Merge branch 'for-6.8/cxl-cdat' into for-6.8/cxl

Pick up the CDAT parsing and QOS class infrastructure for v6.8.

10 files changed, 714 insertions, 30 deletions

diff --git a/drivers/cxl/core/Makefile b/drivers/cxl/core/Makefile
index 1f66b5d4d935..9259bcc6773c 100644
--- a/drivers/cxl/core/Makefile
+++ b/drivers/cxl/core/Makefile
@@ -13,5 +13,6 @@ cxl_core-y += mbox.o
 cxl_core-y += pci.o
 cxl_core-y += hdm.o
 cxl_core-y += pmu.o
+cxl_core-y += cdat.o
 cxl_core-$(CONFIG_TRACING) += trace.o
 cxl_core-$(CONFIG_CXL_REGION) += region.o
diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c
new file mode 100644
index 000000000000..cd84d87f597a
--- /dev/null
+++ b/drivers/cxl/core/cdat.c
@@ -0,0 +1,517 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2023 Intel Corporation. All rights reserved. */
+#include <linux/acpi.h>
+#include <linux/xarray.h>
+#include <linux/fw_table.h>
+#include <linux/node.h>
+#include <linux/overflow.h>
+#include "cxlpci.h"
+#include "cxlmem.h"
+#include "cxl.h"
+
+struct dsmas_entry {
+	struct range dpa_range;
+	u8 handle;
+	struct access_coordinate coord;
+
+	int entries;
+	int qos_class;
+};
+
+static int cdat_dsmas_handler(union acpi_subtable_headers *header, void *arg,
+			      const unsigned long end)
+{
+	struct acpi_cdat_header *hdr = &header->cdat;
+	struct acpi_cdat_dsmas *dsmas;
+	int size = sizeof(*hdr) + sizeof(*dsmas);
+	struct xarray *dsmas_xa = arg;
+	struct dsmas_entry *dent;
+	u16 len;
+	int rc;
+
+	len = le16_to_cpu((__force __le16)hdr->length);
+	if (len != size || (unsigned long)hdr + len > end) {
+		pr_warn("Malformed DSMAS table length: (%u:%u)\n", size, len);
+		return -EINVAL;
+	}
+
+	/* Skip common header */
+	dsmas = (struct acpi_cdat_dsmas *)(hdr + 1);
+
+	dent = kzalloc(sizeof(*dent), GFP_KERNEL);
+	if (!dent)
+		return -ENOMEM;
+
+	dent->handle = dsmas->dsmad_handle;
+	dent->dpa_range.start = le64_to_cpu((__force __le64)dsmas->dpa_base_address);
+	dent->dpa_range.end = le64_to_cpu((__force __le64)dsmas->dpa_base_address) +
+			      le64_to_cpu((__force __le64)dsmas->dpa_length) - 1;
+
+	rc = xa_insert(dsmas_xa, dent->handle, dent, GFP_KERNEL);
+	if (rc) {
+		kfree(dent);
+		return rc;
+	}
+
+	return 0;
+}
+
+static void cxl_access_coordinate_set(struct access_coordinate *coord,
+				      int access, unsigned int val)
+{
+	switch (access) {
+	case ACPI_HMAT_ACCESS_LATENCY:
+		coord->read_latency = val;
+		coord->write_latency = val;
+		break;
+	case ACPI_HMAT_READ_LATENCY:
+		coord->read_latency = val;
+		break;
+	case ACPI_HMAT_WRITE_LATENCY:
+		coord->write_latency = val;
+		break;
+	case ACPI_HMAT_ACCESS_BANDWIDTH:
+		coord->read_bandwidth = val;
+		coord->write_bandwidth = val;
+		break;
+	case ACPI_HMAT_READ_BANDWIDTH:
+		coord->read_bandwidth = val;
+		break;
+	case ACPI_HMAT_WRITE_BANDWIDTH:
+		coord->write_bandwidth = val;
+		break;
+	}
+}
+
+static int cdat_dslbis_handler(union acpi_subtable_headers *header, void *arg,
+			       const unsigned long end)
+{
+	struct acpi_cdat_header *hdr = &header->cdat;
+	struct acpi_cdat_dslbis *dslbis;
+	int size = sizeof(*hdr) + sizeof(*dslbis);
+	struct xarray *dsmas_xa = arg;
+	struct dsmas_entry *dent;
+	__le64 le_base;
+	__le16 le_val;
+	u64 val;
+	u16 len;
+	int rc;
+
+	len = le16_to_cpu((__force __le16)hdr->length);
+	if (len != size || (unsigned long)hdr + len > end) {
+		pr_warn("Malformed DSLBIS table length: (%u:%u)\n", size, len);
+		return -EINVAL;
+	}
+
+	/* Skip common header */
+	dslbis = (struct acpi_cdat_dslbis *)(hdr + 1);
+
+	/* Skip unrecognized data type */
+	if (dslbis->data_type > ACPI_HMAT_WRITE_BANDWIDTH)
+		return 0;
+
+	/* Not a memory type, skip */
+	if ((dslbis->flags & ACPI_HMAT_MEMORY_HIERARCHY) != ACPI_HMAT_MEMORY)
+		return 0;
+
+	dent = xa_load(dsmas_xa, dslbis->handle);
+	if (!dent) {
+		pr_warn("No matching DSMAS entry for DSLBIS entry.\n");
+		return 0;
+	}
+
+	le_base = (__force __le64)dslbis->entry_base_unit;
+	le_val = (__force __le16)dslbis->entry[0];
+	rc = check_mul_overflow(le64_to_cpu(le_base),
+				le16_to_cpu(le_val), &val);
+	if (rc)
+		pr_warn("DSLBIS value overflowed.\n");
+
+	cxl_access_coordinate_set(&dent->coord, dslbis->data_type, val);
+
+	return 0;
+}
+
+static int cdat_table_parse_output(int rc)
+{
+	if (rc < 0)
+		return rc;
+	if (rc == 0)
+		return -ENOENT;
+
+	return 0;
+}
+
+static int cxl_cdat_endpoint_process(struct cxl_port *port,
+				     struct xarray *dsmas_xa)
+{
+	int rc;
+
+	rc = cdat_table_parse(ACPI_CDAT_TYPE_DSMAS, cdat_dsmas_handler,
+			      dsmas_xa, port->cdat.table);
+	rc = cdat_table_parse_output(rc);
+	if (rc)
+		return rc;
+
+	rc = cdat_table_parse(ACPI_CDAT_TYPE_DSLBIS, cdat_dslbis_handler,
+			      dsmas_xa, port->cdat.table);
+	return cdat_table_parse_output(rc);
+}
+
+static int cxl_port_perf_data_calculate(struct cxl_port *port,
+					struct xarray *dsmas_xa)
+{
+	struct access_coordinate c;
+	struct cxl_port *root_port;
+	struct cxl_root *cxl_root;
+	struct dsmas_entry *dent;
+	int valid_entries = 0;
+	unsigned long index;
+	int rc;
+
+	rc = cxl_endpoint_get_perf_coordinates(port, &c);
+	if (rc) {
+		dev_dbg(&port->dev, "Failed to retrieve perf coordinates.\n");
+		return rc;
+	}
+
+	root_port = find_cxl_root(port);
+	cxl_root = to_cxl_root(root_port);
+	if (!cxl_root->ops || !cxl_root->ops->qos_class)
+		return -EOPNOTSUPP;
+
+	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);
+
+		dent->entries = 1;
+		rc = cxl_root->ops->qos_class(root_port, &dent->coord, 1, &qos_class);
+		if (rc != 1)
+			continue;
+
+		valid_entries++;
+		dent->qos_class = qos_class;
+	}
+
+	if (!valid_entries)
+		return -ENOENT;
+
+	return 0;
+}
+
+static void add_perf_entry(struct device *dev, struct dsmas_entry *dent,
+			   struct list_head *list)
+{
+	struct cxl_dpa_perf *dpa_perf;
+
+	dpa_perf = kzalloc(sizeof(*dpa_perf), GFP_KERNEL);
+	if (!dpa_perf)
+		return;
+
+	dpa_perf->dpa_range = dent->dpa_range;
+	dpa_perf->coord = dent->coord;
+	dpa_perf->qos_class = dent->qos_class;
+	list_add_tail(&dpa_perf->list, list);
+	dev_dbg(dev,
+		"DSMAS: dpa: %#llx qos: %d read_bw: %d write_bw %d read_lat: %d write_lat: %d\n",
+		dent->dpa_range.start, dpa_perf->qos_class,
+		dent->coord.read_bandwidth, dent->coord.write_bandwidth,
+		dent->coord.read_latency, dent->coord.write_latency);
+}
+
+static void free_perf_ents(void *data)
+{
+	struct cxl_memdev_state *mds = data;
+	struct cxl_dpa_perf *dpa_perf, *n;
+	LIST_HEAD(discard);
+
+	list_splice_tail_init(&mds->ram_perf_list, &discard);
+	list_splice_tail_init(&mds->pmem_perf_list, &discard);
+	list_for_each_entry_safe(dpa_perf, n, &discard, list) {
+		list_del(&dpa_perf->list);
+		kfree(dpa_perf);
+	}
+}
+
+static void cxl_memdev_set_qos_class(struct cxl_dev_state *cxlds,
+				     struct xarray *dsmas_xa)
+{
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
+	struct device *dev = cxlds->dev;
+	struct range pmem_range = {
+		.start = cxlds->pmem_res.start,
+		.end = cxlds->pmem_res.end,
+	};
+	struct range ram_range = {
+		.start = cxlds->ram_res.start,
+		.end = cxlds->ram_res.end,
+	};
+	struct dsmas_entry *dent;
+	unsigned long index;
+
+	xa_for_each(dsmas_xa, index, dent) {
+		if (resource_size(&cxlds->ram_res) &&
+		    range_contains(&ram_range, &dent->dpa_range))
+			add_perf_entry(dev, dent, &mds->ram_perf_list);
+		else if (resource_size(&cxlds->pmem_res) &&
+			 range_contains(&pmem_range, &dent->dpa_range))
+			add_perf_entry(dev, dent, &mds->pmem_perf_list);
+		else
+			dev_dbg(dev, "no partition for dsmas dpa: %#llx\n",
+				dent->dpa_range.start);
+	}
+
+	devm_add_action_or_reset(&cxlds->cxlmd->dev, free_perf_ents, mds);
+}
+
+static int match_cxlrd_qos_class(struct device *dev, void *data)
+{
+	int dev_qos_class = *(int *)data;
+	struct cxl_root_decoder *cxlrd;
+
+	if (!is_root_decoder(dev))
+		return 0;
+
+	cxlrd = to_cxl_root_decoder(dev);
+	if (cxlrd->qos_class == CXL_QOS_CLASS_INVALID)
+		return 0;
+
+	if (cxlrd->qos_class == dev_qos_class)
+		return 1;
+
+	return 0;
+}
+
+static void cxl_qos_match(struct cxl_port *root_port,
+			  struct list_head *work_list,
+			  struct list_head *discard_list)
+{
+	struct cxl_dpa_perf *dpa_perf, *n;
+
+	list_for_each_entry_safe(dpa_perf, n, work_list, list) {
+		int rc;
+
+		if (dpa_perf->qos_class == CXL_QOS_CLASS_INVALID)
+			return;
+
+		rc = device_for_each_child(&root_port->dev,
+					   (void *)&dpa_perf->qos_class,
+					   match_cxlrd_qos_class);
+		if (!rc)
+			list_move_tail(&dpa_perf->list, discard_list);
+	}
+}
+
+static int match_cxlrd_hb(struct device *dev, void *data)
+{
+	struct device *host_bridge = data;
+	struct cxl_switch_decoder *cxlsd;
+	struct cxl_root_decoder *cxlrd;
+	unsigned int seq;
+
+	if (!is_root_decoder(dev))
+		return 0;
+
+	cxlrd = to_cxl_root_decoder(dev);
+	cxlsd = &cxlrd->cxlsd;
+
+	do {
+		seq = read_seqbegin(&cxlsd->target_lock);
+		for (int i = 0; i < cxlsd->nr_targets; i++) {
+			if (host_bridge == cxlsd->target[i]->dport_dev)
+				return 1;
+		}
+	} while (read_seqretry(&cxlsd->target_lock, seq));
+
+	return 0;
+}
+
+static void discard_dpa_perf(struct list_head *list)
+{
+	struct cxl_dpa_perf *dpa_perf, *n;
+
+	list_for_each_entry_safe(dpa_perf, n, list, list) {
+		list_del(&dpa_perf->list);
+		kfree(dpa_perf);
+	}
+}
+DEFINE_FREE(dpa_perf, struct list_head *, if (!list_empty(_T)) discard_dpa_perf(_T))
+
+static int cxl_qos_class_verify(struct cxl_memdev *cxlmd)
+{
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
+	struct cxl_port *root_port __free(put_device) = NULL;
+	LIST_HEAD(__discard);
+	struct list_head *discard __free(dpa_perf) = &__discard;
+	int rc;
+
+	root_port = find_cxl_root(cxlmd->endpoint);
+	if (!root_port)
+		return -ENODEV;
+
+	/* Check that the QTG IDs are all sane between end device and root decoders */
+	cxl_qos_match(root_port, &mds->ram_perf_list, discard);
+	cxl_qos_match(root_port, &mds->pmem_perf_list, discard);
+
+	/* Check to make sure that the device's host bridge is under a root decoder */
+	rc = device_for_each_child(&root_port->dev,
+				   (void *)cxlmd->endpoint->host_bridge,
+				   match_cxlrd_hb);
+	if (!rc) {
+		list_splice_tail_init(&mds->ram_perf_list, discard);
+		list_splice_tail_init(&mds->pmem_perf_list, discard);
+	}
+
+	return rc;
+}
+
+static void discard_dsmas(struct xarray *xa)
+{
+	unsigned long index;
+	void *ent;
+
+	xa_for_each(xa, index, ent) {
+		xa_erase(xa, index);
+		kfree(ent);
+	}
+	xa_destroy(xa);
+}
+DEFINE_FREE(dsmas, struct xarray *, if (_T) discard_dsmas(_T))
+
+void cxl_endpoint_parse_cdat(struct cxl_port *port)
+{
+	struct cxl_memdev *cxlmd = to_cxl_memdev(port->uport_dev);
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	struct xarray __dsmas_xa;
+	struct xarray *dsmas_xa __free(dsmas) = &__dsmas_xa;
+	int rc;
+
+	xa_init(&__dsmas_xa);
+	if (!port->cdat.table)
+		return;
+
+	rc = cxl_cdat_endpoint_process(port, dsmas_xa);
+	if (rc < 0) {
+		dev_dbg(&port->dev, "Failed to parse CDAT: %d\n", rc);
+		return;
+	}
+
+	rc = cxl_port_perf_data_calculate(port, dsmas_xa);
+	if (rc) {
+		dev_dbg(&port->dev, "Failed to do perf coord calculations.\n");
+		return;
+	}
+
+	cxl_memdev_set_qos_class(cxlds, dsmas_xa);
+	cxl_qos_class_verify(cxlmd);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_endpoint_parse_cdat, CXL);
+
+static int cdat_sslbis_handler(union acpi_subtable_headers *header, void *arg,
+			       const unsigned long end)
+{
+	struct acpi_cdat_sslbis *sslbis;
+	int size = sizeof(header->cdat) + sizeof(*sslbis);
+	struct cxl_port *port = arg;
+	struct device *dev = &port->dev;
+	struct acpi_cdat_sslbe *entry;
+	int remain, entries, i;
+	u16 len;
+
+	len = le16_to_cpu((__force __le16)header->cdat.length);
+	remain = len - size;
+	if (!remain || remain % sizeof(*entry) ||
+	    (unsigned long)header + len > end) {
+		dev_warn(dev, "Malformed SSLBIS table length: (%u)\n", len);
+		return -EINVAL;
+	}
+
+	/* Skip common header */
+	sslbis = (struct acpi_cdat_sslbis *)((unsigned long)header +
+					     sizeof(header->cdat));
+
+	/* Unrecognized data type, we can skip */
+	if (sslbis->data_type > ACPI_HMAT_WRITE_BANDWIDTH)
+		return 0;
+
+	entries = remain / sizeof(*entry);
+	entry = (struct acpi_cdat_sslbe *)((unsigned long)header + sizeof(*sslbis));
+
+	for (i = 0; i < entries; i++) {
+		u16 x = le16_to_cpu((__force __le16)entry->portx_id);
+		u16 y = le16_to_cpu((__force __le16)entry->porty_id);
+		__le64 le_base;
+		__le16 le_val;
+		struct cxl_dport *dport;
+		unsigned long index;
+		u16 dsp_id;
+		u64 val;
+
+		switch (x) {
+		case ACPI_CDAT_SSLBIS_US_PORT:
+			dsp_id = y;
+			break;
+		case ACPI_CDAT_SSLBIS_ANY_PORT:
+			switch (y) {
+			case ACPI_CDAT_SSLBIS_US_PORT:
+				dsp_id = x;
+				break;
+			case ACPI_CDAT_SSLBIS_ANY_PORT:
+				dsp_id = ACPI_CDAT_SSLBIS_ANY_PORT;
+				break;
+			default:
+				dsp_id = y;
+				break;
+			}
+			break;
+		default:
+			dsp_id = x;
+			break;
+		}
+
+		le_base = (__force __le64)sslbis->entry_base_unit;
+		le_val = (__force __le16)entry->latency_or_bandwidth;
+
+		if (check_mul_overflow(le64_to_cpu(le_base),
+				       le16_to_cpu(le_val), &val))
+			dev_warn(dev, "SSLBIS value overflowed!\n");
+
+		xa_for_each(&port->dports, index, dport) {
+			if (dsp_id == ACPI_CDAT_SSLBIS_ANY_PORT ||
+			    dsp_id == dport->port_id)
+				cxl_access_coordinate_set(&dport->sw_coord,
+							  sslbis->data_type,
+							  val);
+		}
+
+		entry++;
+	}
+
+	return 0;
+}
+
+void cxl_switch_parse_cdat(struct cxl_port *port)
+{
+	int rc;
+
+	if (!port->cdat.table)
+		return;
+
+	rc = cdat_table_parse(ACPI_CDAT_TYPE_SSLBIS, cdat_sslbis_handler,
+			      port, port->cdat.table);
+	rc = cdat_table_parse_output(rc);
+	if (rc)
+		dev_dbg(&port->dev, "Failed to parse SSLBIS: %d\n", rc);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_switch_parse_cdat, CXL);
+
+MODULE_IMPORT_NS(CXL);
diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h
index 86d7ba23235e..3b64fb1b9ed0 100644
--- a/drivers/cxl/core/core.h
+++ b/drivers/cxl/core/core.h
@@ -88,4 +88,6 @@ enum cxl_poison_trace_type {
 	CXL_POISON_TRACE_CLEAR,
 };
 
+long cxl_pci_get_latency(struct pci_dev *pdev);
+
 #endif /* __CXL_CORE_H__ */
diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c
index 1cc9be85ba4c..7d97790b893d 100644
--- a/drivers/cxl/core/hdm.c
+++ b/drivers/cxl/core/hdm.c
@@ -363,10 +363,9 @@ resource_size_t cxl_dpa_resource_start(struct cxl_endpoint_decoder *cxled)
 {
 	resource_size_t base = -1;
 
-	down_read(&cxl_dpa_rwsem);
+	lockdep_assert_held(&cxl_dpa_rwsem);
 	if (cxled->dpa_res)
 		base = cxled->dpa_res->start;
-	up_read(&cxl_dpa_rwsem);
 
 	return base;
 }
@@ -839,6 +838,8 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld,
 			cxld->target_type = CXL_DECODER_HOSTONLYMEM;
 		else
 			cxld->target_type = CXL_DECODER_DEVMEM;
+
+		guard(rwsem_write)(&cxl_region_rwsem);
 		if (cxld->id != cxl_num_decoders_committed(port)) {
 			dev_warn(&port->dev,
 				 "decoder%d.%d: Committed out of order\n",
diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index b86dbd25740c..d51a1f250c8c 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -1405,6 +1405,8 @@ struct cxl_memdev_state *cxl_memdev_state_create(struct device *dev)
 	mds->cxlds.reg_map.host = dev;
 	mds->cxlds.reg_map.resource = CXL_RESOURCE_NONE;
 	mds->cxlds.type = CXL_DEVTYPE_CLASSMEM;
+	INIT_LIST_HEAD(&mds->ram_perf_list);
+	INIT_LIST_HEAD(&mds->pmem_perf_list);
 
 	return mds;
 }
diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c
index fc5c2b414793..2f43d368ba07 100644
--- a/drivers/cxl/core/memdev.c
+++ b/drivers/cxl/core/memdev.c
@@ -227,10 +227,16 @@ int cxl_trigger_poison_list(struct cxl_memdev *cxlmd)
 	if (!port || !is_cxl_endpoint(port))
 		return -EINVAL;
 
-	rc = down_read_interruptible(&cxl_dpa_rwsem);
+	rc = down_read_interruptible(&cxl_region_rwsem);
 	if (rc)
 		return rc;
 
+	rc = down_read_interruptible(&cxl_dpa_rwsem);
+	if (rc) {
+		up_read(&cxl_region_rwsem);
+		return rc;
+	}
+
 	if (cxl_num_decoders_committed(port) == 0) {
 		/* No regions mapped to this memdev */
 		rc = cxl_get_poison_by_memdev(cxlmd);
@@ -239,6 +245,7 @@ int cxl_trigger_poison_list(struct cxl_memdev *cxlmd)
 		rc =  cxl_get_poison_by_endpoint(port);
 	}
 	up_read(&cxl_dpa_rwsem);
+	up_read(&cxl_region_rwsem);
 
 	return rc;
 }
@@ -324,10 +331,16 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa)
 	if (!IS_ENABLED(CONFIG_DEBUG_FS))
 		return 0;
 
-	rc = down_read_interruptible(&cxl_dpa_rwsem);
+	rc = down_read_interruptible(&cxl_region_rwsem);
 	if (rc)
 		return rc;
 
+	rc = down_read_interruptible(&cxl_dpa_rwsem);
+	if (rc) {
+		up_read(&cxl_region_rwsem);
+		return rc;
+	}
+
 	rc = cxl_validate_poison_dpa(cxlmd, dpa);
 	if (rc)
 		goto out;
@@ -355,6 +368,7 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa)
 	trace_cxl_poison(cxlmd, cxlr, &record, 0, 0, CXL_POISON_TRACE_INJECT);
 out:
 	up_read(&cxl_dpa_rwsem);
+	up_read(&cxl_region_rwsem);
 
 	return rc;
 }
@@ -372,10 +386,16 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa)
 	if (!IS_ENABLED(CONFIG_DEBUG_FS))
 		return 0;
 
-	rc = down_read_interruptible(&cxl_dpa_rwsem);
+	rc = down_read_interruptible(&cxl_region_rwsem);
 	if (rc)
 		return rc;
 
+	rc = down_read_interruptible(&cxl_dpa_rwsem);
+	if (rc) {
+		up_read(&cxl_region_rwsem);
+		return rc;
+	}
+
 	rc = cxl_validate_poison_dpa(cxlmd, dpa);
 	if (rc)
 		goto out;
@@ -412,6 +432,7 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa)
 	trace_cxl_poison(cxlmd, cxlr, &record, 0, 0, CXL_POISON_TRACE_CLEAR);
 out:
 	up_read(&cxl_dpa_rwsem);
+	up_read(&cxl_region_rwsem);
 
 	return rc;
 }
diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
index eff20e83d0a6..6c9c8d92f8f7 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /* Copyright(c) 2021 Intel Corporation. All rights reserved. */
+#include <linux/units.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/device.h>
 #include <linux/delay.h>
@@ -620,7 +621,7 @@ void read_cdat_data(struct cxl_port *port)
 	struct pci_dev *pdev = NULL;
 	struct cxl_memdev *cxlmd;
 	size_t cdat_length;
-	void *cdat_table;
+	void *cdat_table, *cdat_buf;
 	int rc;
 
 	if (is_cxl_memdev(uport)) {
@@ -651,16 +652,15 @@ void read_cdat_data(struct cxl_port *port)
 		return;
 	}
 
-	cdat_table = devm_kzalloc(dev, cdat_length + sizeof(__le32),
-				  GFP_KERNEL);
-	if (!cdat_table)
+	cdat_buf = devm_kzalloc(dev, cdat_length + sizeof(__le32), GFP_KERNEL);
+	if (!cdat_buf)
 		return;
 
-	rc = cxl_cdat_read_table(dev, cdat_doe, cdat_table, &cdat_length);
+	rc = cxl_cdat_read_table(dev, cdat_doe, cdat_buf, &cdat_length);
 	if (rc)
 		goto err;
 
-	cdat_table = cdat_table + sizeof(__le32);
+	cdat_table = cdat_buf + sizeof(__le32);
 	if (cdat_checksum(cdat_table, cdat_length))
 		goto err;
 
@@ -670,7 +670,7 @@ void read_cdat_data(struct cxl_port *port)
 
 err:
 	/* Don't leave table data allocated on error */
-	devm_kfree(dev, cdat_table);
+	devm_kfree(dev, cdat_buf);
 	dev_err(dev, "Failed to read/validate CDAT.\n");
 }
 EXPORT_SYMBOL_NS_GPL(read_cdat_data, CXL);
@@ -980,3 +980,38 @@ pci_ers_result_t cxl_error_detected(struct pci_dev *pdev,
 	return PCI_ERS_RESULT_NEED_RESET;
 }
 EXPORT_SYMBOL_NS_GPL(cxl_error_detected, CXL);
+
+static int cxl_flit_size(struct pci_dev *pdev)
+{
+	if (cxl_pci_flit_256(pdev))
+		return 256;
+
+	return 68;
+}
+
+/**
+ * cxl_pci_get_latency - calculate the link latency for the PCIe link
+ * @pdev: PCI device
+ *
+ * return: calculated latency or 0 for no latency
+ *
+ * CXL Memory Device SW Guide v1.0 2.11.4 Link latency calculation
+ * Link latency = LinkPropagationLatency + FlitLatency + RetimerLatency
+ * LinkProgationLatency is negligible, so 0 will be used
+ * RetimerLatency is assumed to be negligible and 0 will be used
+ * FlitLatency = FlitSize / LinkBandwidth
+ * FlitSize is defined by spec. CXL rev3.0 4.2.1.
+ * 68B flit is used up to 32GT/s. >32GT/s, 256B flit size is used.
+ * The FlitLatency is converted to picoseconds.
+ */
+long cxl_pci_get_latency(struct pci_dev *pdev)
+{
+	long bw;
+
+	bw = pcie_link_speed_mbps(pdev);
+	if (bw < 0)
+		return 0;
+	bw /= BITS_PER_BYTE;
+
+	return cxl_flit_size(pdev) * MEGA / bw;
+}
diff --git a/drivers/cxl/core/pmu.c b/drivers/cxl/core/pmu.c
index 7684c843e5a5..5d8e06b0ba6e 100644
--- a/drivers/cxl/core/pmu.c
+++ b/drivers/cxl/core/pmu.c
@@ -23,7 +23,7 @@ const struct device_type cxl_pmu_type = {
 
 static void remove_dev(void *dev)
 {
-	device_del(dev);
+	device_unregister(dev);
 }
 
 int devm_cxl_pmu_add(struct device *parent, struct cxl_pmu_regs *regs,
diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index 38441634e4c6..8c00fd6be730 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -9,6 +9,7 @@
 #include <linux/pci.h>
 #include <linux/slab.h>
 #include <linux/idr.h>
+#include <linux/node.h>
 #include <cxlmem.h>
 #include <cxlpci.h>
 #include <cxl.h>
@@ -226,9 +227,9 @@ static ssize_t dpa_resource_show(struct device *dev, struct device_attribute *at
 			    char *buf)
 {
 	struct cxl_endpoint_decoder *cxled = to_cxl_endpoint_decoder(dev);
-	u64 base = cxl_dpa_resource_start(cxled);
 
-	return sysfs_emit(buf, "%#llx\n", base);
+	guard(rwsem_read)(&cxl_dpa_rwsem);
+	return sysfs_emit(buf, "%#llx\n", (u64)cxl_dpa_resource_start(cxled));
 }
 static DEVICE_ATTR_RO(dpa_resource);
 
@@ -541,7 +542,10 @@ static void cxl_port_release(struct device *dev)
 	xa_destroy(&port->dports);
 	xa_destroy(&port->regions);
 	ida_free(&cxl_port_ida, port->id);
-	kfree(port);
+	if (is_cxl_root(port))
+		kfree(to_cxl_root(port));
+	else
+		kfree(port);
 }
 
 static ssize_t decoders_committed_show(struct device *dev,
@@ -669,17 +673,31 @@ static struct lock_class_key cxl_port_key;
 static struct cxl_port *cxl_port_alloc(struct device *uport_dev,
 				       struct cxl_dport *parent_dport)
 {
-	struct cxl_port *port;
+	struct cxl_root *cxl_root __free(kfree) = NULL;
+	struct cxl_port *port, *_port __free(kfree) = NULL;
 	struct device *dev;
 	int rc;
 
-	port = kzalloc(sizeof(*port), GFP_KERNEL);
-	if (!port)
-		return ERR_PTR(-ENOMEM);
+	/* No parent_dport, root cxl_port */
+	if (!parent_dport) {
+		cxl_root = kzalloc(sizeof(*cxl_root), GFP_KERNEL);
+		if (!cxl_root)
+			return ERR_PTR(-ENOMEM);
+	} else {
+		_port = kzalloc(sizeof(*port), GFP_KERNEL);
+		if (!_port)
+			return ERR_PTR(-ENOMEM);
+	}
 
 	rc = ida_alloc(&cxl_port_ida, GFP_KERNEL);
 	if (rc < 0)
-		goto err;
+		return ERR_PTR(rc);
+
+	if (cxl_root)
+		port = &no_free_ptr(cxl_root)->port;
+	else
+		port = no_free_ptr(_port);
+
 	port->id = rc;
 	port->uport_dev = uport_dev;
 
@@ -731,10 +749,6 @@ static struct cxl_port *cxl_port_alloc(struct device *uport_dev,
 	dev->type = &cxl_port_type;
 
 	return port;
-
-err:
-	kfree(port);
-	return ERR_PTR(rc);
 }
 
 static int cxl_setup_comp_regs(struct device *host, struct cxl_register_map *map,
@@ -841,6 +855,9 @@ static struct cxl_port *__devm_cxl_add_port(struct device *host,
 	if (rc)
 		return ERR_PTR(rc);
 
+	if (parent_dport && dev_is_pci(uport_dev))
+		port->pci_latency = cxl_pci_get_latency(to_pci_dev(uport_dev));
+
 	return port;
 
 err:
@@ -884,6 +901,22 @@ struct cxl_port *devm_cxl_add_port(struct device *host,
 }
 EXPORT_SYMBOL_NS_GPL(devm_cxl_add_port, CXL);
 
+struct cxl_root *devm_cxl_add_root(struct device *host,
+				   const struct cxl_root_ops *ops)
+{
+	struct cxl_root *cxl_root;
+	struct cxl_port *port;
+
+	port = devm_cxl_add_port(host, host, CXL_RESOURCE_NONE, NULL);
+	if (IS_ERR(port))
+		return (struct cxl_root *)port;
+
+	cxl_root = to_cxl_root(port);
+	cxl_root->ops = ops;
+	return cxl_root;
+}
+EXPORT_SYMBOL_NS_GPL(devm_cxl_add_root, CXL);
+
 struct pci_bus *cxl_port_to_pci_bus(struct cxl_port *port)
 {
 	/* There is no pci_bus associated with a CXL platform-root port */
@@ -1108,6 +1141,9 @@ __devm_cxl_add_dport(struct cxl_port *port, struct device *dport_dev,
 	if (rc)
 		return ERR_PTR(rc);
 
+	if (dev_is_pci(dport_dev))
+		dport->link_latency = cxl_pci_get_latency(to_pci_dev(dport_dev));
+
 	return dport;
 }
 
@@ -2059,6 +2095,80 @@ 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)
+{
+		if (c2->write_bandwidth)
+			c1->write_bandwidth = min(c1->write_bandwidth,
+						  c2->write_bandwidth);
+		c1->write_latency += c2->write_latency;
+
+		if (c2->read_bandwidth)
+			c1->read_bandwidth = min(c1->read_bandwidth,
+						 c2->read_bandwidth);
+		c1->read_latency += c2->read_latency;
+}
+
+/**
+ * cxl_endpoint_get_perf_coordinates - Retrieve performance numbers stored in dports
+ *				   of CXL path
+ * @port: endpoint cxl_port
+ * @coord: output performance data
+ *
+ * Return: errno on failure, 0 on success.
+ */
+int cxl_endpoint_get_perf_coordinates(struct cxl_port *port,
+				      struct access_coordinate *coord)
+{
+	struct access_coordinate c = {
+		.read_bandwidth = UINT_MAX,
+		.write_bandwidth = UINT_MAX,
+	};
+	struct cxl_port *iter = port;
+	struct cxl_dport *dport;
+	struct pci_dev *pdev;
+	unsigned int bw;
+
+	if (!is_cxl_endpoint(port))
+		return -EINVAL;
+
+	dport = iter->parent_dport;
+
+	/*
+	 * Exit the loop when the parent port of the current port is cxl root.
+	 * The iterative loop starts at the endpoint and gathers the
+	 * latency of the CXL link from the current iter to the next downstream
+	 * port each iteration. If the parent is cxl root then there is
+	 * nothing to gather.
+	 */
+	while (iter && !is_cxl_root(to_cxl_port(iter->dev.parent))) {
+		combine_coordinates(&c, &dport->sw_coord);
+		c.write_latency += dport->link_latency;
+		c.read_latency += dport->link_latency;
+
+		iter = to_cxl_port(iter->dev.parent);
+		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);
+	if (bw == 0)
+		return -ENXIO;
+	bw /= BITS_PER_BYTE;
+
+	c.write_bandwidth = min(c.write_bandwidth, bw);
+	c.read_bandwidth = min(c.read_bandwidth, bw);
+
+	*coord = c;
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_endpoint_get_perf_coordinates, CXL);
+
 /* for user tooling to ensure port disable work has completed */
 static ssize_t flush_store(const struct bus_type *bus, const char *buf, size_t count)
 {
diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index 0e88f1aed018..57a5901d5a60 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -2468,10 +2468,6 @@ int cxl_get_poison_by_endpoint(struct cxl_port *port)
 	struct cxl_poison_context ctx;
 	int rc = 0;
 
-	rc = down_read_interruptible(&cxl_region_rwsem);
-	if (rc)
-		return rc;
-
 	ctx = (struct cxl_poison_context) {
 		.port = port
 	};
@@ -2481,7 +2477,6 @@ int cxl_get_poison_by_endpoint(struct cxl_port *port)
 		rc = cxl_get_poison_unmapped(to_cxl_memdev(port->uport_dev),
 					     &ctx);
 
-	up_read(&cxl_region_rwsem);
 	return rc;
 }