Merging upstream version 6.9.2.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

10 files changed, 501 insertions, 163 deletions

diff --git a/drivers/cxl/Kconfig b/drivers/cxl/Kconfig
index 67998dbd1..5f3c9c552 100644
--- a/drivers/cxl/Kconfig
+++ b/drivers/cxl/Kconfig
@@ -144,17 +144,4 @@ config CXL_REGION_INVALIDATION_TEST
 	  If unsure, or if this kernel is meant for production environments,
 	  say N.
 
-config CXL_PMU
-	tristate "CXL Performance Monitoring Unit"
-	default CXL_BUS
-	depends on PERF_EVENTS
-	help
-	  Support performance monitoring as defined in CXL rev 3.0
-	  section 13.2: Performance Monitoring. CXL components may have
-	  one or more CXL Performance Monitoring Units (CPMUs).
-
-	  Say 'y/m' to enable a driver that will attach to performance
-	  monitoring units and provide standard perf based interfaces.
-
-	  If unsure say 'm'.
 endif
diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c
index af5cb818f..cb8c155a2 100644
--- a/drivers/cxl/acpi.c
+++ b/drivers/cxl/acpi.c
@@ -525,22 +525,11 @@ static int get_genport_coordinates(struct device *dev, struct cxl_dport *dport)
 {
 	struct acpi_device *hb = to_cxl_host_bridge(NULL, dev);
 	u32 uid;
-	int rc;
 
 	if (kstrtou32(acpi_device_uid(hb), 0, &uid))
 		return -EINVAL;
 
-	rc = acpi_get_genport_coordinates(uid, dport->hb_coord);
-	if (rc < 0)
-		return rc;
-
-	/* Adjust back to picoseconds from nanoseconds */
-	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;
+	return acpi_get_genport_coordinates(uid, dport->coord);
 }
 
 static int add_host_bridge_dport(struct device *match, void *arg)
diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c
index fbf167f9d..bb83867d9 100644
--- a/drivers/cxl/core/cdat.c
+++ b/drivers/cxl/core/cdat.c
@@ -9,16 +9,47 @@
 #include "cxlmem.h"
 #include "core.h"
 #include "cxl.h"
+#include "core.h"
 
 struct dsmas_entry {
 	struct range dpa_range;
 	u8 handle;
-	struct access_coordinate coord;
+	struct access_coordinate coord[ACCESS_COORDINATE_MAX];
 
 	int entries;
 	int qos_class;
 };
 
+static u32 cdat_normalize(u16 entry, u64 base, u8 type)
+{
+	u32 value;
+
+	/*
+	 * Check for invalid and overflow values
+	 */
+	if (entry == 0xffff || !entry)
+		return 0;
+	else if (base > (UINT_MAX / (entry)))
+		return 0;
+
+	/*
+	 * CDAT fields follow the format of HMAT fields. See table 5 Device
+	 * Scoped Latency and Bandwidth Information Structure in Coherent Device
+	 * Attribute Table (CDAT) Specification v1.01.
+	 */
+	value = entry * base;
+	switch (type) {
+	case ACPI_HMAT_ACCESS_LATENCY:
+	case ACPI_HMAT_READ_LATENCY:
+	case ACPI_HMAT_WRITE_LATENCY:
+		value = DIV_ROUND_UP(value, 1000);
+		break;
+	default:
+		break;
+	}
+	return value;
+}
+
 static int cdat_dsmas_handler(union acpi_subtable_headers *header, void *arg,
 			      const unsigned long end)
 {
@@ -57,8 +88,8 @@ static int cdat_dsmas_handler(union acpi_subtable_headers *header, void *arg,
 	return 0;
 }
 
-static void cxl_access_coordinate_set(struct access_coordinate *coord,
-				      int access, unsigned int val)
+static void __cxl_access_coordinate_set(struct access_coordinate *coord,
+					int access, unsigned int val)
 {
 	switch (access) {
 	case ACPI_HMAT_ACCESS_LATENCY:
@@ -84,6 +115,13 @@ static void cxl_access_coordinate_set(struct access_coordinate *coord,
 	}
 }
 
+static void cxl_access_coordinate_set(struct access_coordinate *coord,
+				      int access, unsigned int val)
+{
+	for (int i = 0; i < ACCESS_COORDINATE_MAX; i++)
+		__cxl_access_coordinate_set(&coord[i], access, val);
+}
+
 static int cdat_dslbis_handler(union acpi_subtable_headers *header, void *arg,
 			       const unsigned long end)
 {
@@ -96,7 +134,6 @@ static int cdat_dslbis_handler(union acpi_subtable_headers *header, void *arg,
 	__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) {
@@ -123,12 +160,10 @@ static int cdat_dslbis_handler(union acpi_subtable_headers *header, void *arg,
 
 	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");
+	val = cdat_normalize(le16_to_cpu(le_val), le64_to_cpu(le_base),
+			     dslbis->data_type);
 
-	cxl_access_coordinate_set(&dent->coord, dslbis->data_type, val);
+	cxl_access_coordinate_set(dent->coord, dslbis->data_type, val);
 
 	return 0;
 }
@@ -149,38 +184,31 @@ static int cxl_cdat_endpoint_process(struct cxl_port *port,
 	int rc;
 
 	rc = cdat_table_parse(ACPI_CDAT_TYPE_DSMAS, cdat_dsmas_handler,
-			      dsmas_xa, port->cdat.table);
+			      dsmas_xa, port->cdat.table, port->cdat.length);
 	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);
+			      dsmas_xa, port->cdat.table, port->cdat.length);
 	return cdat_table_parse_output(rc);
 }
 
 static int cxl_port_perf_data_calculate(struct cxl_port *port,
 					struct xarray *dsmas_xa)
 {
-	struct access_coordinate ep_c;
-	struct access_coordinate coord[ACCESS_COORDINATE_MAX];
+	struct access_coordinate ep_c[ACCESS_COORDINATE_MAX];
 	struct dsmas_entry *dent;
 	int valid_entries = 0;
 	unsigned long index;
 	int rc;
 
-	rc = cxl_endpoint_get_perf_coordinates(port, &ep_c);
+	rc = cxl_endpoint_get_perf_coordinates(port, ep_c);
 	if (rc) {
 		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;
-	}
-
 	struct cxl_root *cxl_root __free(put_cxl_root) = find_cxl_root(port);
 
 	if (!cxl_root)
@@ -192,18 +220,10 @@ static int cxl_port_perf_data_calculate(struct cxl_port *port,
 	xa_for_each(dsmas_xa, index, dent) {
 		int qos_class;
 
-		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_LOCAL],
-					&coord[ACCESS_COORDINATE_LOCAL],
-					&dent->coord);
+		cxl_coordinates_combine(dent->coord, dent->coord, ep_c);
 		dent->entries = 1;
 		rc = cxl_root->ops->qos_class(cxl_root,
-					      &coord[ACCESS_COORDINATE_LOCAL],
+					      &dent->coord[ACCESS_COORDINATE_CPU],
 					      1, &qos_class);
 		if (rc != 1)
 			continue;
@@ -221,14 +241,17 @@ static int cxl_port_perf_data_calculate(struct cxl_port *port,
 static void update_perf_entry(struct device *dev, struct dsmas_entry *dent,
 			      struct cxl_dpa_perf *dpa_perf)
 {
+	for (int i = 0; i < ACCESS_COORDINATE_MAX; i++)
+		dpa_perf->coord[i] = dent->coord[i];
 	dpa_perf->dpa_range = dent->dpa_range;
-	dpa_perf->coord = dent->coord;
 	dpa_perf->qos_class = dent->qos_class;
 	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);
+		dent->coord[ACCESS_COORDINATE_CPU].read_bandwidth,
+		dent->coord[ACCESS_COORDINATE_CPU].write_bandwidth,
+		dent->coord[ACCESS_COORDINATE_CPU].read_latency,
+		dent->coord[ACCESS_COORDINATE_CPU].write_latency);
 }
 
 static void cxl_memdev_set_qos_class(struct cxl_dev_state *cxlds,
@@ -460,17 +483,16 @@ static int cdat_sslbis_handler(union acpi_subtable_headers *header, void *arg,
 
 		le_base = (__force __le64)tbl->sslbis_header.entry_base_unit;
 		le_val = (__force __le16)tbl->entries[i].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");
+		val = cdat_normalize(le16_to_cpu(le_val), le64_to_cpu(le_base),
+				     sslbis->data_type);
 
 		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,
+			    dsp_id == dport->port_id) {
+				cxl_access_coordinate_set(dport->coord,
 							  sslbis->data_type,
 							  val);
+			}
 		}
 	}
 
@@ -485,13 +507,28 @@ void cxl_switch_parse_cdat(struct cxl_port *port)
 		return;
 
 	rc = cdat_table_parse(ACPI_CDAT_TYPE_SSLBIS, cdat_sslbis_handler,
-			      port, port->cdat.table);
+			      port, port->cdat.table, port->cdat.length);
 	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);
 
+static 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;
+}
+
 /**
  * cxl_coordinates_combine - Combine the two input coordinates
  *
@@ -503,15 +540,60 @@ 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;
+	for (int i = 0; i < ACCESS_COORDINATE_MAX; i++)
+		__cxl_coordinates_combine(&out[i], &c1[i], &c2[i]);
 }
 
 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_dev_state *cxlds = cxlmd->cxlds;
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
+	struct range dpa = {
+			.start = cxled->dpa_res->start,
+			.end = cxled->dpa_res->end,
+	};
+	struct cxl_dpa_perf *perf;
+
+	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;
+
+	for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) {
+		/* 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,
+						    perf->coord[i].read_latency);
+		cxlr->coord[i].write_latency = max_t(unsigned int,
+						     cxlr->coord[i].write_latency,
+						     perf->coord[i].write_latency);
+		cxlr->coord[i].read_bandwidth += perf->coord[i].read_bandwidth;
+		cxlr->coord[i].write_bandwidth += perf->coord[i].write_bandwidth;
+	}
+}
+
+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 3b64fb1b9..bc5a95665 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/pci.c b/drivers/cxl/core/pci.c
index e9e6c81ce..0df09bd79 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -518,14 +518,14 @@ EXPORT_SYMBOL_NS_GPL(cxl_hdm_decode_init, CXL);
 	 FIELD_PREP(CXL_DOE_TABLE_ACCESS_ENTRY_HANDLE, (entry_handle)))
 
 static int cxl_cdat_get_length(struct device *dev,
-			       struct pci_doe_mb *cdat_doe,
+			       struct pci_doe_mb *doe_mb,
 			       size_t *length)
 {
 	__le32 request = CDAT_DOE_REQ(0);
 	__le32 response[2];
 	int rc;
 
-	rc = pci_doe(cdat_doe, PCI_DVSEC_VENDOR_ID_CXL,
+	rc = pci_doe(doe_mb, PCI_DVSEC_VENDOR_ID_CXL,
 		     CXL_DOE_PROTOCOL_TABLE_ACCESS,
 		     &request, sizeof(request),
 		     &response, sizeof(response));
@@ -543,56 +543,58 @@ static int cxl_cdat_get_length(struct device *dev,
 }
 
 static int cxl_cdat_read_table(struct device *dev,
-			       struct pci_doe_mb *cdat_doe,
-			       void *cdat_table, size_t *cdat_length)
+			       struct pci_doe_mb *doe_mb,
+			       struct cdat_doe_rsp *rsp, size_t *length)
 {
-	size_t length = *cdat_length + sizeof(__le32);
-	__le32 *data = cdat_table;
-	int entry_handle = 0;
+	size_t received, remaining = *length;
+	unsigned int entry_handle = 0;
+	union cdat_data *data;
 	__le32 saved_dw = 0;
 
 	do {
 		__le32 request = CDAT_DOE_REQ(entry_handle);
-		struct cdat_entry_header *entry;
-		size_t entry_dw;
 		int rc;
 
-		rc = pci_doe(cdat_doe, PCI_DVSEC_VENDOR_ID_CXL,
+		rc = pci_doe(doe_mb, PCI_DVSEC_VENDOR_ID_CXL,
 			     CXL_DOE_PROTOCOL_TABLE_ACCESS,
 			     &request, sizeof(request),
-			     data, length);
+			     rsp, sizeof(*rsp) + remaining);
 		if (rc < 0) {
 			dev_err(dev, "DOE failed: %d", rc);
 			return rc;
 		}
 
-		/* 1 DW Table Access Response Header + CDAT entry */
-		entry = (struct cdat_entry_header *)(data + 1);
-		if ((entry_handle == 0 &&
-		     rc != sizeof(__le32) + sizeof(struct cdat_header)) ||
-		    (entry_handle > 0 &&
-		     (rc < sizeof(__le32) + sizeof(*entry) ||
-		      rc != sizeof(__le32) + le16_to_cpu(entry->length))))
+		if (rc < sizeof(*rsp))
 			return -EIO;
 
+		data = (union cdat_data *)rsp->data;
+		received = rc - sizeof(*rsp);
+
+		if (entry_handle == 0) {
+			if (received != sizeof(data->header))
+				return -EIO;
+		} else {
+			if (received < sizeof(data->entry) ||
+			    received != le16_to_cpu(data->entry.length))
+				return -EIO;
+		}
+
 		/* Get the CXL table access header entry handle */
 		entry_handle = FIELD_GET(CXL_DOE_TABLE_ACCESS_ENTRY_HANDLE,
-					 le32_to_cpu(data[0]));
-		entry_dw = rc / sizeof(__le32);
-		/* Skip Header */
-		entry_dw -= 1;
+					 le32_to_cpu(rsp->doe_header));
+
 		/*
 		 * Table Access Response Header overwrote the last DW of
 		 * previous entry, so restore that DW
 		 */
-		*data = saved_dw;
-		length -= entry_dw * sizeof(__le32);
-		data += entry_dw;
-		saved_dw = *data;
+		rsp->doe_header = saved_dw;
+		remaining -= received;
+		rsp = (void *)rsp + received;
+		saved_dw = rsp->doe_header;
 	} while (entry_handle != CXL_DOE_TABLE_ACCESS_LAST_ENTRY);
 
 	/* Length in CDAT header may exceed concatenation of CDAT entries */
-	*cdat_length -= length - sizeof(__le32);
+	*length -= remaining;
 
 	return 0;
 }
@@ -617,11 +619,11 @@ void read_cdat_data(struct cxl_port *port)
 {
 	struct device *uport = port->uport_dev;
 	struct device *dev = &port->dev;
-	struct pci_doe_mb *cdat_doe;
+	struct pci_doe_mb *doe_mb;
 	struct pci_dev *pdev = NULL;
 	struct cxl_memdev *cxlmd;
-	size_t cdat_length;
-	void *cdat_table, *cdat_buf;
+	struct cdat_doe_rsp *buf;
+	size_t table_length, length;
 	int rc;
 
 	if (is_cxl_memdev(uport)) {
@@ -638,39 +640,48 @@ void read_cdat_data(struct cxl_port *port)
 	if (!pdev)
 		return;
 
-	cdat_doe = pci_find_doe_mailbox(pdev, PCI_DVSEC_VENDOR_ID_CXL,
-					CXL_DOE_PROTOCOL_TABLE_ACCESS);
-	if (!cdat_doe) {
+	doe_mb = pci_find_doe_mailbox(pdev, PCI_DVSEC_VENDOR_ID_CXL,
+				      CXL_DOE_PROTOCOL_TABLE_ACCESS);
+	if (!doe_mb) {
 		dev_dbg(dev, "No CDAT mailbox\n");
 		return;
 	}
 
 	port->cdat_available = true;
 
-	if (cxl_cdat_get_length(dev, cdat_doe, &cdat_length)) {
+	if (cxl_cdat_get_length(dev, doe_mb, &length)) {
 		dev_dbg(dev, "No CDAT length\n");
 		return;
 	}
 
-	cdat_buf = devm_kzalloc(dev, cdat_length + sizeof(__le32), GFP_KERNEL);
-	if (!cdat_buf)
-		return;
+	/*
+	 * The begin of the CDAT buffer needs space for additional 4
+	 * bytes for the DOE header. Table data starts afterwards.
+	 */
+	buf = devm_kzalloc(dev, sizeof(*buf) + length, GFP_KERNEL);
+	if (!buf)
+		goto err;
+
+	table_length = length;
 
-	rc = cxl_cdat_read_table(dev, cdat_doe, cdat_buf, &cdat_length);
+	rc = cxl_cdat_read_table(dev, doe_mb, buf, &length);
 	if (rc)
 		goto err;
 
-	cdat_table = cdat_buf + sizeof(__le32);
-	if (cdat_checksum(cdat_table, cdat_length))
+	if (table_length != length)
+		dev_warn(dev, "Malformed CDAT table length (%zu:%zu), discarding trailing data\n",
+			table_length, length);
+
+	if (cdat_checksum(buf->data, length))
 		goto err;
 
-	port->cdat.table = cdat_table;
-	port->cdat.length = cdat_length;
-	return;
+	port->cdat.table = buf->data;
+	port->cdat.length = length;
 
+	return;
 err:
 	/* Don't leave table data allocated on error */
-	devm_kfree(dev, cdat_buf);
+	devm_kfree(dev, buf);
 	dev_err(dev, "Failed to read/validate CDAT.\n");
 }
 EXPORT_SYMBOL_NS_GPL(read_cdat_data, CXL);
diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index 4ae441ef3..887ed6e35 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -3,6 +3,7 @@
 #include <linux/platform_device.h>
 #include <linux/memregion.h>
 #include <linux/workqueue.h>
+#include <linux/einj-cxl.h>
 #include <linux/debugfs.h>
 #include <linux/device.h>
 #include <linux/module.h>
@@ -793,6 +794,40 @@ static int cxl_dport_setup_regs(struct device *host, struct cxl_dport *dport,
 	return rc;
 }
 
+DEFINE_SHOW_ATTRIBUTE(einj_cxl_available_error_type);
+
+static int cxl_einj_inject(void *data, u64 type)
+{
+	struct cxl_dport *dport = data;
+
+	if (dport->rch)
+		return einj_cxl_inject_rch_error(dport->rcrb.base, type);
+
+	return einj_cxl_inject_error(to_pci_dev(dport->dport_dev), type);
+}
+DEFINE_DEBUGFS_ATTRIBUTE(cxl_einj_inject_fops, NULL, cxl_einj_inject,
+			 "0x%llx\n");
+
+static void cxl_debugfs_create_dport_dir(struct cxl_dport *dport)
+{
+	struct dentry *dir;
+
+	if (!einj_cxl_is_initialized())
+		return;
+
+	/*
+	 * dport_dev needs to be a PCIe port for CXL 2.0+ ports because
+	 * EINJ expects a dport SBDF to be specified for 2.0 error injection.
+	 */
+	if (!dport->rch && !dev_is_pci(dport->dport_dev))
+		return;
+
+	dir = cxl_debugfs_create_dir(dev_name(dport->dport_dev));
+
+	debugfs_create_file("einj_inject", 0200, dir, dport,
+			    &cxl_einj_inject_fops);
+}
+
 static struct cxl_port *__devm_cxl_add_port(struct device *host,
 					    struct device *uport_dev,
 					    resource_size_t component_reg_phys,
@@ -822,6 +857,7 @@ 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)
@@ -1149,6 +1185,8 @@ __devm_cxl_add_dport(struct cxl_port *port, struct device *dport_dev,
 	if (dev_is_pci(dport_dev))
 		dport->link_latency = cxl_pci_get_latency(to_pci_dev(dport_dev));
 
+	cxl_debugfs_create_dport_dir(dport);
+
 	return dport;
 }
 
@@ -1374,7 +1412,6 @@ 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);
 }
@@ -2096,36 +2133,39 @@ bool schedule_cxl_memdev_detach(struct cxl_memdev *cxlmd)
 }
 EXPORT_SYMBOL_NS_GPL(schedule_cxl_memdev_detach, CXL);
 
-/**
- * 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)
+static void add_latency(struct access_coordinate *c, long latency)
 {
-	struct cxl_port *iter = port;
-	struct cxl_dport *dport;
-
-	if (!is_cxl_endpoint(port))
-		return -EINVAL;
+	for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) {
+		c[i].write_latency += latency;
+		c[i].read_latency += latency;
+	}
+}
 
-	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;
+static bool coordinates_valid(struct access_coordinate *c)
+{
+	for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) {
+		if (c[i].read_bandwidth && c[i].write_bandwidth &&
+		    c[i].read_latency && c[i].write_latency)
+			continue;
+		return false;
 	}
 
-	coord[ACCESS_COORDINATE_LOCAL] =
-		dport->hb_coord[ACCESS_COORDINATE_LOCAL];
-	coord[ACCESS_COORDINATE_CPU] =
-		dport->hb_coord[ACCESS_COORDINATE_CPU];
+	return true;
+}
 
-	return 0;
+static void set_min_bandwidth(struct access_coordinate *c, unsigned int bw)
+{
+	for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) {
+		c[i].write_bandwidth = min(c[i].write_bandwidth, bw);
+		c[i].read_bandwidth = min(c[i].read_bandwidth, bw);
+	}
+}
+
+static void set_access_coordinates(struct access_coordinate *out,
+				   struct access_coordinate *in)
+{
+	for (int i = 0; i < ACCESS_COORDINATE_MAX; i++)
+		out[i] = in[i];
 }
 
 static bool parent_port_is_cxl_root(struct cxl_port *port)
@@ -2144,13 +2184,21 @@ static bool parent_port_is_cxl_root(struct cxl_port *port)
 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_memdev *cxlmd = to_cxl_memdev(port->uport_dev);
+	struct access_coordinate c[] = {
+		{
+			.read_bandwidth = UINT_MAX,
+			.write_bandwidth = UINT_MAX,
+		},
+		{
+			.read_bandwidth = UINT_MAX,
+			.write_bandwidth = UINT_MAX,
+		},
 	};
 	struct cxl_port *iter = port;
 	struct cxl_dport *dport;
 	struct pci_dev *pdev;
+	struct device *dev;
 	unsigned int bw;
 	bool is_cxl_root;
 
@@ -2158,6 +2206,13 @@ int cxl_endpoint_get_perf_coordinates(struct cxl_port *port,
 		return -EINVAL;
 
 	/*
+	 * Skip calculation for RCD. Expectation is HMAT already covers RCD case
+	 * since RCH does not support hotplug.
+	 */
+	if (cxlmd->cxlds->rcd)
+		return 0;
+
+	/*
 	 * Exit the loop when the parent port of the current iter port is cxl
 	 * root. The iterative loop starts at the endpoint and gathers the
 	 * latency of the CXL link from the current device/port to the connected
@@ -2172,23 +2227,33 @@ int cxl_endpoint_get_perf_coordinates(struct cxl_port *port,
 		 * There's no valid access_coordinate for a root port since RPs do not
 		 * have CDAT and therefore needs to be skipped.
 		 */
-		if (!is_cxl_root)
-			cxl_coordinates_combine(&c, &c, &dport->sw_coord);
-		c.write_latency += dport->link_latency;
-		c.read_latency += dport->link_latency;
+		if (!is_cxl_root) {
+			if (!coordinates_valid(dport->coord))
+				return -EINVAL;
+			cxl_coordinates_combine(c, c, dport->coord);
+		}
+		add_latency(c, dport->link_latency);
 	} while (!is_cxl_root);
 
+	dport = iter->parent_dport;
+	/* Retrieve HB coords */
+	if (!coordinates_valid(dport->coord))
+		return -EINVAL;
+	cxl_coordinates_combine(c, c, dport->coord);
+
+	dev = port->uport_dev->parent;
+	if (!dev_is_pci(dev))
+		return -ENODEV;
+
 	/* Get the calculated PCI paths bandwidth */
-	pdev = to_pci_dev(port->uport_dev->parent);
+	pdev = to_pci_dev(dev);
 	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;
+	set_min_bandwidth(c, bw);
+	set_access_coordinates(coord, c);
 
 	return 0;
 }
@@ -2245,6 +2310,10 @@ static __init int cxl_core_init(void)
 
 	cxl_debugfs = debugfs_create_dir("cxl", NULL);
 
+	if (einj_cxl_is_initialized())
+		debugfs_create_file("einj_types", 0400, cxl_debugfs, NULL,
+				    &einj_cxl_available_error_type_fops);
+
 	cxl_mbox_init();
 
 	rc = cxl_memdev_init();
diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index 4c7fd2d5c..5c186e0a3 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 de477eb7f..036d17db6 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 {
@@ -658,8 +663,7 @@ struct cxl_rcrb_info {
  * @rch: Indicate whether this dport was enumerated in RCH or VH mode
  * @port: reference to cxl_port that contains this downstream port
  * @regs: Dport parsed register blocks
- * @sw_coord: access coordinates (performance) for switch from CDAT
- * @hb_coord: access coordinates (performance) from ACPI generic port (host bridge)
+ * @coord: access coordinates (bandwidth and latency performance attributes)
  * @link_latency: calculated PCIe downstream latency
  */
 struct cxl_dport {
@@ -670,8 +674,7 @@ struct cxl_dport {
 	bool rch;
 	struct cxl_port *port;
 	struct cxl_regs regs;
-	struct access_coordinate sw_coord;
-	struct access_coordinate hb_coord[ACCESS_COORDINATE_MAX];
+	struct access_coordinate coord[ACCESS_COORDINATE_MAX];
 	long link_latency;
 };
 
@@ -879,8 +882,8 @@ 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);
 
diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
index 20fb3b35e..36cee9c30 100644
--- a/drivers/cxl/cxlmem.h
+++ b/drivers/cxl/cxlmem.h
@@ -401,7 +401,7 @@ enum cxl_devtype {
  */
 struct cxl_dpa_perf {
 	struct range dpa_range;
-	struct access_coordinate coord;
+	struct access_coordinate coord[ACCESS_COORDINATE_MAX];
 	int qos_class;
 };
 
diff --git a/drivers/cxl/cxlpci.h b/drivers/cxl/cxlpci.h
index 711b05d9a..93992a1c8 100644
--- a/drivers/cxl/cxlpci.h
+++ b/drivers/cxl/cxlpci.h
@@ -71,6 +71,15 @@ enum cxl_regloc_type {
 	CXL_REGLOC_RBI_TYPES
 };
 
+/*
+ * Table Access DOE, CDAT Read Entry Response
+ *
+ * Spec refs:
+ *
+ * CXL 3.1 8.1.11, Table 8-14: Read Entry Response
+ * CDAT Specification 1.03: 2 CDAT Data Structures
+ */
+
 struct cdat_header {
 	__le32 length;
 	u8 revision;
@@ -86,6 +95,21 @@ struct cdat_entry_header {
 } __packed;
 
 /*
+ * The DOE CDAT read response contains a CDAT read entry (either the
+ * CDAT header or a structure).
+ */
+union cdat_data {
+	struct cdat_header header;
+	struct cdat_entry_header entry;
+} __packed;
+
+/* There is an additional CDAT response header of 4 bytes. */
+struct cdat_doe_rsp {
+	__le32 doe_header;
+	u8 data[];
+} __packed;
+
+/*
  * CXL v3.0 6.2.3 Table 6-4
  * The table indicates that if PCIe Flit Mode is set, then CXL is in 256B flits
  * mode, otherwise it's 68B flits mode.