[PATCH v7 0/6] Add support for FORM2 associativity

[PATCH v7 0/6] Add support for FORM2 associativity

[Aneesh Kumar K.V]

Form2 associativity adds a much more flexible NUMA topology layout
than what is provided by Form1. More details can be found in patch 7.

$ numactl -H
...
node distances:
node   0   1   2   3 
  0:  10  11  222  33 
  1:  44  10  55  66 
  2:  77  88  10  99 
  3:  101  121  132  10 
$

After DAX kmem memory add
# numactl -H
available: 5 nodes (0-4)
...
node distances:
node   0   1   2   3   4 
  0:  10  11  222  33  240 
  1:  44  10  55  66  255 
  2:  77  88  10  99  255 
  3:  101  121  132  10  230 
  4:  255  255  255  230  10 


PAPR SCM now use the numa distance details to find the numa_node and target_node
for the device.

kvaneesh@ubuntu-guest:~$ ndctl  list -N -v 
[
  {
    "dev":"namespace0.0",
    "mode":"devdax",
    "map":"dev",
    "size":1071644672,
    "uuid":"d333d867-3f57-44c8-b386-d4d3abdc2bf2",
    "raw_uuid":"915361ad-fe6a-42dd-848f-d6dc9f5af362",
    "daxregion":{
      "id":0,
      "size":1071644672,
      "devices":[
        {
          "chardev":"dax0.0",
          "size":1071644672,
          "target_node":4,
          "mode":"devdax"
        }
      ]
    },
    "align":2097152,
    "numa_node":3
  }
]
kvaneesh@ubuntu-guest:~$ 


The above output is with a Qemu command line

-numa node,nodeid=4 \
-numa dist,src=0,dst=1,val=11 -numa dist,src=0,dst=2,val=222 -numa dist,src=0,dst=3,val=33 -numa dist,src=0,dst=4,val=240 \
-numa dist,src=1,dst=0,val=44 -numa dist,src=1,dst=2,val=55 -numa dist,src=1,dst=3,val=66 -numa dist,src=1,dst=4,val=255 \
-numa dist,src=2,dst=0,val=77 -numa dist,src=2,dst=1,val=88 -numa dist,src=2,dst=3,val=99 -numa dist,src=2,dst=4,val=255 \
-numa dist,src=3,dst=0,val=101 -numa dist,src=3,dst=1,val=121 -numa dist,src=3,dst=2,val=132 -numa dist,src=3,dst=4,val=230 \
-numa dist,src=4,dst=0,val=255 -numa dist,src=4,dst=1,val=255 -numa dist,src=4,dst=2,val=255 -numa dist,src=4,dst=3,val=230 \
-object memory-backend-file,id=memnvdimm1,prealloc=yes,mem-path=$PMEM_DISK,share=yes,size=${PMEM_SIZE}  \
-device nvdimm,label-size=128K,memdev=memnvdimm1,id=nvdimm1,slot=4,uuid=72511b67-0b3b-42fd-8d1d-5be3cae8bcaa,node=4

Qemu changes can be found at https://lore.kernel.org/qemu-devel/20210616011944.2996399-1-danielhb413@gmail.com/

Changes from v6:
* Address review feedback 

Changes from v5:
* Fix build error reported by kernel test robot
* Address review feedback 

Changes from v4:
* Drop DLPAR related device tree property for now because both Qemu nor PowerVM
  will provide the distance details of all possible NUMA nodes during boot.
* Rework numa distance code based on review feedback.

Changes from v3:
* Drop PAPR SCM specific changes and depend completely on NUMA distance information.

Changes from v2:
* Add nvdimm list to Cc:
* update PATCH 8 commit message.

Changes from v1:
* Update FORM2 documentation.
* rename max_domain_index to max_associativity_domain_index


Aneesh Kumar K.V (6):
  powerpc/pseries: rename min_common_depth to primary_domain_index
  powerpc/pseries: Rename TYPE1_AFFINITY to FORM1_AFFINITY
  powerpc/pseries: Consolidate different NUMA distance update code paths
  powerpc/pseries: Add a helper for form1 cpu distance
  powerpc/pseries: Add support for FORM2 associativity
  powerpc/pseries: Consolidate form1 distance initialization into a
    helper

 Documentation/powerpc/associativity.rst       | 103 +++++
 arch/powerpc/include/asm/firmware.h           |   7 +-
 arch/powerpc/include/asm/prom.h               |   3 +-
 arch/powerpc/include/asm/topology.h           |   6 +-
 arch/powerpc/kernel/prom_init.c               |   3 +-
 arch/powerpc/mm/numa.c                        | 433 ++++++++++++++----
 arch/powerpc/platforms/pseries/firmware.c     |   3 +-
 arch/powerpc/platforms/pseries/hotplug-cpu.c  |   2 +
 .../platforms/pseries/hotplug-memory.c        |   2 +
 arch/powerpc/platforms/pseries/lpar.c         |   4 +-
 10 files changed, 455 insertions(+), 111 deletions(-)
 create mode 100644 Documentation/powerpc/associativity.rst

-- 
2.31.1

[PATCH v7 1/6] powerpc/pseries: rename min_common_depth to primary_domain_index

[Aneesh Kumar K.V]

No functional change in this patch.

Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 arch/powerpc/mm/numa.c | 38 +++++++++++++++++++-------------------
 1 file changed, 19 insertions(+), 19 deletions(-)

diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index f2bf98bdcea2..8365b298ec48 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -51,7 +51,7 @@ EXPORT_SYMBOL(numa_cpu_lookup_table);
 EXPORT_SYMBOL(node_to_cpumask_map);
 EXPORT_SYMBOL(node_data);
 
-static int min_common_depth;
+static int primary_domain_index;
 static int n_mem_addr_cells, n_mem_size_cells;
 static int form1_affinity;
 
@@ -232,8 +232,8 @@ static int associativity_to_nid(const __be32 *associativity)
 	if (!numa_enabled)
 		goto out;
 
-	if (of_read_number(associativity, 1) >= min_common_depth)
-		nid = of_read_number(&associativity[min_common_depth], 1);
+	if (of_read_number(associativity, 1) >= primary_domain_index)
+		nid = of_read_number(&associativity[primary_domain_index], 1);
 
 	/* POWER4 LPAR uses 0xffff as invalid node */
 	if (nid == 0xffff || nid >= nr_node_ids)
@@ -284,9 +284,9 @@ int of_node_to_nid(struct device_node *device)
 }
 EXPORT_SYMBOL(of_node_to_nid);
 
-static int __init find_min_common_depth(void)
+static int __init find_primary_domain_index(void)
 {
-	int depth;
+	int index;
 	struct device_node *root;
 
 	if (firmware_has_feature(FW_FEATURE_OPAL))
@@ -326,7 +326,7 @@ static int __init find_min_common_depth(void)
 	}
 
 	if (form1_affinity) {
-		depth = of_read_number(distance_ref_points, 1);
+		index = of_read_number(distance_ref_points, 1);
 	} else {
 		if (distance_ref_points_depth < 2) {
 			printk(KERN_WARNING "NUMA: "
@@ -334,7 +334,7 @@ static int __init find_min_common_depth(void)
 			goto err;
 		}
 
-		depth = of_read_number(&distance_ref_points[1], 1);
+		index = of_read_number(&distance_ref_points[1], 1);
 	}
 
 	/*
@@ -348,7 +348,7 @@ static int __init find_min_common_depth(void)
 	}
 
 	of_node_put(root);
-	return depth;
+	return index;
 
 err:
 	of_node_put(root);
@@ -437,16 +437,16 @@ int of_drconf_to_nid_single(struct drmem_lmb *lmb)
 	int nid = default_nid;
 	int rc, index;
 
-	if ((min_common_depth < 0) || !numa_enabled)
+	if ((primary_domain_index < 0) || !numa_enabled)
 		return default_nid;
 
 	rc = of_get_assoc_arrays(&aa);
 	if (rc)
 		return default_nid;
 
-	if (min_common_depth <= aa.array_sz &&
+	if (primary_domain_index <= aa.array_sz &&
 	    !(lmb->flags & DRCONF_MEM_AI_INVALID) && lmb->aa_index < aa.n_arrays) {
-		index = lmb->aa_index * aa.array_sz + min_common_depth - 1;
+		index = lmb->aa_index * aa.array_sz + primary_domain_index - 1;
 		nid = of_read_number(&aa.arrays[index], 1);
 
 		if (nid == 0xffff || nid >= nr_node_ids)
@@ -708,18 +708,18 @@ static int __init parse_numa_properties(void)
 		return -1;
 	}
 
-	min_common_depth = find_min_common_depth();
+	primary_domain_index = find_primary_domain_index();
 
-	if (min_common_depth < 0) {
+	if (primary_domain_index < 0) {
 		/*
-		 * if we fail to parse min_common_depth from device tree
+		 * if we fail to parse primary_domain_index from device tree
 		 * mark the numa disabled, boot with numa disabled.
 		 */
 		numa_enabled = false;
-		return min_common_depth;
+		return primary_domain_index;
 	}
 
-	dbg("NUMA associativity depth for CPU/Memory: %d\n", min_common_depth);
+	dbg("NUMA associativity depth for CPU/Memory: %d\n", primary_domain_index);
 
 	/*
 	 * Even though we connect cpus to numa domains later in SMP
@@ -919,14 +919,14 @@ static void __init find_possible_nodes(void)
 			goto out;
 	}
 
-	max_nodes = of_read_number(&domains[min_common_depth], 1);
+	max_nodes = of_read_number(&domains[primary_domain_index], 1);
 	for (i = 0; i < max_nodes; i++) {
 		if (!node_possible(i))
 			node_set(i, node_possible_map);
 	}
 
 	prop_length /= sizeof(int);
-	if (prop_length > min_common_depth + 2)
+	if (prop_length > primary_domain_index + 2)
 		coregroup_enabled = 1;
 
 out:
@@ -1259,7 +1259,7 @@ int cpu_to_coregroup_id(int cpu)
 		goto out;
 
 	index = of_read_number(associativity, 1);
-	if (index > min_common_depth + 1)
+	if (index > primary_domain_index + 1)
 		return of_read_number(&associativity[index - 1], 1);
 
 out:
-- 
2.31.1

[PATCH v7 2/6] powerpc/pseries: Rename TYPE1_AFFINITY to FORM1_AFFINITY

[Aneesh Kumar K.V]

Also make related code cleanup that will allow adding FORM2_AFFINITY in
later patches. No functional change in this patch.

Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 arch/powerpc/include/asm/firmware.h       |  4 +--
 arch/powerpc/include/asm/prom.h           |  2 +-
 arch/powerpc/kernel/prom_init.c           |  2 +-
 arch/powerpc/mm/numa.c                    | 35 ++++++++++++++---------
 arch/powerpc/platforms/pseries/firmware.c |  2 +-
 5 files changed, 26 insertions(+), 19 deletions(-)

diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h
index 7604673787d6..60b631161360 100644
--- a/arch/powerpc/include/asm/firmware.h
+++ b/arch/powerpc/include/asm/firmware.h
@@ -44,7 +44,7 @@
 #define FW_FEATURE_OPAL		ASM_CONST(0x0000000010000000)
 #define FW_FEATURE_SET_MODE	ASM_CONST(0x0000000040000000)
 #define FW_FEATURE_BEST_ENERGY	ASM_CONST(0x0000000080000000)
-#define FW_FEATURE_TYPE1_AFFINITY ASM_CONST(0x0000000100000000)
+#define FW_FEATURE_FORM1_AFFINITY ASM_CONST(0x0000000100000000)
 #define FW_FEATURE_PRRN		ASM_CONST(0x0000000200000000)
 #define FW_FEATURE_DRMEM_V2	ASM_CONST(0x0000000400000000)
 #define FW_FEATURE_DRC_INFO	ASM_CONST(0x0000000800000000)
@@ -69,7 +69,7 @@ enum {
 		FW_FEATURE_SPLPAR | FW_FEATURE_LPAR |
 		FW_FEATURE_CMO | FW_FEATURE_VPHN | FW_FEATURE_XCMO |
 		FW_FEATURE_SET_MODE | FW_FEATURE_BEST_ENERGY |
-		FW_FEATURE_TYPE1_AFFINITY | FW_FEATURE_PRRN |
+		FW_FEATURE_FORM1_AFFINITY | FW_FEATURE_PRRN |
 		FW_FEATURE_HPT_RESIZE | FW_FEATURE_DRMEM_V2 |
 		FW_FEATURE_DRC_INFO | FW_FEATURE_BLOCK_REMOVE |
 		FW_FEATURE_PAPR_SCM | FW_FEATURE_ULTRAVISOR |
diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index 324a13351749..df9fec9d232c 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -147,7 +147,7 @@ extern int of_read_drc_info_cell(struct property **prop,
 #define OV5_MSI			0x0201	/* PCIe/MSI support */
 #define OV5_CMO			0x0480	/* Cooperative Memory Overcommitment */
 #define OV5_XCMO		0x0440	/* Page Coalescing */
-#define OV5_TYPE1_AFFINITY	0x0580	/* Type 1 NUMA affinity */
+#define OV5_FORM1_AFFINITY	0x0580	/* FORM1 NUMA affinity */
 #define OV5_PRRN		0x0540	/* Platform Resource Reassignment */
 #define OV5_HP_EVT		0x0604	/* Hot Plug Event support */
 #define OV5_RESIZE_HPT		0x0601	/* Hash Page Table resizing */
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index a5bf355ce1d6..57db605ad33a 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -1096,7 +1096,7 @@ static const struct ibm_arch_vec ibm_architecture_vec_template __initconst = {
 #else
 		0,
 #endif
-		.associativity = OV5_FEAT(OV5_TYPE1_AFFINITY) | OV5_FEAT(OV5_PRRN),
+		.associativity = OV5_FEAT(OV5_FORM1_AFFINITY) | OV5_FEAT(OV5_PRRN),
 		.bin_opts = OV5_FEAT(OV5_RESIZE_HPT) | OV5_FEAT(OV5_HP_EVT),
 		.micro_checkpoint = 0,
 		.reserved0 = 0,
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 8365b298ec48..368719b14dcc 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -53,7 +53,10 @@ EXPORT_SYMBOL(node_data);
 
 static int primary_domain_index;
 static int n_mem_addr_cells, n_mem_size_cells;
-static int form1_affinity;
+
+#define FORM0_AFFINITY 0
+#define FORM1_AFFINITY 1
+static int affinity_form;
 
 #define MAX_DISTANCE_REF_POINTS 4
 static int distance_ref_points_depth;
@@ -190,7 +193,7 @@ int __node_distance(int a, int b)
 	int i;
 	int distance = LOCAL_DISTANCE;
 
-	if (!form1_affinity)
+	if (affinity_form == FORM0_AFFINITY)
 		return ((a == b) ? LOCAL_DISTANCE : REMOTE_DISTANCE);
 
 	for (i = 0; i < distance_ref_points_depth; i++) {
@@ -210,7 +213,7 @@ static void initialize_distance_lookup_table(int nid,
 {
 	int i;
 
-	if (!form1_affinity)
+	if (affinity_form != FORM1_AFFINITY)
 		return;
 
 	for (i = 0; i < distance_ref_points_depth; i++) {
@@ -289,6 +292,17 @@ static int __init find_primary_domain_index(void)
 	int index;
 	struct device_node *root;
 
+	/*
+	 * Check for which form of affinity.
+	 */
+	if (firmware_has_feature(FW_FEATURE_OPAL)) {
+		affinity_form = FORM1_AFFINITY;
+	} else if (firmware_has_feature(FW_FEATURE_FORM1_AFFINITY)) {
+		dbg("Using form 1 affinity\n");
+		affinity_form = FORM1_AFFINITY;
+	} else
+		affinity_form = FORM0_AFFINITY;
+
 	if (firmware_has_feature(FW_FEATURE_OPAL))
 		root = of_find_node_by_path("/ibm,opal");
 	else
@@ -318,23 +332,16 @@ static int __init find_primary_domain_index(void)
 	}
 
 	distance_ref_points_depth /= sizeof(int);
-
-	if (firmware_has_feature(FW_FEATURE_OPAL) ||
-	    firmware_has_feature(FW_FEATURE_TYPE1_AFFINITY)) {
-		dbg("Using form 1 affinity\n");
-		form1_affinity = 1;
-	}
-
-	if (form1_affinity) {
-		index = of_read_number(distance_ref_points, 1);
-	} else {
+	if (affinity_form == FORM0_AFFINITY) {
 		if (distance_ref_points_depth < 2) {
 			printk(KERN_WARNING "NUMA: "
-				"short ibm,associativity-reference-points\n");
+			       "short ibm,associativity-reference-points\n");
 			goto err;
 		}
 
 		index = of_read_number(&distance_ref_points[1], 1);
+	} else {
+		index = of_read_number(distance_ref_points, 1);
 	}
 
 	/*
diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c
index 4c7b7f5a2ebc..5d4c2bc20bba 100644
--- a/arch/powerpc/platforms/pseries/firmware.c
+++ b/arch/powerpc/platforms/pseries/firmware.c
@@ -119,7 +119,7 @@ struct vec5_fw_feature {
 
 static __initdata struct vec5_fw_feature
 vec5_fw_features_table[] = {
-	{FW_FEATURE_TYPE1_AFFINITY,	OV5_TYPE1_AFFINITY},
+	{FW_FEATURE_FORM1_AFFINITY,	OV5_FORM1_AFFINITY},
 	{FW_FEATURE_PRRN,		OV5_PRRN},
 	{FW_FEATURE_DRMEM_V2,		OV5_DRMEM_V2},
 	{FW_FEATURE_DRC_INFO,		OV5_DRC_INFO},
-- 
2.31.1

[PATCH v7 3/6] powerpc/pseries: Consolidate different NUMA distance update code paths

[Aneesh Kumar K.V]

The associativity details of the newly added resourced are collected from
the hypervisor via "ibm,configure-connector" rtas call. Update the numa
distance details of the newly added numa node after the above call.

Instead of updating NUMA distance every time we lookup a node id
from the associativity property, add helpers that can be used
during boot which does this only once. Also remove the distance
update from node id lookup helpers.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 arch/powerpc/include/asm/topology.h           |   2 +
 arch/powerpc/mm/numa.c                        | 178 +++++++++++++-----
 arch/powerpc/platforms/pseries/hotplug-cpu.c  |   2 +
 .../platforms/pseries/hotplug-memory.c        |   2 +
 4 files changed, 138 insertions(+), 46 deletions(-)

diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index e4db64c0e184..a6425a70c37b 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -64,6 +64,7 @@ static inline int early_cpu_to_node(int cpu)
 }
 
 int of_drconf_to_nid_single(struct drmem_lmb *lmb);
+void update_numa_distance(struct device_node *node);
 
 #else
 
@@ -93,6 +94,7 @@ static inline int of_drconf_to_nid_single(struct drmem_lmb *lmb)
 	return first_online_node;
 }
 
+static inline void update_numa_distance(struct device_node *node) {}
 #endif /* CONFIG_NUMA */
 
 #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR)
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 368719b14dcc..c695faf67d68 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -208,22 +208,6 @@ int __node_distance(int a, int b)
 }
 EXPORT_SYMBOL(__node_distance);
 
-static void initialize_distance_lookup_table(int nid,
-		const __be32 *associativity)
-{
-	int i;
-
-	if (affinity_form != FORM1_AFFINITY)
-		return;
-
-	for (i = 0; i < distance_ref_points_depth; i++) {
-		const __be32 *entry;
-
-		entry = &associativity[be32_to_cpu(distance_ref_points[i]) - 1];
-		distance_lookup_table[nid][i] = of_read_number(entry, 1);
-	}
-}
-
 /*
  * Returns nid in the range [0..nr_node_ids], or -1 if no useful NUMA
  * info is found.
@@ -241,15 +225,6 @@ static int associativity_to_nid(const __be32 *associativity)
 	/* POWER4 LPAR uses 0xffff as invalid node */
 	if (nid == 0xffff || nid >= nr_node_ids)
 		nid = NUMA_NO_NODE;
-
-	if (nid > 0 &&
-		of_read_number(associativity, 1) >= distance_ref_points_depth) {
-		/*
-		 * Skip the length field and send start of associativity array
-		 */
-		initialize_distance_lookup_table(nid, associativity + 1);
-	}
-
 out:
 	return nid;
 }
@@ -287,6 +262,48 @@ int of_node_to_nid(struct device_node *device)
 }
 EXPORT_SYMBOL(of_node_to_nid);
 
+static void __initialize_form1_numa_distance(const __be32 *associativity)
+{
+	int i, nid;
+
+	if (affinity_form != FORM1_AFFINITY)
+		return;
+
+	nid = associativity_to_nid(associativity);
+	if (nid != NUMA_NO_NODE) {
+		for (i = 0; i < distance_ref_points_depth; i++) {
+			const __be32 *entry;
+
+			entry = &associativity[be32_to_cpu(distance_ref_points[i])];
+			distance_lookup_table[nid][i] = of_read_number(entry, 1);
+		}
+	}
+}
+
+static void initialize_form1_numa_distance(struct device_node *node)
+{
+	const __be32 *associativity;
+
+	associativity = of_get_associativity(node);
+	if (!associativity)
+		return;
+
+	__initialize_form1_numa_distance(associativity);
+}
+
+/*
+ * Used to update distance information w.r.t newly added node.
+ */
+void update_numa_distance(struct device_node *node)
+{
+	if (affinity_form == FORM0_AFFINITY)
+		return;
+	else if (affinity_form == FORM1_AFFINITY) {
+		initialize_form1_numa_distance(node);
+		return;
+	}
+}
+
 static int __init find_primary_domain_index(void)
 {
 	int index;
@@ -433,6 +450,48 @@ static int of_get_assoc_arrays(struct assoc_arrays *aa)
 	return 0;
 }
 
+static int get_nid_and_numa_distance(struct drmem_lmb *lmb)
+{
+	struct assoc_arrays aa = { .arrays = NULL };
+	int default_nid = NUMA_NO_NODE;
+	int nid = default_nid;
+	int rc, index;
+
+	if ((primary_domain_index < 0) || !numa_enabled)
+		return default_nid;
+
+	rc = of_get_assoc_arrays(&aa);
+	if (rc)
+		return default_nid;
+
+	if (primary_domain_index <= aa.array_sz &&
+	    !(lmb->flags & DRCONF_MEM_AI_INVALID) && lmb->aa_index < aa.n_arrays) {
+		index = lmb->aa_index * aa.array_sz + primary_domain_index - 1;
+		nid = of_read_number(&aa.arrays[index], 1);
+
+		if (nid == 0xffff || nid >= nr_node_ids)
+			nid = default_nid;
+		if (nid > 0 && affinity_form == FORM1_AFFINITY) {
+			int i;
+			const __be32 *associativity;
+
+			index = lmb->aa_index * aa.array_sz;
+			associativity = &aa.arrays[index];
+			/*
+			 * lookup array associativity entries have different format
+			 * There is no length of the array as the first element.
+			 */
+			for (i = 0; i < distance_ref_points_depth; i++) {
+				const __be32 *entry;
+
+				entry = &associativity[be32_to_cpu(distance_ref_points[i]) - 1];
+				distance_lookup_table[nid][i] = of_read_number(entry, 1);
+			}
+		}
+	}
+	return nid;
+}
+
 /*
  * This is like of_node_to_nid_single() for memory represented in the
  * ibm,dynamic-reconfiguration-memory node.
@@ -458,21 +517,14 @@ int of_drconf_to_nid_single(struct drmem_lmb *lmb)
 
 		if (nid == 0xffff || nid >= nr_node_ids)
 			nid = default_nid;
-
-		if (nid > 0) {
-			index = lmb->aa_index * aa.array_sz;
-			initialize_distance_lookup_table(nid,
-							&aa.arrays[index]);
-		}
 	}
-
 	return nid;
 }
 
 #ifdef CONFIG_PPC_SPLPAR
-static int vphn_get_nid(long lcpu)
+
+static int __vphn_get_associativity(long lcpu, __be32 *associativity)
 {
-	__be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
 	long rc, hwid;
 
 	/*
@@ -492,12 +544,30 @@ static int vphn_get_nid(long lcpu)
 
 		rc = hcall_vphn(hwid, VPHN_FLAG_VCPU, associativity);
 		if (rc == H_SUCCESS)
-			return associativity_to_nid(associativity);
+			return 0;
 	}
 
+	return -1;
+}
+
+static int vphn_get_nid(long lcpu)
+{
+	__be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
+
+
+	if (!__vphn_get_associativity(lcpu, associativity))
+		return associativity_to_nid(associativity);
+
 	return NUMA_NO_NODE;
+
 }
 #else
+
+static int __vphn_get_associativity(long lcpu, __be32 *associativity)
+{
+	return -1;
+}
+
 static int vphn_get_nid(long unused)
 {
 	return NUMA_NO_NODE;
@@ -692,7 +762,7 @@ static int __init numa_setup_drmem_lmb(struct drmem_lmb *lmb,
 			size = read_n_cells(n_mem_size_cells, usm);
 		}
 
-		nid = of_drconf_to_nid_single(lmb);
+		nid = get_nid_and_numa_distance(lmb);
 		fake_numa_create_new_node(((base + size) >> PAGE_SHIFT),
 					  &nid);
 		node_set_online(nid);
@@ -709,6 +779,7 @@ static int __init parse_numa_properties(void)
 	struct device_node *memory;
 	int default_nid = 0;
 	unsigned long i;
+	const __be32 *associativity;
 
 	if (numa_enabled == 0) {
 		printk(KERN_WARNING "NUMA disabled by user\n");
@@ -734,18 +805,30 @@ static int __init parse_numa_properties(void)
 	 * each node to be onlined must have NODE_DATA etc backing it.
 	 */
 	for_each_present_cpu(i) {
+		__be32 vphn_assoc[VPHN_ASSOC_BUFSIZE];
 		struct device_node *cpu;
-		int nid = vphn_get_nid(i);
+		int nid = NUMA_NO_NODE;
 
-		/*
-		 * Don't fall back to default_nid yet -- we will plug
-		 * cpus into nodes once the memory scan has discovered
-		 * the topology.
-		 */
-		if (nid == NUMA_NO_NODE) {
+		memset(vphn_assoc, 0, VPHN_ASSOC_BUFSIZE * sizeof(__be32));
+
+		if (__vphn_get_associativity(i, vphn_assoc) == 0) {
+			nid = associativity_to_nid(vphn_assoc);
+			__initialize_form1_numa_distance(vphn_assoc);
+		} else {
+
+			/*
+			 * Don't fall back to default_nid yet -- we will plug
+			 * cpus into nodes once the memory scan has discovered
+			 * the topology.
+			 */
 			cpu = of_get_cpu_node(i, NULL);
 			BUG_ON(!cpu);
-			nid = of_node_to_nid_single(cpu);
+
+			associativity = of_get_associativity(cpu);
+			if (associativity) {
+				nid = associativity_to_nid(associativity);
+				__initialize_form1_numa_distance(associativity);
+			}
 			of_node_put(cpu);
 		}
 
@@ -781,8 +864,11 @@ static int __init parse_numa_properties(void)
 		 * have associativity properties.  If none, then
 		 * everything goes to default_nid.
 		 */
-		nid = of_node_to_nid_single(memory);
-		if (nid < 0)
+		associativity = of_get_associativity(memory);
+		if (associativity) {
+			nid = associativity_to_nid(associativity);
+			__initialize_form1_numa_distance(associativity);
+		} else
 			nid = default_nid;
 
 		fake_numa_create_new_node(((start + size) >> PAGE_SHIFT), &nid);
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 7e970f81d8ff..778b6ab35f0d 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -498,6 +498,8 @@ static ssize_t dlpar_cpu_add(u32 drc_index)
 		return saved_rc;
 	}
 
+	update_numa_distance(dn);
+
 	rc = dlpar_online_cpu(dn);
 	if (rc) {
 		saved_rc = rc;
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 377d852f5a9a..ee1d81d7e54a 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -180,6 +180,8 @@ static int update_lmb_associativity_index(struct drmem_lmb *lmb)
 		return -ENODEV;
 	}
 
+	update_numa_distance(lmb_node);
+
 	dr_node = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
 	if (!dr_node) {
 		dlpar_free_cc_nodes(lmb_node);
-- 
2.31.1

Re: [PATCH v7 3/6] powerpc/pseries: Consolidate different NUMA distance update code paths

[David Gibson]

[-- Attachment #1: Type: text/plain, Size: 11592 bytes --]

On Mon, Aug 09, 2021 at 10:54:31AM +0530, Aneesh Kumar K.V wrote:
> The associativity details of the newly added resourced are collected from
> the hypervisor via "ibm,configure-connector" rtas call. Update the numa
> distance details of the newly added numa node after the above call.
> 
> Instead of updating NUMA distance every time we lookup a node id
> from the associativity property, add helpers that can be used
> during boot which does this only once. Also remove the distance
> update from node id lookup helpers.
> 
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>

It would make review easier if you'd folded the fixes/cleanups from
6/6 in here, rather than having them separate.

> ---
>  arch/powerpc/include/asm/topology.h           |   2 +
>  arch/powerpc/mm/numa.c                        | 178 +++++++++++++-----
>  arch/powerpc/platforms/pseries/hotplug-cpu.c  |   2 +
>  .../platforms/pseries/hotplug-memory.c        |   2 +
>  4 files changed, 138 insertions(+), 46 deletions(-)
> 
> diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
> index e4db64c0e184..a6425a70c37b 100644
> --- a/arch/powerpc/include/asm/topology.h
> +++ b/arch/powerpc/include/asm/topology.h
> @@ -64,6 +64,7 @@ static inline int early_cpu_to_node(int cpu)
>  }
>  
>  int of_drconf_to_nid_single(struct drmem_lmb *lmb);
> +void update_numa_distance(struct device_node *node);
>  
>  #else
>  
> @@ -93,6 +94,7 @@ static inline int of_drconf_to_nid_single(struct drmem_lmb *lmb)
>  	return first_online_node;
>  }
>  
> +static inline void update_numa_distance(struct device_node *node) {}
>  #endif /* CONFIG_NUMA */
>  
>  #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR)
> diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
> index 368719b14dcc..c695faf67d68 100644
> --- a/arch/powerpc/mm/numa.c
> +++ b/arch/powerpc/mm/numa.c
> @@ -208,22 +208,6 @@ int __node_distance(int a, int b)
>  }
>  EXPORT_SYMBOL(__node_distance);
>  
> -static void initialize_distance_lookup_table(int nid,
> -		const __be32 *associativity)
> -{
> -	int i;
> -
> -	if (affinity_form != FORM1_AFFINITY)
> -		return;
> -
> -	for (i = 0; i < distance_ref_points_depth; i++) {
> -		const __be32 *entry;
> -
> -		entry = &associativity[be32_to_cpu(distance_ref_points[i]) - 1];
> -		distance_lookup_table[nid][i] = of_read_number(entry, 1);
> -	}
> -}
> -
>  /*
>   * Returns nid in the range [0..nr_node_ids], or -1 if no useful NUMA
>   * info is found.
> @@ -241,15 +225,6 @@ static int associativity_to_nid(const __be32 *associativity)
>  	/* POWER4 LPAR uses 0xffff as invalid node */
>  	if (nid == 0xffff || nid >= nr_node_ids)
>  		nid = NUMA_NO_NODE;
> -
> -	if (nid > 0 &&
> -		of_read_number(associativity, 1) >= distance_ref_points_depth) {
> -		/*
> -		 * Skip the length field and send start of associativity array

So.. this highlights a point.  In your comments you're treating
"associativity array" as meaning the value including the length plus
the assoc IDs, but this comment you've removed is treating it as just
the assoc IDs.  Personally I think things become clearer to talk about
if you treat the canonical form of "associativity array" as just the
assoc IDs (with implicit length), then treat the ibm,associativity
properties as containing (length + associativity array).

> -		 */
> -		initialize_distance_lookup_table(nid, associativity + 1);
> -	}
> -
>  out:
>  	return nid;
>  }
> @@ -287,6 +262,48 @@ int of_node_to_nid(struct device_node *device)
>  }
>  EXPORT_SYMBOL(of_node_to_nid);
>  
> +static void __initialize_form1_numa_distance(const __be32 *associativity)
> +{
> +	int i, nid;
> +
> +	if (affinity_form != FORM1_AFFINITY)
> +		return;
> +
> +	nid = associativity_to_nid(associativity);
> +	if (nid != NUMA_NO_NODE) {
> +		for (i = 0; i < distance_ref_points_depth; i++) {
> +			const __be32 *entry;
> +
> +			entry = &associativity[be32_to_cpu(distance_ref_points[i])];

So, here you've now removed all checks that distance_ref_points[i]
doesn't overflow the length of associativity.  It comes back in 6/6,
but it's still not ideal.

> +			distance_lookup_table[nid][i] = of_read_number(entry, 1);
> +		}
> +	}
> +}
> +
> +static void initialize_form1_numa_distance(struct device_node *node)
> +{
> +	const __be32 *associativity;
> +
> +	associativity = of_get_associativity(node);
> +	if (!associativity)
> +		return;
> +
> +	__initialize_form1_numa_distance(associativity);
> +}
> +
> +/*
> + * Used to update distance information w.r.t newly added node.
> + */
> +void update_numa_distance(struct device_node *node)
> +{
> +	if (affinity_form == FORM0_AFFINITY)
> +		return;
> +	else if (affinity_form == FORM1_AFFINITY) {
> +		initialize_form1_numa_distance(node);
> +		return;
> +	}
> +}
> +
>  static int __init find_primary_domain_index(void)
>  {
>  	int index;
> @@ -433,6 +450,48 @@ static int of_get_assoc_arrays(struct assoc_arrays *aa)
>  	return 0;
>  }
>  
> +static int get_nid_and_numa_distance(struct drmem_lmb *lmb)
> +{
> +	struct assoc_arrays aa = { .arrays = NULL };
> +	int default_nid = NUMA_NO_NODE;

There's still no point I can see to this intermediate variable.

> +	int nid = default_nid;
> +	int rc, index;
> +
> +	if ((primary_domain_index < 0) || !numa_enabled)
> +		return default_nid;
> +
> +	rc = of_get_assoc_arrays(&aa);
> +	if (rc)
> +		return default_nid;
> +
> +	if (primary_domain_index <= aa.array_sz &&
> +	    !(lmb->flags & DRCONF_MEM_AI_INVALID) && lmb->aa_index < aa.n_arrays) {
> +		index = lmb->aa_index * aa.array_sz + primary_domain_index - 1;
> +		nid = of_read_number(&aa.arrays[index], 1);
> +
> +		if (nid == 0xffff || nid >= nr_node_ids)
> +			nid = default_nid;
> +		if (nid > 0 && affinity_form == FORM1_AFFINITY) {
> +			int i;
> +			const __be32 *associativity;
> +
> +			index = lmb->aa_index * aa.array_sz;
> +			associativity = &aa.arrays[index];
> +			/*
> +			 * lookup array associativity entries have different format
> +			 * There is no length of the array as the first element.
> +			 */
> +			for (i = 0; i < distance_ref_points_depth; i++) {
> +				const __be32 *entry;
> +
> +				entry = &associativity[be32_to_cpu(distance_ref_points[i]) - 1];
> +				distance_lookup_table[nid][i] = of_read_number(entry, 1);
> +			}
> +		}
> +	}
> +	return nid;
> +}
> +
>  /*
>   * This is like of_node_to_nid_single() for memory represented in the
>   * ibm,dynamic-reconfiguration-memory node.
> @@ -458,21 +517,14 @@ int of_drconf_to_nid_single(struct drmem_lmb *lmb)
>  
>  		if (nid == 0xffff || nid >= nr_node_ids)
>  			nid = default_nid;
> -
> -		if (nid > 0) {
> -			index = lmb->aa_index * aa.array_sz;
> -			initialize_distance_lookup_table(nid,
> -							&aa.arrays[index]);
> -		}
>  	}
> -
>  	return nid;
>  }
>  
>  #ifdef CONFIG_PPC_SPLPAR
> -static int vphn_get_nid(long lcpu)
> +
> +static int __vphn_get_associativity(long lcpu, __be32 *associativity)
>  {
> -	__be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
>  	long rc, hwid;
>  
>  	/*
> @@ -492,12 +544,30 @@ static int vphn_get_nid(long lcpu)
>  
>  		rc = hcall_vphn(hwid, VPHN_FLAG_VCPU, associativity);
>  		if (rc == H_SUCCESS)
> -			return associativity_to_nid(associativity);
> +			return 0;
>  	}
>  
> +	return -1;
> +}
> +
> +static int vphn_get_nid(long lcpu)
> +{
> +	__be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
> +
> +
> +	if (!__vphn_get_associativity(lcpu, associativity))
> +		return associativity_to_nid(associativity);
> +
>  	return NUMA_NO_NODE;
> +
>  }
>  #else
> +
> +static int __vphn_get_associativity(long lcpu, __be32 *associativity)
> +{
> +	return -1;
> +}
> +
>  static int vphn_get_nid(long unused)
>  {
>  	return NUMA_NO_NODE;
> @@ -692,7 +762,7 @@ static int __init numa_setup_drmem_lmb(struct drmem_lmb *lmb,
>  			size = read_n_cells(n_mem_size_cells, usm);
>  		}
>  
> -		nid = of_drconf_to_nid_single(lmb);
> +		nid = get_nid_and_numa_distance(lmb);
>  		fake_numa_create_new_node(((base + size) >> PAGE_SHIFT),
>  					  &nid);
>  		node_set_online(nid);
> @@ -709,6 +779,7 @@ static int __init parse_numa_properties(void)
>  	struct device_node *memory;
>  	int default_nid = 0;
>  	unsigned long i;
> +	const __be32 *associativity;
>  
>  	if (numa_enabled == 0) {
>  		printk(KERN_WARNING "NUMA disabled by user\n");
> @@ -734,18 +805,30 @@ static int __init parse_numa_properties(void)
>  	 * each node to be onlined must have NODE_DATA etc backing it.
>  	 */
>  	for_each_present_cpu(i) {
> +		__be32 vphn_assoc[VPHN_ASSOC_BUFSIZE];
>  		struct device_node *cpu;
> -		int nid = vphn_get_nid(i);
> +		int nid = NUMA_NO_NODE;
>  
> -		/*
> -		 * Don't fall back to default_nid yet -- we will plug
> -		 * cpus into nodes once the memory scan has discovered
> -		 * the topology.
> -		 */
> -		if (nid == NUMA_NO_NODE) {
> +		memset(vphn_assoc, 0, VPHN_ASSOC_BUFSIZE * sizeof(__be32));
> +
> +		if (__vphn_get_associativity(i, vphn_assoc) == 0) {
> +			nid = associativity_to_nid(vphn_assoc);
> +			__initialize_form1_numa_distance(vphn_assoc);
> +		} else {
> +
> +			/*
> +			 * Don't fall back to default_nid yet -- we will plug
> +			 * cpus into nodes once the memory scan has discovered
> +			 * the topology.
> +			 */
>  			cpu = of_get_cpu_node(i, NULL);
>  			BUG_ON(!cpu);
> -			nid = of_node_to_nid_single(cpu);
> +
> +			associativity = of_get_associativity(cpu);
> +			if (associativity) {
> +				nid = associativity_to_nid(associativity);
> +				__initialize_form1_numa_distance(associativity);
> +			}
>  			of_node_put(cpu);
>  		}
>  
> @@ -781,8 +864,11 @@ static int __init parse_numa_properties(void)
>  		 * have associativity properties.  If none, then
>  		 * everything goes to default_nid.
>  		 */
> -		nid = of_node_to_nid_single(memory);
> -		if (nid < 0)
> +		associativity = of_get_associativity(memory);
> +		if (associativity) {
> +			nid = associativity_to_nid(associativity);
> +			__initialize_form1_numa_distance(associativity);
> +		} else
>  			nid = default_nid;
>  
>  		fake_numa_create_new_node(((start + size) >> PAGE_SHIFT), &nid);
> diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
> index 7e970f81d8ff..778b6ab35f0d 100644
> --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
> +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
> @@ -498,6 +498,8 @@ static ssize_t dlpar_cpu_add(u32 drc_index)
>  		return saved_rc;
>  	}
>  
> +	update_numa_distance(dn);
> +
>  	rc = dlpar_online_cpu(dn);
>  	if (rc) {
>  		saved_rc = rc;
> diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
> index 377d852f5a9a..ee1d81d7e54a 100644
> --- a/arch/powerpc/platforms/pseries/hotplug-memory.c
> +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
> @@ -180,6 +180,8 @@ static int update_lmb_associativity_index(struct drmem_lmb *lmb)
>  		return -ENODEV;
>  	}
>  
> +	update_numa_distance(lmb_node);
> +
>  	dr_node = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
>  	if (!dr_node) {
>  		dlpar_free_cc_nodes(lmb_node);

-- 
David Gibson			| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you.  NOT _the_ _other_
				| _way_ _around_!
http://www.ozlabs.org/~dgibson

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

[PATCH v7 4/6] powerpc/pseries: Add a helper for form1 cpu distance

[Aneesh Kumar K.V]

This helper is only used with the dispatch trace log collection.
A later patch will add Form2 affinity support and this change helps
in keeping that simpler. Also add a comment explaining we don't expect
the code to be called with FORM0

Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 arch/powerpc/include/asm/topology.h   |  4 ++--
 arch/powerpc/mm/numa.c                | 10 +++++++++-
 arch/powerpc/platforms/pseries/lpar.c |  4 ++--
 3 files changed, 13 insertions(+), 5 deletions(-)

diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index a6425a70c37b..a4712ecad3e9 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -36,7 +36,7 @@ static inline int pcibus_to_node(struct pci_bus *bus)
 				 cpu_all_mask :				\
 				 cpumask_of_node(pcibus_to_node(bus)))
 
-extern int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc);
+int cpu_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc);
 extern int __node_distance(int, int);
 #define node_distance(a, b) __node_distance(a, b)
 
@@ -84,7 +84,7 @@ static inline void sysfs_remove_device_from_node(struct device *dev,
 
 static inline void update_numa_cpu_lookup_table(unsigned int cpu, int node) {}
 
-static inline int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
+static inline int cpu_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
 {
 	return 0;
 }
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index c695faf67d68..a244398a7766 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -166,7 +166,7 @@ static void unmap_cpu_from_node(unsigned long cpu)
 }
 #endif /* CONFIG_HOTPLUG_CPU || CONFIG_PPC_SPLPAR */
 
-int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
+static int __cpu_form1_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
 {
 	int dist = 0;
 
@@ -182,6 +182,14 @@ int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
 	return dist;
 }
 
+int cpu_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
+{
+	/* We should not get called with FORM0 */
+	VM_WARN_ON(affinity_form == FORM0_AFFINITY);
+
+	return __cpu_form1_relative_distance(cpu1_assoc, cpu2_assoc);
+}
+
 /* must hold reference to node during call */
 static const __be32 *of_get_associativity(struct device_node *dev)
 {
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index dab356e3ff87..afefbdfe768d 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -261,7 +261,7 @@ static int cpu_relative_dispatch_distance(int last_disp_cpu, int cur_disp_cpu)
 	if (!last_disp_cpu_assoc || !cur_disp_cpu_assoc)
 		return -EIO;
 
-	return cpu_distance(last_disp_cpu_assoc, cur_disp_cpu_assoc);
+	return cpu_relative_distance(last_disp_cpu_assoc, cur_disp_cpu_assoc);
 }
 
 static int cpu_home_node_dispatch_distance(int disp_cpu)
@@ -281,7 +281,7 @@ static int cpu_home_node_dispatch_distance(int disp_cpu)
 	if (!disp_cpu_assoc || !vcpu_assoc)
 		return -EIO;
 
-	return cpu_distance(disp_cpu_assoc, vcpu_assoc);
+	return cpu_relative_distance(disp_cpu_assoc, vcpu_assoc);
 }
 
 static void update_vcpu_disp_stat(int disp_cpu)
-- 
2.31.1

[PATCH v7 5/6] powerpc/pseries: Add support for FORM2 associativity

[Aneesh Kumar K.V]

PAPR interface currently supports two different ways of communicating resource
grouping details to the OS. These are referred to as Form 0 and Form 1
associativity grouping. Form 0 is the older format and is now considered
deprecated. This patch adds another resource grouping named FORM2.

Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 Documentation/powerpc/associativity.rst   | 103 +++++++++++++
 arch/powerpc/include/asm/firmware.h       |   3 +-
 arch/powerpc/include/asm/prom.h           |   1 +
 arch/powerpc/kernel/prom_init.c           |   3 +-
 arch/powerpc/mm/numa.c                    | 168 ++++++++++++++++++----
 arch/powerpc/platforms/pseries/firmware.c |   1 +
 6 files changed, 252 insertions(+), 27 deletions(-)
 create mode 100644 Documentation/powerpc/associativity.rst

diff --git a/Documentation/powerpc/associativity.rst b/Documentation/powerpc/associativity.rst
new file mode 100644
index 000000000000..b6c89706ca03
--- /dev/null
+++ b/Documentation/powerpc/associativity.rst
@@ -0,0 +1,103 @@
+============================
+NUMA resource associativity
+=============================
+
+Associativity represents the groupings of the various platform resources into
+domains of substantially similar mean performance relative to resources outside
+of that domain. Resources subsets of a given domain that exhibit better
+performance relative to each other than relative to other resources subsets
+are represented as being members of a sub-grouping domain. This performance
+characteristic is presented in terms of NUMA node distance within the Linux kernel.
+From the platform view, these groups are also referred to as domains.
+
+PAPR interface currently supports different ways of communicating these resource
+grouping details to the OS. These are referred to as Form 0, Form 1 and Form2
+associativity grouping. Form 0 is the oldest format and is now considered deprecated.
+
+Hypervisor indicates the type/form of associativity used via "ibm,architecture-vec-5 property".
+Bit 0 of byte 5 in the "ibm,architecture-vec-5" property indicates usage of Form 0 or Form 1.
+A value of 1 indicates the usage of Form 1 associativity. For Form 2 associativity
+bit 2 of byte 5 in the "ibm,architecture-vec-5" property is used.
+
+Form 0
+-----
+Form 0 associativity supports only two NUMA distances (LOCAL and REMOTE).
+
+Form 1
+-----
+With Form 1 a combination of ibm,associativity-reference-points, and ibm,associativity
+device tree properties are used to determine the NUMA distance between resource groups/domains.
+
+The “ibm,associativity” property contains a list of one or more numbers (domainID)
+representing the resource’s platform grouping domains.
+
+The “ibm,associativity-reference-points” property contains a list of one or more numbers
+(domainID index) that represents the 1 based ordinal in the associativity lists.
+The list of domainID indexes represents an increasing hierarchy of resource grouping.
+
+ex:
+{ primary domainID index, secondary domainID index, tertiary domainID index.. }
+
+Linux kernel uses the domainID at the primary domainID index as the NUMA node id.
+Linux kernel computes NUMA distance between two domains by recursively comparing
+if they belong to the same higher-level domains. For mismatch at every higher
+level of the resource group, the kernel doubles the NUMA distance between the
+comparing domains.
+
+Form 2
+-------
+Form 2 associativity format adds separate device tree properties representing NUMA node distance
+thereby making the node distance computation flexible. Form 2 also allows flexible primary
+domain numbering. With numa distance computation now detached from the index value in
+"ibm,associativity-reference-points" property, Form 2 allows a large number of primary domain
+ids at the same domainID index representing resource groups of different performance/latency
+characteristics.
+
+Hypervisor indicates the usage of FORM2 associativity using bit 2 of byte 5 in the
+"ibm,architecture-vec-5" property.
+
+"ibm,numa-lookup-index-table" property contains a list of one or more numbers representing
+the domainIDs present in the system. The offset of the domainID in this property is
+used as an index while computing numa distance information via "ibm,numa-distance-table".
+
+prop-encoded-array: The number N of the domainIDs encoded as with encode-int, followed by
+N domainID encoded as with encode-int
+
+For ex:
+"ibm,numa-lookup-index-table" =  {4, 0, 8, 250, 252}. The offset of domainID 8 (2) is used when
+computing the distance of domain 8 from other domains present in the system. For the rest of
+this document, this offset will be referred to as domain distance offset.
+
+"ibm,numa-distance-table" property contains a list of one or more numbers representing the NUMA
+distance between resource groups/domains present in the system.
+
+prop-encoded-array: The number N of the distance values encoded as with encode-int, followed by
+N distance values encoded as with encode-bytes. The max distance value we could encode is 255.
+The number N must be equal to the square of m where m is the number of domainIDs in the
+numa-lookup-index-table.
+
+For ex:
+ibm,numa-lookup-index-table =  {3, 0, 8, 40}
+ibm,numa-distance-table     =  {9:u32, 10:u8, 20:u8, 80:u8, 20:u8, 10:u8, 160:u8, 80:u8, 160:u8, 10:u8}
+
+  | 0    8   40
+--|------------
+  |
+0 | 10   20  80
+  |
+8 | 20   10  160
+  |
+40| 80   160  10
+
+A possible "ibm,associativity" property for resources in node 0, 8 and 40
+
+{ 3, 6, 7, 0 }
+{ 3, 6, 9, 8 }
+{ 3, 6, 7, 40}
+
+With "ibm,associativity-reference-points"  { 0x3 }
+
+"ibm,lookup-index-table" helps in having a compact representation of distance matrix.
+Since domainID can be sparse, the matrix of distances can also be effectively sparse.
+With "ibm,lookup-index-table" we can achieve a compact representation of
+distance information.
diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h
index 60b631161360..97a3bd9ffeb9 100644
--- a/arch/powerpc/include/asm/firmware.h
+++ b/arch/powerpc/include/asm/firmware.h
@@ -53,6 +53,7 @@
 #define FW_FEATURE_ULTRAVISOR	ASM_CONST(0x0000004000000000)
 #define FW_FEATURE_STUFF_TCE	ASM_CONST(0x0000008000000000)
 #define FW_FEATURE_RPT_INVALIDATE ASM_CONST(0x0000010000000000)
+#define FW_FEATURE_FORM2_AFFINITY ASM_CONST(0x0000020000000000)
 
 #ifndef __ASSEMBLY__
 
@@ -73,7 +74,7 @@ enum {
 		FW_FEATURE_HPT_RESIZE | FW_FEATURE_DRMEM_V2 |
 		FW_FEATURE_DRC_INFO | FW_FEATURE_BLOCK_REMOVE |
 		FW_FEATURE_PAPR_SCM | FW_FEATURE_ULTRAVISOR |
-		FW_FEATURE_RPT_INVALIDATE,
+		FW_FEATURE_RPT_INVALIDATE | FW_FEATURE_FORM2_AFFINITY,
 	FW_FEATURE_PSERIES_ALWAYS = 0,
 	FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL | FW_FEATURE_ULTRAVISOR,
 	FW_FEATURE_POWERNV_ALWAYS = 0,
diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index df9fec9d232c..5c80152e8f18 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -149,6 +149,7 @@ extern int of_read_drc_info_cell(struct property **prop,
 #define OV5_XCMO		0x0440	/* Page Coalescing */
 #define OV5_FORM1_AFFINITY	0x0580	/* FORM1 NUMA affinity */
 #define OV5_PRRN		0x0540	/* Platform Resource Reassignment */
+#define OV5_FORM2_AFFINITY	0x0520	/* Form2 NUMA affinity */
 #define OV5_HP_EVT		0x0604	/* Hot Plug Event support */
 #define OV5_RESIZE_HPT		0x0601	/* Hash Page Table resizing */
 #define OV5_PFO_HW_RNG		0x1180	/* PFO Random Number Generator */
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 57db605ad33a..95a42d49e291 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -1096,7 +1096,8 @@ static const struct ibm_arch_vec ibm_architecture_vec_template __initconst = {
 #else
 		0,
 #endif
-		.associativity = OV5_FEAT(OV5_FORM1_AFFINITY) | OV5_FEAT(OV5_PRRN),
+		.associativity = OV5_FEAT(OV5_FORM1_AFFINITY) | OV5_FEAT(OV5_PRRN) |
+		OV5_FEAT(OV5_FORM2_AFFINITY),
 		.bin_opts = OV5_FEAT(OV5_RESIZE_HPT) | OV5_FEAT(OV5_HP_EVT),
 		.micro_checkpoint = 0,
 		.reserved0 = 0,
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index a244398a7766..fffb3c40f595 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -56,12 +56,17 @@ static int n_mem_addr_cells, n_mem_size_cells;
 
 #define FORM0_AFFINITY 0
 #define FORM1_AFFINITY 1
+#define FORM2_AFFINITY 2
 static int affinity_form;
 
 #define MAX_DISTANCE_REF_POINTS 4
 static int distance_ref_points_depth;
 static const __be32 *distance_ref_points;
 static int distance_lookup_table[MAX_NUMNODES][MAX_DISTANCE_REF_POINTS];
+static int numa_distance_table[MAX_NUMNODES][MAX_NUMNODES] = {
+	[0 ... MAX_NUMNODES - 1] = { [0 ... MAX_NUMNODES - 1] = -1 }
+};
+static int numa_id_index_table[MAX_NUMNODES] = { [0 ... MAX_NUMNODES - 1] = NUMA_NO_NODE };
 
 /*
  * Allocate node_to_cpumask_map based on number of available nodes
@@ -166,6 +171,44 @@ static void unmap_cpu_from_node(unsigned long cpu)
 }
 #endif /* CONFIG_HOTPLUG_CPU || CONFIG_PPC_SPLPAR */
 
+/*
+ * Returns nid in the range [0..nr_node_ids], or -1 if no useful NUMA
+ * info is found.
+ */
+static int associativity_to_nid(const __be32 *associativity)
+{
+	int nid = NUMA_NO_NODE;
+
+	if (!numa_enabled)
+		goto out;
+
+	if (of_read_number(associativity, 1) >= primary_domain_index)
+		nid = of_read_number(&associativity[primary_domain_index], 1);
+
+	/* POWER4 LPAR uses 0xffff as invalid node */
+	if (nid == 0xffff || nid >= nr_node_ids)
+		nid = NUMA_NO_NODE;
+out:
+	return nid;
+}
+
+static int __cpu_form2_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
+{
+	int dist;
+	int node1, node2;
+
+	node1 = associativity_to_nid(cpu1_assoc);
+	node2 = associativity_to_nid(cpu2_assoc);
+
+	dist = numa_distance_table[node1][node2];
+	if (dist <= LOCAL_DISTANCE)
+		return 0;
+	else if (dist <= REMOTE_DISTANCE)
+		return 1;
+	else
+		return 2;
+}
+
 static int __cpu_form1_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
 {
 	int dist = 0;
@@ -186,8 +229,9 @@ int cpu_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
 {
 	/* We should not get called with FORM0 */
 	VM_WARN_ON(affinity_form == FORM0_AFFINITY);
-
-	return __cpu_form1_relative_distance(cpu1_assoc, cpu2_assoc);
+	if (affinity_form == FORM1_AFFINITY)
+		return __cpu_form1_relative_distance(cpu1_assoc, cpu2_assoc);
+	return __cpu_form2_relative_distance(cpu1_assoc, cpu2_assoc);
 }
 
 /* must hold reference to node during call */
@@ -201,7 +245,9 @@ int __node_distance(int a, int b)
 	int i;
 	int distance = LOCAL_DISTANCE;
 
-	if (affinity_form == FORM0_AFFINITY)
+	if (affinity_form == FORM2_AFFINITY)
+		return numa_distance_table[a][b];
+	else if (affinity_form == FORM0_AFFINITY)
 		return ((a == b) ? LOCAL_DISTANCE : REMOTE_DISTANCE);
 
 	for (i = 0; i < distance_ref_points_depth; i++) {
@@ -216,27 +262,6 @@ int __node_distance(int a, int b)
 }
 EXPORT_SYMBOL(__node_distance);
 
-/*
- * Returns nid in the range [0..nr_node_ids], or -1 if no useful NUMA
- * info is found.
- */
-static int associativity_to_nid(const __be32 *associativity)
-{
-	int nid = NUMA_NO_NODE;
-
-	if (!numa_enabled)
-		goto out;
-
-	if (of_read_number(associativity, 1) >= primary_domain_index)
-		nid = of_read_number(&associativity[primary_domain_index], 1);
-
-	/* POWER4 LPAR uses 0xffff as invalid node */
-	if (nid == 0xffff || nid >= nr_node_ids)
-		nid = NUMA_NO_NODE;
-out:
-	return nid;
-}
-
 /* Returns the nid associated with the given device tree node,
  * or -1 if not found.
  */
@@ -304,12 +329,93 @@ static void initialize_form1_numa_distance(struct device_node *node)
  */
 void update_numa_distance(struct device_node *node)
 {
+	int nid;
+
 	if (affinity_form == FORM0_AFFINITY)
 		return;
 	else if (affinity_form == FORM1_AFFINITY) {
 		initialize_form1_numa_distance(node);
 		return;
 	}
+
+	/* FORM2 affinity  */
+	nid = of_node_to_nid_single(node);
+	if (nid == NUMA_NO_NODE)
+		return;
+
+	/*
+	 * With FORM2 we expect NUMA distance of all possible NUMA
+	 * nodes to be provided during boot.
+	 */
+	WARN(numa_distance_table[nid][nid] == -1,
+	     "NUMA distance details for node %d not provided\n", nid);
+}
+
+/*
+ * ibm,numa-lookup-index-table= {N, domainid1, domainid2, ..... domainidN}
+ * ibm,numa-distance-table = { N, 1, 2, 4, 5, 1, 6, .... N elements}
+ */
+static void initialize_form2_numa_distance_lookup_table(void)
+{
+	int i, j;
+	struct device_node *root;
+	const __u8 *numa_dist_table;
+	const __be32 *numa_lookup_index;
+	int numa_dist_table_length;
+	int max_numa_index, distance_index;
+
+	if (firmware_has_feature(FW_FEATURE_OPAL))
+		root = of_find_node_by_path("/ibm,opal");
+	else
+		root = of_find_node_by_path("/rtas");
+	if (!root)
+		root = of_find_node_by_path("/");
+
+	numa_lookup_index = of_get_property(root, "ibm,numa-lookup-index-table", NULL);
+	max_numa_index = of_read_number(&numa_lookup_index[0], 1);
+
+	/* first element of the array is the size and is encode-int */
+	numa_dist_table = of_get_property(root, "ibm,numa-distance-table", NULL);
+	numa_dist_table_length = of_read_number((const __be32 *)&numa_dist_table[0], 1);
+	/* Skip the size which is encoded int */
+	numa_dist_table += sizeof(__be32);
+
+	pr_debug("numa_dist_table_len = %d, numa_dist_indexes_len = %d\n",
+		 numa_dist_table_length, max_numa_index);
+
+	for (i = 0; i < max_numa_index; i++)
+		/* +1 skip the max_numa_index in the property */
+		numa_id_index_table[i] = of_read_number(&numa_lookup_index[i + 1], 1);
+
+
+	if (numa_dist_table_length != max_numa_index * max_numa_index) {
+
+		WARN(1, "Wrong NUMA distance information\n");
+		/* consider everybody else just remote. */
+		for (i = 0;  i < max_numa_index; i++) {
+			for (j = 0; j < max_numa_index; j++) {
+				int nodeA = numa_id_index_table[i];
+				int nodeB = numa_id_index_table[j];
+
+				if (nodeA == nodeB)
+					numa_distance_table[nodeA][nodeB] = LOCAL_DISTANCE;
+				else
+					numa_distance_table[nodeA][nodeB] = REMOTE_DISTANCE;
+			}
+		}
+	}
+
+	distance_index = 0;
+	for (i = 0;  i < max_numa_index; i++) {
+		for (j = 0; j < max_numa_index; j++) {
+			int nodeA = numa_id_index_table[i];
+			int nodeB = numa_id_index_table[j];
+
+			numa_distance_table[nodeA][nodeB] = numa_dist_table[distance_index++];
+			pr_debug("dist[%d][%d]=%d ", nodeA, nodeB, numa_distance_table[nodeA][nodeB]);
+		}
+	}
+	of_node_put(root);
 }
 
 static int __init find_primary_domain_index(void)
@@ -322,6 +428,9 @@ static int __init find_primary_domain_index(void)
 	 */
 	if (firmware_has_feature(FW_FEATURE_OPAL)) {
 		affinity_form = FORM1_AFFINITY;
+	} else if (firmware_has_feature(FW_FEATURE_FORM2_AFFINITY)) {
+		dbg("Using form 2 affinity\n");
+		affinity_form = FORM2_AFFINITY;
 	} else if (firmware_has_feature(FW_FEATURE_FORM1_AFFINITY)) {
 		dbg("Using form 1 affinity\n");
 		affinity_form = FORM1_AFFINITY;
@@ -366,9 +475,12 @@ static int __init find_primary_domain_index(void)
 
 		index = of_read_number(&distance_ref_points[1], 1);
 	} else {
+		/*
+		 * Both FORM1 and FORM2 affinity find the primary domain details
+		 * at the same offset.
+		 */
 		index = of_read_number(distance_ref_points, 1);
 	}
-
 	/*
 	 * Warn and cap if the hardware supports more than
 	 * MAX_DISTANCE_REF_POINTS domains.
@@ -807,6 +919,12 @@ static int __init parse_numa_properties(void)
 
 	dbg("NUMA associativity depth for CPU/Memory: %d\n", primary_domain_index);
 
+	/*
+	 * If it is FORM2 initialize the distance table here.
+	 */
+	if (affinity_form == FORM2_AFFINITY)
+		initialize_form2_numa_distance_lookup_table();
+
 	/*
 	 * Even though we connect cpus to numa domains later in SMP
 	 * init, we need to know the node ids now. This is because
diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c
index 5d4c2bc20bba..f162156b7b68 100644
--- a/arch/powerpc/platforms/pseries/firmware.c
+++ b/arch/powerpc/platforms/pseries/firmware.c
@@ -123,6 +123,7 @@ vec5_fw_features_table[] = {
 	{FW_FEATURE_PRRN,		OV5_PRRN},
 	{FW_FEATURE_DRMEM_V2,		OV5_DRMEM_V2},
 	{FW_FEATURE_DRC_INFO,		OV5_DRC_INFO},
+	{FW_FEATURE_FORM2_AFFINITY,	OV5_FORM2_AFFINITY},
 };
 
 static void __init fw_vec5_feature_init(const char *vec5, unsigned long len)
-- 
2.31.1

Re: [PATCH v7 5/6] powerpc/pseries: Add support for FORM2 associativity

[David Gibson]

[-- Attachment #1: Type: text/plain, Size: 18795 bytes --]

On Mon, Aug 09, 2021 at 10:54:33AM +0530, Aneesh Kumar K.V wrote:
> PAPR interface currently supports two different ways of communicating resource
> grouping details to the OS. These are referred to as Form 0 and Form 1
> associativity grouping. Form 0 is the older format and is now considered
> deprecated. This patch adds another resource grouping named FORM2.
> 
> Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com>
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>

LGTM, with the exception of some minor nits noted below.

> ---
>  Documentation/powerpc/associativity.rst   | 103 +++++++++++++
>  arch/powerpc/include/asm/firmware.h       |   3 +-
>  arch/powerpc/include/asm/prom.h           |   1 +
>  arch/powerpc/kernel/prom_init.c           |   3 +-
>  arch/powerpc/mm/numa.c                    | 168 ++++++++++++++++++----
>  arch/powerpc/platforms/pseries/firmware.c |   1 +
>  6 files changed, 252 insertions(+), 27 deletions(-)
>  create mode 100644 Documentation/powerpc/associativity.rst
> 
> diff --git a/Documentation/powerpc/associativity.rst b/Documentation/powerpc/associativity.rst
> new file mode 100644
> index 000000000000..b6c89706ca03
> --- /dev/null
> +++ b/Documentation/powerpc/associativity.rst
> @@ -0,0 +1,103 @@
> +============================
> +NUMA resource associativity
> +=============================
> +
> +Associativity represents the groupings of the various platform resources into
> +domains of substantially similar mean performance relative to resources outside
> +of that domain. Resources subsets of a given domain that exhibit better
> +performance relative to each other than relative to other resources subsets
> +are represented as being members of a sub-grouping domain. This performance
> +characteristic is presented in terms of NUMA node distance within the Linux kernel.
> +From the platform view, these groups are also referred to as domains.
> +
> +PAPR interface currently supports different ways of communicating these resource
> +grouping details to the OS. These are referred to as Form 0, Form 1 and Form2
> +associativity grouping. Form 0 is the oldest format and is now considered deprecated.
> +
> +Hypervisor indicates the type/form of associativity used via "ibm,architecture-vec-5 property".
> +Bit 0 of byte 5 in the "ibm,architecture-vec-5" property indicates usage of Form 0 or Form 1.
> +A value of 1 indicates the usage of Form 1 associativity. For Form 2 associativity
> +bit 2 of byte 5 in the "ibm,architecture-vec-5" property is used.
> +
> +Form 0
> +-----
> +Form 0 associativity supports only two NUMA distances (LOCAL and REMOTE).
> +
> +Form 1
> +-----
> +With Form 1 a combination of ibm,associativity-reference-points, and ibm,associativity
> +device tree properties are used to determine the NUMA distance between resource groups/domains.
> +
> +The “ibm,associativity” property contains a list of one or more numbers (domainID)
> +representing the resource’s platform grouping domains.
> +
> +The “ibm,associativity-reference-points” property contains a list of one or more numbers
> +(domainID index) that represents the 1 based ordinal in the associativity lists.
> +The list of domainID indexes represents an increasing hierarchy of resource grouping.
> +
> +ex:
> +{ primary domainID index, secondary domainID index, tertiary domainID index.. }
> +
> +Linux kernel uses the domainID at the primary domainID index as the NUMA node id.
> +Linux kernel computes NUMA distance between two domains by recursively comparing
> +if they belong to the same higher-level domains. For mismatch at every higher
> +level of the resource group, the kernel doubles the NUMA distance between the
> +comparing domains.
> +
> +Form 2
> +-------
> +Form 2 associativity format adds separate device tree properties representing NUMA node distance
> +thereby making the node distance computation flexible. Form 2 also allows flexible primary
> +domain numbering. With numa distance computation now detached from the index value in
> +"ibm,associativity-reference-points" property, Form 2 allows a large number of primary domain
> +ids at the same domainID index representing resource groups of different performance/latency
> +characteristics.
> +
> +Hypervisor indicates the usage of FORM2 associativity using bit 2 of byte 5 in the
> +"ibm,architecture-vec-5" property.
> +
> +"ibm,numa-lookup-index-table" property contains a list of one or more numbers representing
> +the domainIDs present in the system. The offset of the domainID in this property is
> +used as an index while computing numa distance information via "ibm,numa-distance-table".
> +
> +prop-encoded-array: The number N of the domainIDs encoded as with encode-int, followed by
> +N domainID encoded as with encode-int
> +
> +For ex:
> +"ibm,numa-lookup-index-table" =  {4, 0, 8, 250, 252}. The offset of domainID 8 (2) is used when
> +computing the distance of domain 8 from other domains present in the system. For the rest of
> +this document, this offset will be referred to as domain distance offset.
> +
> +"ibm,numa-distance-table" property contains a list of one or more numbers representing the NUMA
> +distance between resource groups/domains present in the system.
> +
> +prop-encoded-array: The number N of the distance values encoded as with encode-int, followed by
> +N distance values encoded as with encode-bytes. The max distance value we could encode is 255.
> +The number N must be equal to the square of m where m is the number of domainIDs in the
> +numa-lookup-index-table.
> +
> +For ex:
> +ibm,numa-lookup-index-table =  {3, 0, 8, 40}
> +ibm,numa-distance-table     =  {9:u32, 10:u8, 20:u8, 80:u8, 20:u8, 10:u8, 160:u8, 80:u8, 160:u8, 10:u8}

An alternative to the :u32 :u8 formatting which might be more widely
readable would be to use dts syntax for the values.  So:

	ibm,numa-lookup-index-table = <3 0 8 40>;
	ibm,numa-distace-table = <9>, /bits/ 8 < 10  20  80
	                                         20  10 160
						 80 160  10>;

> +
> +  | 0    8   40
> +--|------------
> +  |
> +0 | 10   20  80
> +  |
> +8 | 20   10  160
> +  |
> +40| 80   160  10
> +
> +A possible "ibm,associativity" property for resources in node 0, 8 and 40
> +
> +{ 3, 6, 7, 0 }
> +{ 3, 6, 9, 8 }
> +{ 3, 6, 7, 40}
> +
> +With "ibm,associativity-reference-points"  { 0x3 }
> +
> +"ibm,lookup-index-table" helps in having a compact representation of distance matrix.
> +Since domainID can be sparse, the matrix of distances can also be effectively sparse.
> +With "ibm,lookup-index-table" we can achieve a compact representation of
> +distance information.
> diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h
> index 60b631161360..97a3bd9ffeb9 100644
> --- a/arch/powerpc/include/asm/firmware.h
> +++ b/arch/powerpc/include/asm/firmware.h
> @@ -53,6 +53,7 @@
>  #define FW_FEATURE_ULTRAVISOR	ASM_CONST(0x0000004000000000)
>  #define FW_FEATURE_STUFF_TCE	ASM_CONST(0x0000008000000000)
>  #define FW_FEATURE_RPT_INVALIDATE ASM_CONST(0x0000010000000000)
> +#define FW_FEATURE_FORM2_AFFINITY ASM_CONST(0x0000020000000000)
>  
>  #ifndef __ASSEMBLY__
>  
> @@ -73,7 +74,7 @@ enum {
>  		FW_FEATURE_HPT_RESIZE | FW_FEATURE_DRMEM_V2 |
>  		FW_FEATURE_DRC_INFO | FW_FEATURE_BLOCK_REMOVE |
>  		FW_FEATURE_PAPR_SCM | FW_FEATURE_ULTRAVISOR |
> -		FW_FEATURE_RPT_INVALIDATE,
> +		FW_FEATURE_RPT_INVALIDATE | FW_FEATURE_FORM2_AFFINITY,
>  	FW_FEATURE_PSERIES_ALWAYS = 0,
>  	FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL | FW_FEATURE_ULTRAVISOR,
>  	FW_FEATURE_POWERNV_ALWAYS = 0,
> diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
> index df9fec9d232c..5c80152e8f18 100644
> --- a/arch/powerpc/include/asm/prom.h
> +++ b/arch/powerpc/include/asm/prom.h
> @@ -149,6 +149,7 @@ extern int of_read_drc_info_cell(struct property **prop,
>  #define OV5_XCMO		0x0440	/* Page Coalescing */
>  #define OV5_FORM1_AFFINITY	0x0580	/* FORM1 NUMA affinity */
>  #define OV5_PRRN		0x0540	/* Platform Resource Reassignment */
> +#define OV5_FORM2_AFFINITY	0x0520	/* Form2 NUMA affinity */
>  #define OV5_HP_EVT		0x0604	/* Hot Plug Event support */
>  #define OV5_RESIZE_HPT		0x0601	/* Hash Page Table resizing */
>  #define OV5_PFO_HW_RNG		0x1180	/* PFO Random Number Generator */
> diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
> index 57db605ad33a..95a42d49e291 100644
> --- a/arch/powerpc/kernel/prom_init.c
> +++ b/arch/powerpc/kernel/prom_init.c
> @@ -1096,7 +1096,8 @@ static const struct ibm_arch_vec ibm_architecture_vec_template __initconst = {
>  #else
>  		0,
>  #endif
> -		.associativity = OV5_FEAT(OV5_FORM1_AFFINITY) | OV5_FEAT(OV5_PRRN),
> +		.associativity = OV5_FEAT(OV5_FORM1_AFFINITY) | OV5_FEAT(OV5_PRRN) |
> +		OV5_FEAT(OV5_FORM2_AFFINITY),
>  		.bin_opts = OV5_FEAT(OV5_RESIZE_HPT) | OV5_FEAT(OV5_HP_EVT),
>  		.micro_checkpoint = 0,
>  		.reserved0 = 0,
> diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
> index a244398a7766..fffb3c40f595 100644
> --- a/arch/powerpc/mm/numa.c
> +++ b/arch/powerpc/mm/numa.c
> @@ -56,12 +56,17 @@ static int n_mem_addr_cells, n_mem_size_cells;
>  
>  #define FORM0_AFFINITY 0
>  #define FORM1_AFFINITY 1
> +#define FORM2_AFFINITY 2
>  static int affinity_form;
>  
>  #define MAX_DISTANCE_REF_POINTS 4
>  static int distance_ref_points_depth;
>  static const __be32 *distance_ref_points;
>  static int distance_lookup_table[MAX_NUMNODES][MAX_DISTANCE_REF_POINTS];
> +static int numa_distance_table[MAX_NUMNODES][MAX_NUMNODES] = {
> +	[0 ... MAX_NUMNODES - 1] = { [0 ... MAX_NUMNODES - 1] = -1 }
> +};
> +static int numa_id_index_table[MAX_NUMNODES] = { [0 ... MAX_NUMNODES - 1] = NUMA_NO_NODE };
>  
>  /*
>   * Allocate node_to_cpumask_map based on number of available nodes
> @@ -166,6 +171,44 @@ static void unmap_cpu_from_node(unsigned long cpu)
>  }
>  #endif /* CONFIG_HOTPLUG_CPU || CONFIG_PPC_SPLPAR */
>  
> +/*
> + * Returns nid in the range [0..nr_node_ids], or -1 if no useful NUMA
> + * info is found.
> + */
> +static int associativity_to_nid(const __be32 *associativity)
> +{
> +	int nid = NUMA_NO_NODE;
> +
> +	if (!numa_enabled)
> +		goto out;

Again, no reason for a goto here, you can just do a direct return.

But I guess this is just a code motion, so that's an unrelated
change.. ok.

> +
> +	if (of_read_number(associativity, 1) >= primary_domain_index)
> +		nid = of_read_number(&associativity[primary_domain_index], 1);
> +
> +	/* POWER4 LPAR uses 0xffff as invalid node */
> +	if (nid == 0xffff || nid >= nr_node_ids)
> +		nid = NUMA_NO_NODE;
> +out:
> +	return nid;
> +}
> +
> +static int __cpu_form2_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
> +{
> +	int dist;
> +	int node1, node2;
> +
> +	node1 = associativity_to_nid(cpu1_assoc);
> +	node2 = associativity_to_nid(cpu2_assoc);
> +
> +	dist = numa_distance_table[node1][node2];
> +	if (dist <= LOCAL_DISTANCE)
> +		return 0;
> +	else if (dist <= REMOTE_DISTANCE)
> +		return 1;
> +	else
> +		return 2;
> +}
> +
>  static int __cpu_form1_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
>  {
>  	int dist = 0;
> @@ -186,8 +229,9 @@ int cpu_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
>  {
>  	/* We should not get called with FORM0 */
>  	VM_WARN_ON(affinity_form == FORM0_AFFINITY);
> -
> -	return __cpu_form1_relative_distance(cpu1_assoc, cpu2_assoc);
> +	if (affinity_form == FORM1_AFFINITY)
> +		return __cpu_form1_relative_distance(cpu1_assoc, cpu2_assoc);
> +	return __cpu_form2_relative_distance(cpu1_assoc, cpu2_assoc);
>  }
>  
>  /* must hold reference to node during call */
> @@ -201,7 +245,9 @@ int __node_distance(int a, int b)
>  	int i;
>  	int distance = LOCAL_DISTANCE;
>  
> -	if (affinity_form == FORM0_AFFINITY)
> +	if (affinity_form == FORM2_AFFINITY)
> +		return numa_distance_table[a][b];
> +	else if (affinity_form == FORM0_AFFINITY)
>  		return ((a == b) ? LOCAL_DISTANCE : REMOTE_DISTANCE);
>  
>  	for (i = 0; i < distance_ref_points_depth; i++) {
> @@ -216,27 +262,6 @@ int __node_distance(int a, int b)
>  }
>  EXPORT_SYMBOL(__node_distance);
>  
> -/*
> - * Returns nid in the range [0..nr_node_ids], or -1 if no useful NUMA
> - * info is found.
> - */
> -static int associativity_to_nid(const __be32 *associativity)
> -{
> -	int nid = NUMA_NO_NODE;
> -
> -	if (!numa_enabled)
> -		goto out;
> -
> -	if (of_read_number(associativity, 1) >= primary_domain_index)
> -		nid = of_read_number(&associativity[primary_domain_index], 1);
> -
> -	/* POWER4 LPAR uses 0xffff as invalid node */
> -	if (nid == 0xffff || nid >= nr_node_ids)
> -		nid = NUMA_NO_NODE;
> -out:
> -	return nid;
> -}
> -
>  /* Returns the nid associated with the given device tree node,
>   * or -1 if not found.
>   */
> @@ -304,12 +329,93 @@ static void initialize_form1_numa_distance(struct device_node *node)
>   */
>  void update_numa_distance(struct device_node *node)
>  {
> +	int nid;
> +
>  	if (affinity_form == FORM0_AFFINITY)
>  		return;
>  	else if (affinity_form == FORM1_AFFINITY) {
>  		initialize_form1_numa_distance(node);
>  		return;
>  	}
> +
> +	/* FORM2 affinity  */
> +	nid = of_node_to_nid_single(node);
> +	if (nid == NUMA_NO_NODE)
> +		return;
> +
> +	/*
> +	 * With FORM2 we expect NUMA distance of all possible NUMA
> +	 * nodes to be provided during boot.
> +	 */
> +	WARN(numa_distance_table[nid][nid] == -1,
> +	     "NUMA distance details for node %d not provided\n", nid);
> +}
> +
> +/*
> + * ibm,numa-lookup-index-table= {N, domainid1, domainid2, ..... domainidN}
> + * ibm,numa-distance-table = { N, 1, 2, 4, 5, 1, 6, .... N elements}
> + */
> +static void initialize_form2_numa_distance_lookup_table(void)
> +{
> +	int i, j;
> +	struct device_node *root;
> +	const __u8 *numa_dist_table;
> +	const __be32 *numa_lookup_index;
> +	int numa_dist_table_length;
> +	int max_numa_index, distance_index;
> +
> +	if (firmware_has_feature(FW_FEATURE_OPAL))
> +		root = of_find_node_by_path("/ibm,opal");
> +	else
> +		root = of_find_node_by_path("/rtas");
> +	if (!root)
> +		root = of_find_node_by_path("/");
> +
> +	numa_lookup_index = of_get_property(root, "ibm,numa-lookup-index-table", NULL);
> +	max_numa_index = of_read_number(&numa_lookup_index[0], 1);
> +
> +	/* first element of the array is the size and is encode-int */
> +	numa_dist_table = of_get_property(root, "ibm,numa-distance-table", NULL);
> +	numa_dist_table_length = of_read_number((const __be32 *)&numa_dist_table[0], 1);
> +	/* Skip the size which is encoded int */
> +	numa_dist_table += sizeof(__be32);
> +
> +	pr_debug("numa_dist_table_len = %d, numa_dist_indexes_len = %d\n",
> +		 numa_dist_table_length, max_numa_index);
> +
> +	for (i = 0; i < max_numa_index; i++)
> +		/* +1 skip the max_numa_index in the property */
> +		numa_id_index_table[i] = of_read_number(&numa_lookup_index[i + 1], 1);
> +
> +
> +	if (numa_dist_table_length != max_numa_index * max_numa_index) {
> +

Stray extra whitespace line here.

> +		WARN(1, "Wrong NUMA distance information\n");
> +		/* consider everybody else just remote. */
> +		for (i = 0;  i < max_numa_index; i++) {
> +			for (j = 0; j < max_numa_index; j++) {
> +				int nodeA = numa_id_index_table[i];
> +				int nodeB = numa_id_index_table[j];
> +
> +				if (nodeA == nodeB)
> +					numa_distance_table[nodeA][nodeB] = LOCAL_DISTANCE;
> +				else
> +					numa_distance_table[nodeA][nodeB] = REMOTE_DISTANCE;
> +			}
> +		}

I don't think it's necessarily a problem, but something to consider is
that this fallback will initialize distance for *all* node IDs,
whereas the normal path will only initialize it for nodes that are in
the index table.  Since some later error checks key off whether
certain fields in the distance table are initialized, is that the
outcome you want?

> +	}
> +
> +	distance_index = 0;
> +	for (i = 0;  i < max_numa_index; i++) {
> +		for (j = 0; j < max_numa_index; j++) {
> +			int nodeA = numa_id_index_table[i];
> +			int nodeB = numa_id_index_table[j];
> +
> +			numa_distance_table[nodeA][nodeB] = numa_dist_table[distance_index++];
> +			pr_debug("dist[%d][%d]=%d ", nodeA, nodeB, numa_distance_table[nodeA][nodeB]);
> +		}
> +	}
> +	of_node_put(root);
>  }
>  
>  static int __init find_primary_domain_index(void)
> @@ -322,6 +428,9 @@ static int __init find_primary_domain_index(void)
>  	 */
>  	if (firmware_has_feature(FW_FEATURE_OPAL)) {
>  		affinity_form = FORM1_AFFINITY;
> +	} else if (firmware_has_feature(FW_FEATURE_FORM2_AFFINITY)) {
> +		dbg("Using form 2 affinity\n");
> +		affinity_form = FORM2_AFFINITY;
>  	} else if (firmware_has_feature(FW_FEATURE_FORM1_AFFINITY)) {
>  		dbg("Using form 1 affinity\n");
>  		affinity_form = FORM1_AFFINITY;
> @@ -366,9 +475,12 @@ static int __init find_primary_domain_index(void)
>  
>  		index = of_read_number(&distance_ref_points[1], 1);
>  	} else {
> +		/*
> +		 * Both FORM1 and FORM2 affinity find the primary domain details
> +		 * at the same offset.
> +		 */
>  		index = of_read_number(distance_ref_points, 1);
>  	}
> -
>  	/*
>  	 * Warn and cap if the hardware supports more than
>  	 * MAX_DISTANCE_REF_POINTS domains.
> @@ -807,6 +919,12 @@ static int __init parse_numa_properties(void)
>  
>  	dbg("NUMA associativity depth for CPU/Memory: %d\n", primary_domain_index);
>  
> +	/*
> +	 * If it is FORM2 initialize the distance table here.
> +	 */
> +	if (affinity_form == FORM2_AFFINITY)
> +		initialize_form2_numa_distance_lookup_table();
> +
>  	/*
>  	 * Even though we connect cpus to numa domains later in SMP
>  	 * init, we need to know the node ids now. This is because
> diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c
> index 5d4c2bc20bba..f162156b7b68 100644
> --- a/arch/powerpc/platforms/pseries/firmware.c
> +++ b/arch/powerpc/platforms/pseries/firmware.c
> @@ -123,6 +123,7 @@ vec5_fw_features_table[] = {
>  	{FW_FEATURE_PRRN,		OV5_PRRN},
>  	{FW_FEATURE_DRMEM_V2,		OV5_DRMEM_V2},
>  	{FW_FEATURE_DRC_INFO,		OV5_DRC_INFO},
> +	{FW_FEATURE_FORM2_AFFINITY,	OV5_FORM2_AFFINITY},
>  };
>  
>  static void __init fw_vec5_feature_init(const char *vec5, unsigned long len)

-- 
David Gibson			| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you.  NOT _the_ _other_
				| _way_ _around_!
http://www.ozlabs.org/~dgibson

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

Re: [PATCH v7 5/6] powerpc/pseries: Add support for FORM2 associativity

[Aneesh Kumar K.V]

David Gibson <david@gibson.dropbear.id.au> writes:

> On Mon, Aug 09, 2021 at 10:54:33AM +0530, Aneesh Kumar K.V wrote:
>> PAPR interface currently supports two different ways of communicating resource
>> grouping details to the OS. These are referred to as Form 0 and Form 1
>> associativity grouping. Form 0 is the older format and is now considered
>> deprecated. This patch adds another resource grouping named FORM2.
>> 
>> Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com>
>> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
>
> LGTM, with the exception of some minor nits noted below.
...

> +
>> +	for (i = 0; i < max_numa_index; i++)
>> +		/* +1 skip the max_numa_index in the property */
>> +		numa_id_index_table[i] = of_read_number(&numa_lookup_index[i + 1], 1);
>> +
>> +
>> +	if (numa_dist_table_length != max_numa_index * max_numa_index) {
>> +
>
> Stray extra whitespace line here.
>
>> +		WARN(1, "Wrong NUMA distance information\n");
>> +		/* consider everybody else just remote. */
>> +		for (i = 0;  i < max_numa_index; i++) {
>> +			for (j = 0; j < max_numa_index; j++) {
>> +				int nodeA = numa_id_index_table[i];
>> +				int nodeB = numa_id_index_table[j];
>> +
>> +				if (nodeA == nodeB)
>> +					numa_distance_table[nodeA][nodeB] = LOCAL_DISTANCE;
>> +				else
>> +					numa_distance_table[nodeA][nodeB] = REMOTE_DISTANCE;
>> +			}
>> +		}
>
> I don't think it's necessarily a problem, but something to consider is
> that this fallback will initialize distance for *all* node IDs,
> whereas the normal path will only initialize it for nodes that are in
> the index table.  Since some later error checks key off whether
> certain fields in the distance table are initialized, is that the
> outcome you want?
>

With the device tree details not correct, one of the possible way to
make progress is to consider everybody remote. With new node hotplug
support we used to check whether the distance table entry is
initialized. With the updated spec, we expect all possible numa node
distance to be available during boot.

-aneesh

Re: [PATCH v7 5/6] powerpc/pseries: Add support for FORM2 associativity

[David Gibson]

[-- Attachment #1: Type: text/plain, Size: 2691 bytes --]

On Wed, Aug 11, 2021 at 09:39:32AM +0530, Aneesh Kumar K.V wrote:
> David Gibson <david@gibson.dropbear.id.au> writes:
> 
> > On Mon, Aug 09, 2021 at 10:54:33AM +0530, Aneesh Kumar K.V wrote:
> >> PAPR interface currently supports two different ways of communicating resource
> >> grouping details to the OS. These are referred to as Form 0 and Form 1
> >> associativity grouping. Form 0 is the older format and is now considered
> >> deprecated. This patch adds another resource grouping named FORM2.
> >> 
> >> Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com>
> >> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
> >
> > LGTM, with the exception of some minor nits noted below.
> ...
> 
> > +
> >> +	for (i = 0; i < max_numa_index; i++)
> >> +		/* +1 skip the max_numa_index in the property */
> >> +		numa_id_index_table[i] = of_read_number(&numa_lookup_index[i + 1], 1);
> >> +
> >> +
> >> +	if (numa_dist_table_length != max_numa_index * max_numa_index) {
> >> +
> >
> > Stray extra whitespace line here.
> >
> >> +		WARN(1, "Wrong NUMA distance information\n");
> >> +		/* consider everybody else just remote. */
> >> +		for (i = 0;  i < max_numa_index; i++) {
> >> +			for (j = 0; j < max_numa_index; j++) {
> >> +				int nodeA = numa_id_index_table[i];
> >> +				int nodeB = numa_id_index_table[j];
> >> +
> >> +				if (nodeA == nodeB)
> >> +					numa_distance_table[nodeA][nodeB] = LOCAL_DISTANCE;
> >> +				else
> >> +					numa_distance_table[nodeA][nodeB] = REMOTE_DISTANCE;
> >> +			}
> >> +		}
> >
> > I don't think it's necessarily a problem, but something to consider is
> > that this fallback will initialize distance for *all* node IDs,
> > whereas the normal path will only initialize it for nodes that are in
> > the index table.  Since some later error checks key off whether
> > certain fields in the distance table are initialized, is that the
> > outcome you want?
> >
> 
> With the device tree details not correct, one of the possible way to
> make progress is to consider everybody remote. With new node hotplug
> support we used to check whether the distance table entry is
> initialized. With the updated spec, we expect all possible numa node
> distance to be available during boot.

Sure.  But my main point here is that the fallback behaviour in this
clause is different from the fallback behaviour if the table is there
and parseable, but incomplete - which is also not expected.

-- 
David Gibson			| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you.  NOT _the_ _other_
				| _way_ _around_!
http://www.ozlabs.org/~dgibson

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

Re: [PATCH v7 5/6] powerpc/pseries: Add support for FORM2 associativity

[Aneesh Kumar K.V]

On 8/12/21 7:11 AM, David Gibson wrote:
> On Wed, Aug 11, 2021 at 09:39:32AM +0530, Aneesh Kumar K.V wrote:
>> David Gibson <david@gibson.dropbear.id.au> writes:
>>
>>> On Mon, Aug 09, 2021 at 10:54:33AM +0530, Aneesh Kumar K.V wrote:
>>>> PAPR interface currently supports two different ways of communicating resource
>>>> grouping details to the OS. These are referred to as Form 0 and Form 1
>>>> associativity grouping. Form 0 is the older format and is now considered
>>>> deprecated. This patch adds another resource grouping named FORM2.
>>>>
>>>> Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com>
>>>> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
>>>
>>> LGTM, with the exception of some minor nits noted below.
>> ...
>>
>>> +
>>>> +	for (i = 0; i < max_numa_index; i++)
>>>> +		/* +1 skip the max_numa_index in the property */
>>>> +		numa_id_index_table[i] = of_read_number(&numa_lookup_index[i + 1], 1);
>>>> +
>>>> +
>>>> +	if (numa_dist_table_length != max_numa_index * max_numa_index) {
>>>> +
>>>
>>> Stray extra whitespace line here.
>>>
>>>> +		WARN(1, "Wrong NUMA distance information\n");
>>>> +		/* consider everybody else just remote. */
>>>> +		for (i = 0;  i < max_numa_index; i++) {
>>>> +			for (j = 0; j < max_numa_index; j++) {
>>>> +				int nodeA = numa_id_index_table[i];
>>>> +				int nodeB = numa_id_index_table[j];
>>>> +
>>>> +				if (nodeA == nodeB)
>>>> +					numa_distance_table[nodeA][nodeB] = LOCAL_DISTANCE;
>>>> +				else
>>>> +					numa_distance_table[nodeA][nodeB] = REMOTE_DISTANCE;
>>>> +			}
>>>> +		}
>>>
>>> I don't think it's necessarily a problem, but something to consider is
>>> that this fallback will initialize distance for *all* node IDs,
>>> whereas the normal path will only initialize it for nodes that are in
>>> the index table.  Since some later error checks key off whether
>>> certain fields in the distance table are initialized, is that the
>>> outcome you want?
>>>
>>
>> With the device tree details not correct, one of the possible way to
>> make progress is to consider everybody remote. With new node hotplug
>> support we used to check whether the distance table entry is
>> initialized. With the updated spec, we expect all possible numa node
>> distance to be available during boot.
> 
> Sure.  But my main point here is that the fallback behaviour in this
> clause is different from the fallback behaviour if the table is there
> and parseable, but incomplete - which is also not expected.
> 

With FORM2 fallback with bad device tree details is to consider 
everybody REMOTE. With Form1, we leave the distance table not populated 
as it was with the current kernel versions.

-aneesh

[PATCH v7 6/6] powerpc/pseries: Consolidate form1 distance initialization into a helper

[Aneesh Kumar K.V]

Currently, we duplicate parsing code for ibm,associativity and
ibm,associativity-lookup-arrays in the kernel. The associativity array provided
by these device tree properties are very similar and hence can use
a helper to parse the node id and numa distance details.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 arch/powerpc/mm/numa.c | 104 +++++++++++++++++++++++------------------
 1 file changed, 58 insertions(+), 46 deletions(-)

diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index fffb3c40f595..e6d47fcba335 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -171,26 +171,36 @@ static void unmap_cpu_from_node(unsigned long cpu)
 }
 #endif /* CONFIG_HOTPLUG_CPU || CONFIG_PPC_SPLPAR */
 
-/*
- * Returns nid in the range [0..nr_node_ids], or -1 if no useful NUMA
- * info is found.
- */
-static int associativity_to_nid(const __be32 *associativity)
+static int __associativity_to_nid(const __be32 *associativity,
+				  int max_array_sz)
 {
-	int nid = NUMA_NO_NODE;
+	int nid;
+	/*
+	 * primary_domain_index is 1 based array index.
+	 */
+	int index = primary_domain_index  - 1;
 
-	if (!numa_enabled)
-		goto out;
+	if (!numa_enabled || index >= max_array_sz)
+		return NUMA_NO_NODE;
 
-	if (of_read_number(associativity, 1) >= primary_domain_index)
-		nid = of_read_number(&associativity[primary_domain_index], 1);
+	nid = of_read_number(&associativity[index], 1);
 
 	/* POWER4 LPAR uses 0xffff as invalid node */
 	if (nid == 0xffff || nid >= nr_node_ids)
 		nid = NUMA_NO_NODE;
-out:
 	return nid;
 }
+/*
+ * Returns nid in the range [0..nr_node_ids], or -1 if no useful NUMA
+ * info is found.
+ */
+static int associativity_to_nid(const __be32 *associativity)
+{
+	int array_sz = of_read_number(associativity, 1);
+
+	/* Skip the first element in the associativity array */
+	return __associativity_to_nid((associativity + 1), array_sz);
+}
 
 static int __cpu_form2_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
 {
@@ -295,33 +305,39 @@ int of_node_to_nid(struct device_node *device)
 }
 EXPORT_SYMBOL(of_node_to_nid);
 
-static void __initialize_form1_numa_distance(const __be32 *associativity)
+static void __initialize_form1_numa_distance(const __be32 *associativity,
+					     int max_array_sz)
 {
 	int i, nid;
 
 	if (affinity_form != FORM1_AFFINITY)
 		return;
 
-	nid = associativity_to_nid(associativity);
+	nid = __associativity_to_nid(associativity, max_array_sz);
 	if (nid != NUMA_NO_NODE) {
 		for (i = 0; i < distance_ref_points_depth; i++) {
 			const __be32 *entry;
+			int index = be32_to_cpu(distance_ref_points[i]) - 1;
+
+			/*
+			 * broken hierarchy, return with broken distance table
+			 */
+			if (WARN(index >= max_array_sz, "Broken ibm,associativity property"))
+				return;
 
-			entry = &associativity[be32_to_cpu(distance_ref_points[i])];
+			entry = &associativity[index];
 			distance_lookup_table[nid][i] = of_read_number(entry, 1);
 		}
 	}
 }
 
-static void initialize_form1_numa_distance(struct device_node *node)
+static void initialize_form1_numa_distance(const __be32 *associativity)
 {
-	const __be32 *associativity;
-
-	associativity = of_get_associativity(node);
-	if (!associativity)
-		return;
+	int array_sz;
 
-	__initialize_form1_numa_distance(associativity);
+	array_sz = of_read_number(associativity, 1);
+	/* Skip the first element in the associativity array */
+	__initialize_form1_numa_distance(associativity + 1, array_sz);
 }
 
 /*
@@ -334,7 +350,13 @@ void update_numa_distance(struct device_node *node)
 	if (affinity_form == FORM0_AFFINITY)
 		return;
 	else if (affinity_form == FORM1_AFFINITY) {
-		initialize_form1_numa_distance(node);
+		const __be32 *associativity;
+
+		associativity = of_get_associativity(node);
+		if (!associativity)
+			return;
+
+		initialize_form1_numa_distance(associativity);
 		return;
 	}
 
@@ -586,27 +608,17 @@ static int get_nid_and_numa_distance(struct drmem_lmb *lmb)
 
 	if (primary_domain_index <= aa.array_sz &&
 	    !(lmb->flags & DRCONF_MEM_AI_INVALID) && lmb->aa_index < aa.n_arrays) {
-		index = lmb->aa_index * aa.array_sz + primary_domain_index - 1;
-		nid = of_read_number(&aa.arrays[index], 1);
+		const __be32 *associativity;
 
-		if (nid == 0xffff || nid >= nr_node_ids)
-			nid = default_nid;
+		index = lmb->aa_index * aa.array_sz;
+		associativity = &aa.arrays[index];
+		nid = __associativity_to_nid(associativity, aa.array_sz);
 		if (nid > 0 && affinity_form == FORM1_AFFINITY) {
-			int i;
-			const __be32 *associativity;
-
-			index = lmb->aa_index * aa.array_sz;
-			associativity = &aa.arrays[index];
 			/*
-			 * lookup array associativity entries have different format
-			 * There is no length of the array as the first element.
+			 * lookup array associativity entries have
+			 * no length of the array as the first element.
 			 */
-			for (i = 0; i < distance_ref_points_depth; i++) {
-				const __be32 *entry;
-
-				entry = &associativity[be32_to_cpu(distance_ref_points[i]) - 1];
-				distance_lookup_table[nid][i] = of_read_number(entry, 1);
-			}
+			__initialize_form1_numa_distance(associativity, aa.array_sz);
 		}
 	}
 	return nid;
@@ -632,11 +644,11 @@ int of_drconf_to_nid_single(struct drmem_lmb *lmb)
 
 	if (primary_domain_index <= aa.array_sz &&
 	    !(lmb->flags & DRCONF_MEM_AI_INVALID) && lmb->aa_index < aa.n_arrays) {
-		index = lmb->aa_index * aa.array_sz + primary_domain_index - 1;
-		nid = of_read_number(&aa.arrays[index], 1);
+		const __be32 *associativity;
 
-		if (nid == 0xffff || nid >= nr_node_ids)
-			nid = default_nid;
+		index = lmb->aa_index * aa.array_sz;
+		associativity = &aa.arrays[index];
+		nid = __associativity_to_nid(associativity, aa.array_sz);
 	}
 	return nid;
 }
@@ -939,7 +951,7 @@ static int __init parse_numa_properties(void)
 
 		if (__vphn_get_associativity(i, vphn_assoc) == 0) {
 			nid = associativity_to_nid(vphn_assoc);
-			__initialize_form1_numa_distance(vphn_assoc);
+			initialize_form1_numa_distance(vphn_assoc);
 		} else {
 
 			/*
@@ -953,7 +965,7 @@ static int __init parse_numa_properties(void)
 			associativity = of_get_associativity(cpu);
 			if (associativity) {
 				nid = associativity_to_nid(associativity);
-				__initialize_form1_numa_distance(associativity);
+				initialize_form1_numa_distance(associativity);
 			}
 			of_node_put(cpu);
 		}
@@ -993,7 +1005,7 @@ static int __init parse_numa_properties(void)
 		associativity = of_get_associativity(memory);
 		if (associativity) {
 			nid = associativity_to_nid(associativity);
-			__initialize_form1_numa_distance(associativity);
+			initialize_form1_numa_distance(associativity);
 		} else
 			nid = default_nid;
 
-- 
2.31.1

Re: [PATCH v7 6/6] powerpc/pseries: Consolidate form1 distance initialization into a helper

[David Gibson]

[-- Attachment #1: Type: text/plain, Size: 7676 bytes --]

On Mon, Aug 09, 2021 at 10:54:34AM +0530, Aneesh Kumar K.V wrote:
> Currently, we duplicate parsing code for ibm,associativity and
> ibm,associativity-lookup-arrays in the kernel. The associativity array provided
> by these device tree properties are very similar and hence can use
> a helper to parse the node id and numa distance details.
> 
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>

Reviewed-by: David Gibson <david@gibson.dropbear.id.au>

Though I'd prefer to see these fixes folded in with the earlier patch.

> ---
>  arch/powerpc/mm/numa.c | 104 +++++++++++++++++++++++------------------
>  1 file changed, 58 insertions(+), 46 deletions(-)
> 
> diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
> index fffb3c40f595..e6d47fcba335 100644
> --- a/arch/powerpc/mm/numa.c
> +++ b/arch/powerpc/mm/numa.c
> @@ -171,26 +171,36 @@ static void unmap_cpu_from_node(unsigned long cpu)
>  }
>  #endif /* CONFIG_HOTPLUG_CPU || CONFIG_PPC_SPLPAR */
>  
> -/*
> - * Returns nid in the range [0..nr_node_ids], or -1 if no useful NUMA
> - * info is found.
> - */
> -static int associativity_to_nid(const __be32 *associativity)
> +static int __associativity_to_nid(const __be32 *associativity,
> +				  int max_array_sz)
>  {
> -	int nid = NUMA_NO_NODE;
> +	int nid;
> +	/*
> +	 * primary_domain_index is 1 based array index.
> +	 */
> +	int index = primary_domain_index  - 1;
>  
> -	if (!numa_enabled)
> -		goto out;
> +	if (!numa_enabled || index >= max_array_sz)
> +		return NUMA_NO_NODE;
>  
> -	if (of_read_number(associativity, 1) >= primary_domain_index)
> -		nid = of_read_number(&associativity[primary_domain_index], 1);
> +	nid = of_read_number(&associativity[index], 1);
>  
>  	/* POWER4 LPAR uses 0xffff as invalid node */
>  	if (nid == 0xffff || nid >= nr_node_ids)
>  		nid = NUMA_NO_NODE;
> -out:
>  	return nid;
>  }
> +/*
> + * Returns nid in the range [0..nr_node_ids], or -1 if no useful NUMA
> + * info is found.
> + */
> +static int associativity_to_nid(const __be32 *associativity)
> +{
> +	int array_sz = of_read_number(associativity, 1);
> +
> +	/* Skip the first element in the associativity array */
> +	return __associativity_to_nid((associativity + 1), array_sz);
> +}
>  
>  static int __cpu_form2_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
>  {
> @@ -295,33 +305,39 @@ int of_node_to_nid(struct device_node *device)
>  }
>  EXPORT_SYMBOL(of_node_to_nid);
>  
> -static void __initialize_form1_numa_distance(const __be32 *associativity)
> +static void __initialize_form1_numa_distance(const __be32 *associativity,
> +					     int max_array_sz)
>  {
>  	int i, nid;
>  
>  	if (affinity_form != FORM1_AFFINITY)
>  		return;
>  
> -	nid = associativity_to_nid(associativity);
> +	nid = __associativity_to_nid(associativity, max_array_sz);
>  	if (nid != NUMA_NO_NODE) {
>  		for (i = 0; i < distance_ref_points_depth; i++) {
>  			const __be32 *entry;
> +			int index = be32_to_cpu(distance_ref_points[i]) - 1;
> +
> +			/*
> +			 * broken hierarchy, return with broken distance table
> +			 */
> +			if (WARN(index >= max_array_sz, "Broken ibm,associativity property"))
> +				return;
>  
> -			entry = &associativity[be32_to_cpu(distance_ref_points[i])];
> +			entry = &associativity[index];
>  			distance_lookup_table[nid][i] = of_read_number(entry, 1);
>  		}
>  	}
>  }
>  
> -static void initialize_form1_numa_distance(struct device_node *node)
> +static void initialize_form1_numa_distance(const __be32 *associativity)
>  {
> -	const __be32 *associativity;
> -
> -	associativity = of_get_associativity(node);
> -	if (!associativity)
> -		return;
> +	int array_sz;
>  
> -	__initialize_form1_numa_distance(associativity);
> +	array_sz = of_read_number(associativity, 1);
> +	/* Skip the first element in the associativity array */
> +	__initialize_form1_numa_distance(associativity + 1, array_sz);
>  }
>  
>  /*
> @@ -334,7 +350,13 @@ void update_numa_distance(struct device_node *node)
>  	if (affinity_form == FORM0_AFFINITY)
>  		return;
>  	else if (affinity_form == FORM1_AFFINITY) {
> -		initialize_form1_numa_distance(node);
> +		const __be32 *associativity;
> +
> +		associativity = of_get_associativity(node);
> +		if (!associativity)
> +			return;
> +
> +		initialize_form1_numa_distance(associativity);
>  		return;
>  	}
>  
> @@ -586,27 +608,17 @@ static int get_nid_and_numa_distance(struct drmem_lmb *lmb)
>  
>  	if (primary_domain_index <= aa.array_sz &&
>  	    !(lmb->flags & DRCONF_MEM_AI_INVALID) && lmb->aa_index < aa.n_arrays) {
> -		index = lmb->aa_index * aa.array_sz + primary_domain_index - 1;
> -		nid = of_read_number(&aa.arrays[index], 1);
> +		const __be32 *associativity;
>  
> -		if (nid == 0xffff || nid >= nr_node_ids)
> -			nid = default_nid;
> +		index = lmb->aa_index * aa.array_sz;
> +		associativity = &aa.arrays[index];
> +		nid = __associativity_to_nid(associativity, aa.array_sz);
>  		if (nid > 0 && affinity_form == FORM1_AFFINITY) {
> -			int i;
> -			const __be32 *associativity;
> -
> -			index = lmb->aa_index * aa.array_sz;
> -			associativity = &aa.arrays[index];
>  			/*
> -			 * lookup array associativity entries have different format
> -			 * There is no length of the array as the first element.
> +			 * lookup array associativity entries have
> +			 * no length of the array as the first element.
>  			 */
> -			for (i = 0; i < distance_ref_points_depth; i++) {
> -				const __be32 *entry;
> -
> -				entry = &associativity[be32_to_cpu(distance_ref_points[i]) - 1];
> -				distance_lookup_table[nid][i] = of_read_number(entry, 1);
> -			}
> +			__initialize_form1_numa_distance(associativity, aa.array_sz);
>  		}
>  	}
>  	return nid;
> @@ -632,11 +644,11 @@ int of_drconf_to_nid_single(struct drmem_lmb *lmb)
>  
>  	if (primary_domain_index <= aa.array_sz &&
>  	    !(lmb->flags & DRCONF_MEM_AI_INVALID) && lmb->aa_index < aa.n_arrays) {
> -		index = lmb->aa_index * aa.array_sz + primary_domain_index - 1;
> -		nid = of_read_number(&aa.arrays[index], 1);
> +		const __be32 *associativity;
>  
> -		if (nid == 0xffff || nid >= nr_node_ids)
> -			nid = default_nid;
> +		index = lmb->aa_index * aa.array_sz;
> +		associativity = &aa.arrays[index];
> +		nid = __associativity_to_nid(associativity, aa.array_sz);
>  	}
>  	return nid;
>  }
> @@ -939,7 +951,7 @@ static int __init parse_numa_properties(void)
>  
>  		if (__vphn_get_associativity(i, vphn_assoc) == 0) {
>  			nid = associativity_to_nid(vphn_assoc);
> -			__initialize_form1_numa_distance(vphn_assoc);
> +			initialize_form1_numa_distance(vphn_assoc);
>  		} else {
>  
>  			/*
> @@ -953,7 +965,7 @@ static int __init parse_numa_properties(void)
>  			associativity = of_get_associativity(cpu);
>  			if (associativity) {
>  				nid = associativity_to_nid(associativity);
> -				__initialize_form1_numa_distance(associativity);
> +				initialize_form1_numa_distance(associativity);
>  			}
>  			of_node_put(cpu);
>  		}
> @@ -993,7 +1005,7 @@ static int __init parse_numa_properties(void)
>  		associativity = of_get_associativity(memory);
>  		if (associativity) {
>  			nid = associativity_to_nid(associativity);
> -			__initialize_form1_numa_distance(associativity);
> +			initialize_form1_numa_distance(associativity);
>  		} else
>  			nid = default_nid;
>  

-- 
David Gibson			| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you.  NOT _the_ _other_
				| _way_ _around_!
http://www.ozlabs.org/~dgibson

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

Re: [PATCH v7 0/6] Add support for FORM2 associativity

[Daniel Henrique Barboza]

On 8/9/21 2:24 AM, Aneesh Kumar K.V wrote:
> Form2 associativity adds a much more flexible NUMA topology layout
> than what is provided by Form1. More details can be found in patch 7.
> 
> $ numactl -H
> ...
> node distances:
> node   0   1   2   3
>    0:  10  11  222  33
>    1:  44  10  55  66
>    2:  77  88  10  99
>    3:  101  121  132  10
> $
> 
> After DAX kmem memory add
> # numactl -H
> available: 5 nodes (0-4)
> ...
> node distances:
> node   0   1   2   3   4
>    0:  10  11  222  33  240
>    1:  44  10  55  66  255
>    2:  77  88  10  99  255
>    3:  101  121  132  10  230
>    4:  255  255  255  230  10
> 
> 
> PAPR SCM now use the numa distance details to find the numa_node and target_node
> for the device.
> 
> kvaneesh@ubuntu-guest:~$ ndctl  list -N -v
> [
>    {
>      "dev":"namespace0.0",
>      "mode":"devdax",
>      "map":"dev",
>      "size":1071644672,
>      "uuid":"d333d867-3f57-44c8-b386-d4d3abdc2bf2",
>      "raw_uuid":"915361ad-fe6a-42dd-848f-d6dc9f5af362",
>      "daxregion":{
>        "id":0,
>        "size":1071644672,
>        "devices":[
>          {
>            "chardev":"dax0.0",
>            "size":1071644672,
>            "target_node":4,
>            "mode":"devdax"
>          }
>        ]
>      },
>      "align":2097152,
>      "numa_node":3
>    }
> ]
> kvaneesh@ubuntu-guest:~$
> 
> 
> The above output is with a Qemu command line
> 
> -numa node,nodeid=4 \
> -numa dist,src=0,dst=1,val=11 -numa dist,src=0,dst=2,val=222 -numa dist,src=0,dst=3,val=33 -numa dist,src=0,dst=4,val=240 \
> -numa dist,src=1,dst=0,val=44 -numa dist,src=1,dst=2,val=55 -numa dist,src=1,dst=3,val=66 -numa dist,src=1,dst=4,val=255 \
> -numa dist,src=2,dst=0,val=77 -numa dist,src=2,dst=1,val=88 -numa dist,src=2,dst=3,val=99 -numa dist,src=2,dst=4,val=255 \
> -numa dist,src=3,dst=0,val=101 -numa dist,src=3,dst=1,val=121 -numa dist,src=3,dst=2,val=132 -numa dist,src=3,dst=4,val=230 \
> -numa dist,src=4,dst=0,val=255 -numa dist,src=4,dst=1,val=255 -numa dist,src=4,dst=2,val=255 -numa dist,src=4,dst=3,val=230 \
> -object memory-backend-file,id=memnvdimm1,prealloc=yes,mem-path=$PMEM_DISK,share=yes,size=${PMEM_SIZE}  \
> -device nvdimm,label-size=128K,memdev=memnvdimm1,id=nvdimm1,slot=4,uuid=72511b67-0b3b-42fd-8d1d-5be3cae8bcaa,node=4
> 
> Qemu changes can be found at https://lore.kernel.org/qemu-devel/20210616011944.2996399-1-danielhb413@gmail.com/


Series tested with the forementioned QEMU build. All patches:


Tested-by: Daniel Henrique Barboza <danielhb413@gmail.com>

> 
> Changes from v6:
> * Address review feedback
> 
> Changes from v5:
> * Fix build error reported by kernel test robot
> * Address review feedback
> 
> Changes from v4:
> * Drop DLPAR related device tree property for now because both Qemu nor PowerVM
>    will provide the distance details of all possible NUMA nodes during boot.
> * Rework numa distance code based on review feedback.
> 
> Changes from v3:
> * Drop PAPR SCM specific changes and depend completely on NUMA distance information.
> 
> Changes from v2:
> * Add nvdimm list to Cc:
> * update PATCH 8 commit message.
> 
> Changes from v1:
> * Update FORM2 documentation.
> * rename max_domain_index to max_associativity_domain_index
> 
> 
> Aneesh Kumar K.V (6):
>    powerpc/pseries: rename min_common_depth to primary_domain_index
>    powerpc/pseries: Rename TYPE1_AFFINITY to FORM1_AFFINITY
>    powerpc/pseries: Consolidate different NUMA distance update code paths
>    powerpc/pseries: Add a helper for form1 cpu distance
>    powerpc/pseries: Add support for FORM2 associativity
>    powerpc/pseries: Consolidate form1 distance initialization into a
>      helper
> 
>   Documentation/powerpc/associativity.rst       | 103 +++++
>   arch/powerpc/include/asm/firmware.h           |   7 +-
>   arch/powerpc/include/asm/prom.h               |   3 +-
>   arch/powerpc/include/asm/topology.h           |   6 +-
>   arch/powerpc/kernel/prom_init.c               |   3 +-
>   arch/powerpc/mm/numa.c                        | 433 ++++++++++++++----
>   arch/powerpc/platforms/pseries/firmware.c     |   3 +-
>   arch/powerpc/platforms/pseries/hotplug-cpu.c  |   2 +
>   .../platforms/pseries/hotplug-memory.c        |   2 +
>   arch/powerpc/platforms/pseries/lpar.c         |   4 +-
>   10 files changed, 455 insertions(+), 111 deletions(-)
>   create mode 100644 Documentation/powerpc/associativity.rst
>