> +++ linux-2.6/arch/powerpc/include/asm/topology.h 2010-04-29
> 15:59:00.000000000 +1000
> @@ -77,6 +77,9 @@ static inline int pcibus_to_node(struct
> .balance_interval = 1, \
> }
>
> +extern int __node_distance(int, int);
> +#define node_distance(a, b) __node_distance(a, b)
> +
> extern void __init dump_numa_cpu_topology(void);
>
> extern int sysfs_add_device_to_node(struct sys_device *dev, int nid);
> Index: linux-2.6/arch/powerpc/mm/numa.c
> ===================================================================
> --- linux-2.6.orig/arch/powerpc/mm/numa.c 2010-04-29 15:58:59.000000000
> +1000
> +++ linux-2.6/arch/powerpc/mm/numa.c 2010-04-29 22:05:24.000000000 +1000
> @@ -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];
>
> static int __cpuinit fake_numa_create_new_node(unsigned long end_pfn,
> unsigned int *nid)
> @@ -179,6 +185,39 @@ static const u32 *of_get_usable_memory(s
> 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.
> */
> @@ -200,6 +239,10 @@ static int of_node_to_nid_single(struct
> /* 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;
> }
> @@ -226,26 +269,10 @@ int of_node_to_nid(struct device_node *d
> }
> 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 <haveb...@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 *options;
>
> rtas_root = of_find_node_by_path("/rtas");
> @@ -254,35 +281,62 @@ static int __init find_min_common_depth(
> 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)
> + goto err;
> +
> + distance_ref_points_depth /= sizeof(int);
>
> - /*
> - * For type 1 affinity information we want the first field
> - */
> options = of_find_node_by_path("/options");
> if (options) {
> const char *str;
> str = of_get_property(options, "ibm,associativity-form", NULL);
> if (str && !strcmp(str, "1"))
> - 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)
> + goto err;
> +
> + depth = distance_ref_points[1];
> }
> +
> + /*
> + * 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:
> + dbg("NUMA: ibm,associativity-reference-points not found.\n");
> + of_node_put(rtas_root);
> + return -1;
> }
>
> static void __init get_n_mem_cells(int *n_addr_cells, int *n_size_cells)
_______________________________________________
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev
