Merge branch 'for-6.9/cxl-qos' into for-6.9/cxl

Pick up support for CXL "HMEM reporting" for v6.9, i.e. build an HMAT
from CXL CDAT and PCIe switch information.

Author: djbw

Documentation/ABI/testing/sysfs-bus-cxl

@@ -552,3 +552,37 @@ Description:
 		attribute is only visible for devices supporting the
 		capability. The retrieved errors are logged as kernel
 		events when cxl_poison event tracing is enabled.
+
+
+What:		/sys/bus/cxl/devices/regionZ/accessY/read_bandwidth
+		/sys/bus/cxl/devices/regionZ/accessY/write_banwidth
+Date:		Jan, 2024
+KernelVersion:	v6.9
+Contact:	linux-cxl@vger.kernel.org
+Description:
+		(RO) The aggregated read or write bandwidth of the region. The
+		number is the accumulated read or write bandwidth of all CXL memory
+		devices that contributes to the region in MB/s. It is
+		identical data that should appear in
+		/sys/devices/system/node/nodeX/accessY/initiators/read_bandwidth or
+		/sys/devices/system/node/nodeX/accessY/initiators/write_bandwidth.
+		See Documentation/ABI/stable/sysfs-devices-node. access0 provides
+		the number to the closest initiator and access1 provides the
+		number to the closest CPU.
+
+
+What:		/sys/bus/cxl/devices/regionZ/accessY/read_latency
+		/sys/bus/cxl/devices/regionZ/accessY/write_latency
+Date:		Jan, 2024
+KernelVersion:	v6.9
+Contact:	linux-cxl@vger.kernel.org
+Description:
+		(RO) The read or write latency of the region. The number is
+		the worst read or write latency of all CXL memory devices that
+		contributes to the region in nanoseconds. It is identical data
+		that should appear in
+		/sys/devices/system/node/nodeX/accessY/initiators/read_latency or
+		/sys/devices/system/node/nodeX/accessY/initiators/write_latency.
+		See Documentation/ABI/stable/sysfs-devices-node. access0 provides
+		the number to the closest initiator and access1 provides the
+		number to the closest CPU.

drivers/acpi/numa/hmat.c

@@ -59,9 +59,8 @@ struct target_cache {
 };
 
 enum {
-	NODE_ACCESS_CLASS_0 = 0,
-	NODE_ACCESS_CLASS_1,
-	NODE_ACCESS_CLASS_GENPORT_SINK,
+	NODE_ACCESS_CLASS_GENPORT_SINK_LOCAL = ACCESS_COORDINATE_MAX,
+	NODE_ACCESS_CLASS_GENPORT_SINK_CPU,
 	NODE_ACCESS_CLASS_MAX,
 };
 
@@ -75,6 +74,7 @@ struct memory_target {
 	struct node_cache_attrs cache_attrs;
 	u8 gen_port_device_handle[ACPI_SRAT_DEVICE_HANDLE_SIZE];
 	bool registered;
+	bool ext_updated;	/* externally updated */
 };
 
 struct memory_initiator {
@@ -127,7 +127,8 @@ static struct memory_target *acpi_find_genport_target(u32 uid)
 /**
  * acpi_get_genport_coordinates - Retrieve the access coordinates for a generic port
  * @uid: ACPI unique id
- * @coord: The access coordinates written back out for the generic port
+ * @coord: The access coordinates written back out for the generic port.
+ *	   Expect 2 levels array.
  *
  * Return: 0 on success. Errno on failure.
  *
@@ -143,7 +144,10 @@ int acpi_get_genport_coordinates(u32 uid,
 	if (!target)
 		return -ENOENT;
 
-	*coord = target->coord[NODE_ACCESS_CLASS_GENPORT_SINK];
+	coord[ACCESS_COORDINATE_LOCAL] =
+		target->coord[NODE_ACCESS_CLASS_GENPORT_SINK_LOCAL];
+	coord[ACCESS_COORDINATE_CPU] =
+		target->coord[NODE_ACCESS_CLASS_GENPORT_SINK_CPU];
 
 	return 0;
 }
@@ -325,6 +329,35 @@ static void hmat_update_target_access(struct memory_target *target,
 	}
 }
 
+int hmat_update_target_coordinates(int nid, struct access_coordinate *coord,
+				   enum access_coordinate_class access)
+{
+	struct memory_target *target;
+	int pxm;
+
+	if (nid == NUMA_NO_NODE)
+		return -EINVAL;
+
+	pxm = node_to_pxm(nid);
+	guard(mutex)(&target_lock);
+	target = find_mem_target(pxm);
+	if (!target)
+		return -ENODEV;
+
+	hmat_update_target_access(target, ACPI_HMAT_READ_LATENCY,
+				  coord->read_latency, access);
+	hmat_update_target_access(target, ACPI_HMAT_WRITE_LATENCY,
+				  coord->write_latency, access);
+	hmat_update_target_access(target, ACPI_HMAT_READ_BANDWIDTH,
+				  coord->read_bandwidth, access);
+	hmat_update_target_access(target, ACPI_HMAT_WRITE_BANDWIDTH,
+				  coord->write_bandwidth, access);
+	target->ext_updated = true;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(hmat_update_target_coordinates);
+
 static __init void hmat_add_locality(struct acpi_hmat_locality *hmat_loc)
 {
 	struct memory_locality *loc;
@@ -374,11 +407,11 @@ static __init void hmat_update_target(unsigned int tgt_pxm, unsigned int init_px
 
 	if (target && target->processor_pxm == init_pxm) {
 		hmat_update_target_access(target, type, value,
-					  NODE_ACCESS_CLASS_0);
+					  ACCESS_COORDINATE_LOCAL);
 		/* If the node has a CPU, update access 1 */
 		if (node_state(pxm_to_node(init_pxm), N_CPU))
 			hmat_update_target_access(target, type, value,
-						  NODE_ACCESS_CLASS_1);
+						  ACCESS_COORDINATE_CPU);
 	}
 }
 
@@ -696,8 +729,13 @@ static void hmat_update_target_attrs(struct memory_target *target,
 	u32 best = 0;
 	int i;
 
+	/* Don't update if an external agent has changed the data.  */
+	if (target->ext_updated)
+		return;
+
 	/* Don't update for generic port if there's no device handle */
-	if (access == NODE_ACCESS_CLASS_GENPORT_SINK &&
+	if ((access == NODE_ACCESS_CLASS_GENPORT_SINK_LOCAL ||
+	     access == NODE_ACCESS_CLASS_GENPORT_SINK_CPU) &&
 	    !(*(u16 *)target->gen_port_device_handle))
 		return;
 
@@ -709,7 +747,8 @@ static void hmat_update_target_attrs(struct memory_target *target,
 	 */
 	if (target->processor_pxm != PXM_INVAL) {
 		cpu_nid = pxm_to_node(target->processor_pxm);
-		if (access == 0 || node_state(cpu_nid, N_CPU)) {
+		if (access == ACCESS_COORDINATE_LOCAL ||
+		    node_state(cpu_nid, N_CPU)) {
 			set_bit(target->processor_pxm, p_nodes);
 			return;
 		}
@@ -737,7 +776,9 @@ static void hmat_update_target_attrs(struct memory_target *target,
 		list_for_each_entry(initiator, &initiators, node) {
 			u32 value;
 
-			if (access == 1 && !initiator->has_cpu) {
+			if ((access == ACCESS_COORDINATE_CPU ||
+			     access == NODE_ACCESS_CLASS_GENPORT_SINK_CPU) &&
+			    !initiator->has_cpu) {
 				clear_bit(initiator->processor_pxm, p_nodes);
 				continue;
 			}
@@ -770,20 +811,24 @@ static void __hmat_register_target_initiators(struct memory_target *target,
 	}
 }
 
-static void hmat_register_generic_target_initiators(struct memory_target *target)
+static void hmat_update_generic_target(struct memory_target *target)
 {
 	static DECLARE_BITMAP(p_nodes, MAX_NUMNODES);
 
-	__hmat_register_target_initiators(target, p_nodes,
-					  NODE_ACCESS_CLASS_GENPORT_SINK);
+	hmat_update_target_attrs(target, p_nodes,
+				 NODE_ACCESS_CLASS_GENPORT_SINK_LOCAL);
+	hmat_update_target_attrs(target, p_nodes,
+				 NODE_ACCESS_CLASS_GENPORT_SINK_CPU);
 }
 
 static void hmat_register_target_initiators(struct memory_target *target)
 {
 	static DECLARE_BITMAP(p_nodes, MAX_NUMNODES);
 
-	__hmat_register_target_initiators(target, p_nodes, 0);
-	__hmat_register_target_initiators(target, p_nodes, 1);
+	__hmat_register_target_initiators(target, p_nodes,
+					  ACCESS_COORDINATE_LOCAL);
+	__hmat_register_target_initiators(target, p_nodes,
+					  ACCESS_COORDINATE_CPU);
 }
 
 static void hmat_register_target_cache(struct memory_target *target)
@@ -835,7 +880,7 @@ static void hmat_register_target(struct memory_target *target)
 	 */
 	mutex_lock(&target_lock);
 	if (*(u16 *)target->gen_port_device_handle) {
-		hmat_register_generic_target_initiators(target);
+		hmat_update_generic_target(target);
 		target->registered = true;
 	}
 	mutex_unlock(&target_lock);
@@ -854,8 +899,8 @@ static void hmat_register_target(struct memory_target *target)
 	if (!target->registered) {
 		hmat_register_target_initiators(target);
 		hmat_register_target_cache(target);
-		hmat_register_target_perf(target, NODE_ACCESS_CLASS_0);
-		hmat_register_target_perf(target, NODE_ACCESS_CLASS_1);
+		hmat_register_target_perf(target, ACCESS_COORDINATE_LOCAL);
+		hmat_register_target_perf(target, ACCESS_COORDINATE_CPU);
 		target->registered = true;
 	}
 	mutex_unlock(&target_lock);
@@ -927,7 +972,7 @@ static int hmat_calculate_adistance(struct notifier_block *self,
 		return NOTIFY_OK;
 
 	mutex_lock(&target_lock);
-	hmat_update_target_attrs(target, p_nodes, 1);
+	hmat_update_target_attrs(target, p_nodes, ACCESS_COORDINATE_CPU);
 	mutex_unlock(&target_lock);
 
 	perf = &target->coord[1];

drivers/acpi/numa/srat.c

@@ -29,6 +29,8 @@ static int node_to_pxm_map[MAX_NUMNODES]
 unsigned char acpi_srat_revision __initdata;
 static int acpi_numa __initdata;
 
+static int last_real_pxm;
+
 void __init disable_srat(void)
 {
 	acpi_numa = -1;
@@ -536,6 +538,7 @@ int __init acpi_numa_init(void)
 		if (node_to_pxm_map[i] > fake_pxm)
 			fake_pxm = node_to_pxm_map[i];
 	}
+	last_real_pxm = fake_pxm;
 	fake_pxm++;
 	acpi_table_parse_cedt(ACPI_CEDT_TYPE_CFMWS, acpi_parse_cfmws,
 			      &fake_pxm);
@@ -547,6 +550,14 @@ int __init acpi_numa_init(void)
 	return 0;
 }
 
+bool acpi_node_backed_by_real_pxm(int nid)
+{
+	int pxm = node_to_pxm(nid);
+
+	return pxm <= last_real_pxm;
+}
+EXPORT_SYMBOL_GPL(acpi_node_backed_by_real_pxm);
+
 static int acpi_get_pxm(acpi_handle h)
 {
 	unsigned long long pxm;

drivers/base/node.c

@@ -126,7 +126,7 @@ static void node_access_release(struct device *dev)
 }
 
 static struct node_access_nodes *node_init_node_access(struct node *node,
-						       unsigned int access)
+						       enum access_coordinate_class access)
 {
 	struct node_access_nodes *access_node;
 	struct device *dev;
@@ -191,7 +191,7 @@ static struct attribute *access_attrs[] = {
  * @access: The access class the for the given attributes
  */
 void node_set_perf_attrs(unsigned int nid, struct access_coordinate *coord,
-			 unsigned int access)
+			 enum access_coordinate_class access)
 {
 	struct node_access_nodes *c;
 	struct node *node;
@@ -215,6 +215,7 @@ void node_set_perf_attrs(unsigned int nid, struct access_coordinate *coord,
 		}
 	}
 }
+EXPORT_SYMBOL_GPL(node_set_perf_attrs);
 
 /**
  * struct node_cache_info - Internal tracking for memory node caches
@@ -689,7 +690,7 @@ int register_cpu_under_node(unsigned int cpu, unsigned int nid)
  */
 int register_memory_node_under_compute_node(unsigned int mem_nid,
 					    unsigned int cpu_nid,
-					    unsigned int access)
+					    enum access_coordinate_class access)
 {
 	struct node *init_node, *targ_node;
 	struct node_access_nodes *initiator, *target;

drivers/cxl/acpi.c

@@ -530,13 +530,15 @@ static int get_genport_coordinates(struct device *dev, struct cxl_dport *dport)
 	if (kstrtou32(acpi_device_uid(hb), 0, &uid))
 		return -EINVAL;
 
-	rc = acpi_get_genport_coordinates(uid, &dport->hb_coord);
+	rc = acpi_get_genport_coordinates(uid, dport->hb_coord);
 	if (rc < 0)
 		return rc;
 
 	/* Adjust back to picoseconds from nanoseconds */
-	dport->hb_coord.read_latency *= 1000;
-	dport->hb_coord.write_latency *= 1000;
+	for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) {
+		dport->hb_coord[i].read_latency *= 1000;
+		dport->hb_coord[i].write_latency *= 1000;
+	}
 
 	return 0;
 }