perf/x86/intel/uncore: With > 8 nodes, get pci bus die id from NUMA info

The registers used to determine which die a pci bus belongs to don't
contain enough information to uniquely specify more than 8 dies, so
when more than 8 dies are present, use NUMA information instead.

Continue to use the previous method for 8 or fewer because it
works there, and covers cases of NUMA being disabled.

Signed-off-by: Steve Wahl <steve.wahl@hpe.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Link: https://lkml.kernel.org/r/20210108153549.108989-3-steve.wahl@hpe.com

1 files changed, 65 insertions, 28 deletions

diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 2d7014dc46f6..b79951d0707c 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -1370,40 +1370,77 @@ static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool
 		if (!ubox_dev)
 			break;
 		bus = ubox_dev->bus->number;
-		/* get the Node ID of the local register */
-		err = pci_read_config_dword(ubox_dev, nodeid_loc, &config);
-		if (err)
-			break;
-		nodeid = config & NODE_ID_MASK;
-		/* get the Node ID mapping */
-		err = pci_read_config_dword(ubox_dev, idmap_loc, &config);
-		if (err)
-			break;
+		/*
+		 * The nodeid and idmap registers only contain enough
+		 * information to handle 8 nodes.  On systems with more
+		 * than 8 nodes, we need to rely on NUMA information,
+		 * filled in from BIOS supplied information, to determine
+		 * the topology.
+		 */
+		if (nr_node_ids <= 8) {
+			/* get the Node ID of the local register */
+			err = pci_read_config_dword(ubox_dev, nodeid_loc, &config);
+			if (err)
+				break;
+			nodeid = config & NODE_ID_MASK;
+			/* get the Node ID mapping */
+			err = pci_read_config_dword(ubox_dev, idmap_loc, &config);
+			if (err)
+				break;
 
-		segment = pci_domain_nr(ubox_dev->bus);
-		raw_spin_lock(&pci2phy_map_lock);
-		map = __find_pci2phy_map(segment);
-		if (!map) {
+			segment = pci_domain_nr(ubox_dev->bus);
+			raw_spin_lock(&pci2phy_map_lock);
+			map = __find_pci2phy_map(segment);
+			if (!map) {
+				raw_spin_unlock(&pci2phy_map_lock);
+				err = -ENOMEM;
+				break;
+			}
+
+			/*
+			 * every three bits in the Node ID mapping register maps
+			 * to a particular node.
+			 */
+			for (i = 0; i < 8; i++) {
+				if (nodeid == ((config >> (3 * i)) & 0x7)) {
+					if (topology_max_die_per_package() > 1)
+						die_id = i;
+					else
+						die_id = topology_phys_to_logical_pkg(i);
+					map->pbus_to_dieid[bus] = die_id;
+					break;
+				}
+			}
 			raw_spin_unlock(&pci2phy_map_lock);
-			err = -ENOMEM;
-			break;
-		}
+		} else {
+			int node = pcibus_to_node(ubox_dev->bus);
+			int cpu;
+
+			segment = pci_domain_nr(ubox_dev->bus);
+			raw_spin_lock(&pci2phy_map_lock);
+			map = __find_pci2phy_map(segment);
+			if (!map) {
+				raw_spin_unlock(&pci2phy_map_lock);
+				err = -ENOMEM;
+				break;
+			}
 
-		/*
-		 * every three bits in the Node ID mapping register maps
-		 * to a particular node.
-		 */
-		for (i = 0; i < 8; i++) {
-			if (nodeid == ((config >> (3 * i)) & 0x7)) {
-				if (topology_max_die_per_package() > 1)
-					die_id = i;
-				else
-					die_id = topology_phys_to_logical_pkg(i);
-				map->pbus_to_dieid[bus] = die_id;
+			die_id = -1;
+			for_each_cpu(cpu, cpumask_of_pcibus(ubox_dev->bus)) {
+				struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+				if (c->initialized && cpu_to_node(cpu) == node) {
+					map->pbus_to_dieid[bus] = die_id = c->logical_die_id;
+					break;
+				}
+			}
+			raw_spin_unlock(&pci2phy_map_lock);
+
+			if (WARN_ON_ONCE(die_id == -1)) {
+				err = -EINVAL;
 				break;
 			}
 		}
-		raw_spin_unlock(&pci2phy_map_lock);
 	}
 
 	if (!err) {