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.

6 files changed, 342 insertions, 33 deletions

diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c
index 1a3e6aafbdcc..af5cb818f84d 100644
--- a/drivers/cxl/acpi.c
+++ b/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;
 }
diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c
index c8737e480789..e8c066293b31 100644
--- a/drivers/cxl/core/cdat.c
+++ b/drivers/cxl/core/cdat.c
@@ -9,6 +9,7 @@
 #include "cxlmem.h"
 #include "core.h"
 #include "cxl.h"
+#include "core.h"
 
 struct dsmas_entry {
 	struct range dpa_range;
@@ -162,15 +163,22 @@ static int cxl_cdat_endpoint_process(struct cxl_port *port,
 static int cxl_port_perf_data_calculate(struct cxl_port *port,
 					struct xarray *dsmas_xa)
 {
-	struct access_coordinate c;
+	struct access_coordinate ep_c;
+	struct access_coordinate coord[ACCESS_COORDINATE_MAX];
 	struct dsmas_entry *dent;
 	int valid_entries = 0;
 	unsigned long index;
 	int rc;
 
-	rc = cxl_endpoint_get_perf_coordinates(port, &c);
+	rc = cxl_endpoint_get_perf_coordinates(port, &ep_c);
 	if (rc) {
-		dev_dbg(&port->dev, "Failed to retrieve perf coordinates.\n");
+		dev_dbg(&port->dev, "Failed to retrieve ep perf coordinates.\n");
+		return rc;
+	}
+
+	rc = cxl_hb_get_perf_coordinates(port, coord);
+	if (rc)  {
+		dev_dbg(&port->dev, "Failed to retrieve hb perf coordinates.\n");
 		return rc;
 	}
 
@@ -185,18 +193,19 @@ static int cxl_port_perf_data_calculate(struct cxl_port *port,
 	xa_for_each(dsmas_xa, index, dent) {
 		int qos_class;
 
-		dent->coord.read_latency = dent->coord.read_latency +
-					   c.read_latency;
-		dent->coord.write_latency = dent->coord.write_latency +
-					    c.write_latency;
-		dent->coord.read_bandwidth = min_t(int, c.read_bandwidth,
-						   dent->coord.read_bandwidth);
-		dent->coord.write_bandwidth = min_t(int, c.write_bandwidth,
-						    dent->coord.write_bandwidth);
-
+		cxl_coordinates_combine(&dent->coord, &dent->coord, &ep_c);
+		/*
+		 * Keeping the host bridge coordinates separate from the dsmas
+		 * coordinates in order to allow calculation of access class
+		 * 0 and 1 for region later.
+		 */
+		cxl_coordinates_combine(&coord[ACCESS_COORDINATE_CPU],
+					&coord[ACCESS_COORDINATE_CPU],
+					&dent->coord);
 		dent->entries = 1;
-		rc = cxl_root->ops->qos_class(cxl_root, &dent->coord, 1,
-					      &qos_class);
+		rc = cxl_root->ops->qos_class(cxl_root,
+					      &coord[ACCESS_COORDINATE_CPU],
+					      1, &qos_class);
 		if (rc != 1)
 			continue;
 
@@ -484,4 +493,101 @@ void cxl_switch_parse_cdat(struct cxl_port *port)
 }
 EXPORT_SYMBOL_NS_GPL(cxl_switch_parse_cdat, CXL);
 
+/**
+ * cxl_coordinates_combine - Combine the two input coordinates
+ *
+ * @out: Output coordinate of c1 and c2 combined
+ * @c1: input coordinates
+ * @c2: input coordinates
+ */
+void cxl_coordinates_combine(struct access_coordinate *out,
+			     struct access_coordinate *c1,
+			     struct access_coordinate *c2)
+{
+		if (c1->write_bandwidth && c2->write_bandwidth)
+			out->write_bandwidth = min(c1->write_bandwidth,
+						   c2->write_bandwidth);
+		out->write_latency = c1->write_latency + c2->write_latency;
+
+		if (c1->read_bandwidth && c2->read_bandwidth)
+			out->read_bandwidth = min(c1->read_bandwidth,
+						  c2->read_bandwidth);
+		out->read_latency = c1->read_latency + c2->read_latency;
+}
+
 MODULE_IMPORT_NS(CXL);
+
+void cxl_region_perf_data_calculate(struct cxl_region *cxlr,
+				    struct cxl_endpoint_decoder *cxled)
+{
+	struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
+	struct cxl_port *port = cxlmd->endpoint;
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
+	struct access_coordinate hb_coord[ACCESS_COORDINATE_MAX];
+	struct access_coordinate coord;
+	struct range dpa = {
+			.start = cxled->dpa_res->start,
+			.end = cxled->dpa_res->end,
+	};
+	struct cxl_dpa_perf *perf;
+	int rc;
+
+	switch (cxlr->mode) {
+	case CXL_DECODER_RAM:
+		perf = &mds->ram_perf;
+		break;
+	case CXL_DECODER_PMEM:
+		perf = &mds->pmem_perf;
+		break;
+	default:
+		return;
+	}
+
+	lockdep_assert_held(&cxl_dpa_rwsem);
+
+	if (!range_contains(&perf->dpa_range, &dpa))
+		return;
+
+	rc = cxl_hb_get_perf_coordinates(port, hb_coord);
+	if (rc)  {
+		dev_dbg(&port->dev, "Failed to retrieve hb perf coordinates.\n");
+		return;
+	}
+
+	for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) {
+		/* Pickup the host bridge coords */
+		cxl_coordinates_combine(&coord, &hb_coord[i], &perf->coord);
+
+		/* Get total bandwidth and the worst latency for the cxl region */
+		cxlr->coord[i].read_latency = max_t(unsigned int,
+						    cxlr->coord[i].read_latency,
+						    coord.read_latency);
+		cxlr->coord[i].write_latency = max_t(unsigned int,
+						     cxlr->coord[i].write_latency,
+						     coord.write_latency);
+		cxlr->coord[i].read_bandwidth += coord.read_bandwidth;
+		cxlr->coord[i].write_bandwidth += coord.write_bandwidth;
+
+		/*
+		 * Convert latency to nanosec from picosec to be consistent
+		 * with the resulting latency coordinates computed by the
+		 * HMAT_REPORTING code.
+		 */
+		cxlr->coord[i].read_latency =
+			DIV_ROUND_UP(cxlr->coord[i].read_latency, 1000);
+		cxlr->coord[i].write_latency =
+			DIV_ROUND_UP(cxlr->coord[i].write_latency, 1000);
+	}
+}
+
+int cxl_update_hmat_access_coordinates(int nid, struct cxl_region *cxlr,
+				       enum access_coordinate_class access)
+{
+	return hmat_update_target_coordinates(nid, &cxlr->coord[access], access);
+}
+
+bool cxl_need_node_perf_attrs_update(int nid)
+{
+	return !acpi_node_backed_by_real_pxm(nid);
+}
diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h
index 3b64fb1b9ed0..bc5a95665aa0 100644
--- a/drivers/cxl/core/core.h
+++ b/drivers/cxl/core/core.h
@@ -90,4 +90,8 @@ enum cxl_poison_trace_type {
 
 long cxl_pci_get_latency(struct pci_dev *pdev);
 
+int cxl_update_hmat_access_coordinates(int nid, struct cxl_region *cxlr,
+				       enum access_coordinate_class access);
+bool cxl_need_node_perf_attrs_update(int nid);
+
 #endif /* __CXL_CORE_H__ */
diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index e59d9d37aa65..9ab542e7af65 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -822,6 +822,7 @@ static struct cxl_port *__devm_cxl_add_port(struct device *host,
 		 */
 		port->reg_map = cxlds->reg_map;
 		port->reg_map.host = &port->dev;
+		cxlmd->endpoint = port;
 	} else if (parent_dport) {
 		rc = dev_set_name(dev, "port%d", port->id);
 		if (rc)
@@ -1374,7 +1375,6 @@ int cxl_endpoint_autoremove(struct cxl_memdev *cxlmd, struct cxl_port *endpoint)
 
 	get_device(host);
 	get_device(&endpoint->dev);
-	cxlmd->endpoint = endpoint;
 	cxlmd->depth = endpoint->depth;
 	return devm_add_action_or_reset(dev, delete_endpoint, cxlmd);
 }
@@ -2096,18 +2096,36 @@ bool schedule_cxl_memdev_detach(struct cxl_memdev *cxlmd)
 }
 EXPORT_SYMBOL_NS_GPL(schedule_cxl_memdev_detach, CXL);
 
-static void combine_coordinates(struct access_coordinate *c1,
-				struct access_coordinate *c2)
+/**
+ * cxl_hb_get_perf_coordinates - Retrieve performance numbers between initiator
+ *				 and host bridge
+ *
+ * @port: endpoint cxl_port
+ * @coord: output access coordinates
+ *
+ * Return: errno on failure, 0 on success.
+ */
+int cxl_hb_get_perf_coordinates(struct cxl_port *port,
+				struct access_coordinate *coord)
 {
-		if (c2->write_bandwidth)
-			c1->write_bandwidth = min(c1->write_bandwidth,
-						  c2->write_bandwidth);
-		c1->write_latency += c2->write_latency;
+	struct cxl_port *iter = port;
+	struct cxl_dport *dport;
+
+	if (!is_cxl_endpoint(port))
+		return -EINVAL;
+
+	dport = iter->parent_dport;
+	while (iter && !is_cxl_root(to_cxl_port(iter->dev.parent))) {
+		iter = to_cxl_port(iter->dev.parent);
+		dport = iter->parent_dport;
+	}
+
+	coord[ACCESS_COORDINATE_LOCAL] =
+		dport->hb_coord[ACCESS_COORDINATE_LOCAL];
+	coord[ACCESS_COORDINATE_CPU] =
+		dport->hb_coord[ACCESS_COORDINATE_CPU];
 
-		if (c2->read_bandwidth)
-			c1->read_bandwidth = min(c1->read_bandwidth,
-						 c2->read_bandwidth);
-		c1->read_latency += c2->read_latency;
+	return 0;
 }
 
 /**
@@ -2143,7 +2161,7 @@ int cxl_endpoint_get_perf_coordinates(struct cxl_port *port,
 	 * nothing to gather.
 	 */
 	while (iter && !is_cxl_root(to_cxl_port(iter->dev.parent))) {
-		combine_coordinates(&c, &dport->sw_coord);
+		cxl_coordinates_combine(&c, &c, &dport->sw_coord);
 		c.write_latency += dport->link_latency;
 		c.read_latency += dport->link_latency;
 
@@ -2151,9 +2169,6 @@ int cxl_endpoint_get_perf_coordinates(struct cxl_port *port,
 		dport = iter->parent_dport;
 	}
 
-	/* Augment with the generic port (host bridge) perf data */
-	combine_coordinates(&c, &dport->hb_coord);
-
 	/* Get the calculated PCI paths bandwidth */
 	pdev = to_pci_dev(port->uport_dev->parent);
 	bw = pcie_bandwidth_available(pdev, NULL, NULL, NULL);
diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index 4c7fd2d5cccb..5c186e0a39b9 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -4,6 +4,7 @@
 #include <linux/genalloc.h>
 #include <linux/device.h>
 #include <linux/module.h>
+#include <linux/memory.h>
 #include <linux/slab.h>
 #include <linux/uuid.h>
 #include <linux/sort.h>
@@ -30,6 +31,108 @@
 
 static struct cxl_region *to_cxl_region(struct device *dev);
 
+#define __ACCESS_ATTR_RO(_level, _name) {				\
+	.attr	= { .name = __stringify(_name), .mode = 0444 },		\
+	.show	= _name##_access##_level##_show,			\
+}
+
+#define ACCESS_DEVICE_ATTR_RO(level, name)	\
+	struct device_attribute dev_attr_access##level##_##name = __ACCESS_ATTR_RO(level, name)
+
+#define ACCESS_ATTR_RO(level, attrib)					      \
+static ssize_t attrib##_access##level##_show(struct device *dev,	      \
+					  struct device_attribute *attr,      \
+					  char *buf)			      \
+{									      \
+	struct cxl_region *cxlr = to_cxl_region(dev);			      \
+									      \
+	if (cxlr->coord[level].attrib == 0)				      \
+		return -ENOENT;						      \
+									      \
+	return sysfs_emit(buf, "%u\n", cxlr->coord[level].attrib);	      \
+}									      \
+static ACCESS_DEVICE_ATTR_RO(level, attrib)
+
+ACCESS_ATTR_RO(0, read_bandwidth);
+ACCESS_ATTR_RO(0, read_latency);
+ACCESS_ATTR_RO(0, write_bandwidth);
+ACCESS_ATTR_RO(0, write_latency);
+
+#define ACCESS_ATTR_DECLARE(level, attrib)	\
+	(&dev_attr_access##level##_##attrib.attr)
+
+static struct attribute *access0_coordinate_attrs[] = {
+	ACCESS_ATTR_DECLARE(0, read_bandwidth),
+	ACCESS_ATTR_DECLARE(0, write_bandwidth),
+	ACCESS_ATTR_DECLARE(0, read_latency),
+	ACCESS_ATTR_DECLARE(0, write_latency),
+	NULL
+};
+
+ACCESS_ATTR_RO(1, read_bandwidth);
+ACCESS_ATTR_RO(1, read_latency);
+ACCESS_ATTR_RO(1, write_bandwidth);
+ACCESS_ATTR_RO(1, write_latency);
+
+static struct attribute *access1_coordinate_attrs[] = {
+	ACCESS_ATTR_DECLARE(1, read_bandwidth),
+	ACCESS_ATTR_DECLARE(1, write_bandwidth),
+	ACCESS_ATTR_DECLARE(1, read_latency),
+	ACCESS_ATTR_DECLARE(1, write_latency),
+	NULL
+};
+
+#define ACCESS_VISIBLE(level)						\
+static umode_t cxl_region_access##level##_coordinate_visible(		\
+		struct kobject *kobj, struct attribute *a, int n)	\
+{									\
+	struct device *dev = kobj_to_dev(kobj);				\
+	struct cxl_region *cxlr = to_cxl_region(dev);			\
+									\
+	if (a == &dev_attr_access##level##_read_latency.attr &&		\
+	    cxlr->coord[level].read_latency == 0)			\
+		return 0;						\
+									\
+	if (a == &dev_attr_access##level##_write_latency.attr &&	\
+	    cxlr->coord[level].write_latency == 0)			\
+		return 0;						\
+									\
+	if (a == &dev_attr_access##level##_read_bandwidth.attr &&	\
+	    cxlr->coord[level].read_bandwidth == 0)			\
+		return 0;						\
+									\
+	if (a == &dev_attr_access##level##_write_bandwidth.attr &&	\
+	    cxlr->coord[level].write_bandwidth == 0)			\
+		return 0;						\
+									\
+	return a->mode;							\
+}
+
+ACCESS_VISIBLE(0);
+ACCESS_VISIBLE(1);
+
+static const struct attribute_group cxl_region_access0_coordinate_group = {
+	.name = "access0",
+	.attrs = access0_coordinate_attrs,
+	.is_visible = cxl_region_access0_coordinate_visible,
+};
+
+static const struct attribute_group *get_cxl_region_access0_group(void)
+{
+	return &cxl_region_access0_coordinate_group;
+}
+
+static const struct attribute_group cxl_region_access1_coordinate_group = {
+	.name = "access1",
+	.attrs = access1_coordinate_attrs,
+	.is_visible = cxl_region_access1_coordinate_visible,
+};
+
+static const struct attribute_group *get_cxl_region_access1_group(void)
+{
+	return &cxl_region_access1_coordinate_group;
+}
+
 static ssize_t uuid_show(struct device *dev, struct device_attribute *attr,
 			 char *buf)
 {
@@ -1752,6 +1855,8 @@ static int cxl_region_attach(struct cxl_region *cxlr,
 		return -EINVAL;
 	}
 
+	cxl_region_perf_data_calculate(cxlr, cxled);
+
 	if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags)) {
 		int i;
 
@@ -2067,6 +2172,8 @@ static const struct attribute_group *region_groups[] = {
 	&cxl_base_attribute_group,
 	&cxl_region_group,
 	&cxl_region_target_group,
+	&cxl_region_access0_coordinate_group,
+	&cxl_region_access1_coordinate_group,
 	NULL,
 };
 
@@ -2120,6 +2227,7 @@ static void unregister_region(void *_cxlr)
 	struct cxl_region_params *p = &cxlr->params;
 	int i;
 
+	unregister_memory_notifier(&cxlr->memory_notifier);
 	device_del(&cxlr->dev);
 
 	/*
@@ -2164,6 +2272,63 @@ static struct cxl_region *cxl_region_alloc(struct cxl_root_decoder *cxlrd, int i
 	return cxlr;
 }
 
+static bool cxl_region_update_coordinates(struct cxl_region *cxlr, int nid)
+{
+	int cset = 0;
+	int rc;
+
+	for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) {
+		if (cxlr->coord[i].read_bandwidth) {
+			rc = 0;
+			if (cxl_need_node_perf_attrs_update(nid))
+				node_set_perf_attrs(nid, &cxlr->coord[i], i);
+			else
+				rc = cxl_update_hmat_access_coordinates(nid, cxlr, i);
+
+			if (rc == 0)
+				cset++;
+		}
+	}
+
+	if (!cset)
+		return false;
+
+	rc = sysfs_update_group(&cxlr->dev.kobj, get_cxl_region_access0_group());
+	if (rc)
+		dev_dbg(&cxlr->dev, "Failed to update access0 group\n");
+
+	rc = sysfs_update_group(&cxlr->dev.kobj, get_cxl_region_access1_group());
+	if (rc)
+		dev_dbg(&cxlr->dev, "Failed to update access1 group\n");
+
+	return true;
+}
+
+static int cxl_region_perf_attrs_callback(struct notifier_block *nb,
+					  unsigned long action, void *arg)
+{
+	struct cxl_region *cxlr = container_of(nb, struct cxl_region,
+					       memory_notifier);
+	struct cxl_region_params *p = &cxlr->params;
+	struct cxl_endpoint_decoder *cxled = p->targets[0];
+	struct cxl_decoder *cxld = &cxled->cxld;
+	struct memory_notify *mnb = arg;
+	int nid = mnb->status_change_nid;
+	int region_nid;
+
+	if (nid == NUMA_NO_NODE || action != MEM_ONLINE)
+		return NOTIFY_DONE;
+
+	region_nid = phys_to_target_node(cxld->hpa_range.start);
+	if (nid != region_nid)
+		return NOTIFY_DONE;
+
+	if (!cxl_region_update_coordinates(cxlr, nid))
+		return NOTIFY_DONE;
+
+	return NOTIFY_OK;
+}
+
 /**
  * devm_cxl_add_region - Adds a region to a decoder
  * @cxlrd: root decoder
@@ -2211,6 +2376,10 @@ static struct cxl_region *devm_cxl_add_region(struct cxl_root_decoder *cxlrd,
 	if (rc)
 		goto err;
 
+	cxlr->memory_notifier.notifier_call = cxl_region_perf_attrs_callback;
+	cxlr->memory_notifier.priority = CXL_CALLBACK_PRI;
+	register_memory_notifier(&cxlr->memory_notifier);
+
 	rc = devm_add_action_or_reset(port->uport_dev, unregister_region, cxlr);
 	if (rc)
 		return ERR_PTR(rc);
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index 003feebab79b..534e25e2f0a4 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -6,6 +6,7 @@
 
 #include <linux/libnvdimm.h>
 #include <linux/bitfield.h>
+#include <linux/notifier.h>
 #include <linux/bitops.h>
 #include <linux/log2.h>
 #include <linux/node.h>
@@ -517,6 +518,8 @@ struct cxl_region_params {
  * @cxlr_pmem: (for pmem regions) cached copy of the nvdimm bridge
  * @flags: Region state flags
  * @params: active + config params for the region
+ * @coord: QoS access coordinates for the region
+ * @memory_notifier: notifier for setting the access coordinates to node
  */
 struct cxl_region {
 	struct device dev;
@@ -527,6 +530,8 @@ struct cxl_region {
 	struct cxl_pmem_region *cxlr_pmem;
 	unsigned long flags;
 	struct cxl_region_params params;
+	struct access_coordinate coord[ACCESS_COORDINATE_MAX];
+	struct notifier_block memory_notifier;
 };
 
 struct cxl_nvdimm_bridge {
@@ -671,7 +676,7 @@ struct cxl_dport {
 	struct cxl_port *port;
 	struct cxl_regs regs;
 	struct access_coordinate sw_coord;
-	struct access_coordinate hb_coord;
+	struct access_coordinate hb_coord[ACCESS_COORDINATE_MAX];
 	long link_latency;
 };
 
@@ -879,9 +884,17 @@ void cxl_switch_parse_cdat(struct cxl_port *port);
 
 int cxl_endpoint_get_perf_coordinates(struct cxl_port *port,
 				      struct access_coordinate *coord);
+int cxl_hb_get_perf_coordinates(struct cxl_port *port,
+				struct access_coordinate *coord);
+void cxl_region_perf_data_calculate(struct cxl_region *cxlr,
+				    struct cxl_endpoint_decoder *cxled);
 
 void cxl_memdev_update_perf(struct cxl_memdev *cxlmd);
 
+void cxl_coordinates_combine(struct access_coordinate *out,
+			     struct access_coordinate *c1,
+			     struct access_coordinate *c2);
+
 /*
  * Unit test builds overrides this to __weak, find the 'strong' version
  * of these symbols in tools/testing/cxl/.