6 files changed, 176 insertions, 98 deletions

diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c
index 6fe11546889f..08fd0baea7a0 100644
--- a/drivers/cxl/core/cdat.c
+++ b/drivers/cxl/core/cdat.c
@@ -210,19 +210,12 @@ static int cxl_port_perf_data_calculate(struct cxl_port *port,
 	return 0;
 }
 
-static void add_perf_entry(struct device *dev, struct dsmas_entry *dent,
-			   struct list_head *list)
+static void update_perf_entry(struct device *dev, struct dsmas_entry *dent,
+			      struct cxl_dpa_perf *dpa_perf)
 {
-	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,
@@ -230,20 +223,6 @@ static void add_perf_entry(struct device *dev, struct dsmas_entry *dent,
 		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)
 {
@@ -263,16 +242,14 @@ static void cxl_memdev_set_qos_class(struct cxl_dev_state *cxlds,
 	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);
+			update_perf_entry(dev, dent, &mds->ram_perf);
 		else if (resource_size(&cxlds->pmem_res) &&
 			 range_contains(&pmem_range, &dent->dpa_range))
-			add_perf_entry(dev, dent, &mds->pmem_perf_list);
+			update_perf_entry(dev, dent, &mds->pmem_perf);
 		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)
@@ -293,24 +270,24 @@ static int match_cxlrd_qos_class(struct device *dev, void *data)
 	return 0;
 }
 
-static void cxl_qos_match(struct cxl_port *root_port,
-			  struct list_head *work_list,
-			  struct list_head *discard_list)
+static void reset_dpa_perf(struct cxl_dpa_perf *dpa_perf)
 {
-	struct cxl_dpa_perf *dpa_perf, *n;
+	*dpa_perf = (struct cxl_dpa_perf) {
+		.qos_class = CXL_QOS_CLASS_INVALID,
+	};
+}
 
-	list_for_each_entry_safe(dpa_perf, n, work_list, list) {
-		int rc;
+static bool cxl_qos_match(struct cxl_port *root_port,
+			  struct cxl_dpa_perf *dpa_perf)
+{
+	if (dpa_perf->qos_class == CXL_QOS_CLASS_INVALID)
+		return false;
 
-		if (dpa_perf->qos_class == CXL_QOS_CLASS_INVALID)
-			return;
+	if (!device_for_each_child(&root_port->dev, &dpa_perf->qos_class,
+				   match_cxlrd_qos_class))
+		return false;
 
-		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);
-	}
+	return true;
 }
 
 static int match_cxlrd_hb(struct device *dev, void *data)
@@ -334,23 +311,10 @@ static int match_cxlrd_hb(struct device *dev, void *data)
 	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);
-	LIST_HEAD(__discard);
-	struct list_head *discard __free(dpa_perf) = &__discard;
 	struct cxl_port *root_port;
 	int rc;
 
@@ -363,16 +327,17 @@ static int cxl_qos_class_verify(struct cxl_memdev *cxlmd)
 	root_port = &cxl_root->port;
 
 	/* 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);
+	if (!cxl_qos_match(root_port, &mds->ram_perf))
+		reset_dpa_perf(&mds->ram_perf);
+	if (!cxl_qos_match(root_port, &mds->pmem_perf))
+		reset_dpa_perf(&mds->pmem_perf);
 
 	/* 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);
+				   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);
+		reset_dpa_perf(&mds->ram_perf);
+		reset_dpa_perf(&mds->pmem_perf);
 	}
 
 	return rc;
@@ -417,6 +382,7 @@ void cxl_endpoint_parse_cdat(struct cxl_port *port)
 
 	cxl_memdev_set_qos_class(cxlds, dsmas_xa);
 	cxl_qos_class_verify(cxlmd);
+	cxl_memdev_update_perf(cxlmd);
 }
 EXPORT_SYMBOL_NS_GPL(cxl_endpoint_parse_cdat, CXL);
 
diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index 27166a411705..9adda4795eb7 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -1391,8 +1391,8 @@ 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);
+	mds->ram_perf.qos_class = CXL_QOS_CLASS_INVALID;
+	mds->pmem_perf.qos_class = CXL_QOS_CLASS_INVALID;
 
 	return mds;
 }
diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c
index dae8802ecdb0..d4e259f3a7e9 100644
--- a/drivers/cxl/core/memdev.c
+++ b/drivers/cxl/core/memdev.c
@@ -447,13 +447,41 @@ static struct attribute *cxl_memdev_attributes[] = {
 	NULL,
 };
 
+static ssize_t pmem_qos_class_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
+
+	return sysfs_emit(buf, "%d\n", mds->pmem_perf.qos_class);
+}
+
+static struct device_attribute dev_attr_pmem_qos_class =
+	__ATTR(qos_class, 0444, pmem_qos_class_show, NULL);
+
 static struct attribute *cxl_memdev_pmem_attributes[] = {
 	&dev_attr_pmem_size.attr,
+	&dev_attr_pmem_qos_class.attr,
 	NULL,
 };
 
+static ssize_t ram_qos_class_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
+
+	return sysfs_emit(buf, "%d\n", mds->ram_perf.qos_class);
+}
+
+static struct device_attribute dev_attr_ram_qos_class =
+	__ATTR(qos_class, 0444, ram_qos_class_show, NULL);
+
 static struct attribute *cxl_memdev_ram_attributes[] = {
 	&dev_attr_ram_size.attr,
+	&dev_attr_ram_qos_class.attr,
 	NULL,
 };
 
@@ -477,14 +505,42 @@ static struct attribute_group cxl_memdev_attribute_group = {
 	.is_visible = cxl_memdev_visible,
 };
 
+static umode_t cxl_ram_visible(struct kobject *kobj, struct attribute *a, int n)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
+
+	if (a == &dev_attr_ram_qos_class.attr)
+		if (mds->ram_perf.qos_class == CXL_QOS_CLASS_INVALID)
+			return 0;
+
+	return a->mode;
+}
+
 static struct attribute_group cxl_memdev_ram_attribute_group = {
 	.name = "ram",
 	.attrs = cxl_memdev_ram_attributes,
+	.is_visible = cxl_ram_visible,
 };
 
+static umode_t cxl_pmem_visible(struct kobject *kobj, struct attribute *a, int n)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
+
+	if (a == &dev_attr_pmem_qos_class.attr)
+		if (mds->pmem_perf.qos_class == CXL_QOS_CLASS_INVALID)
+			return 0;
+
+	return a->mode;
+}
+
 static struct attribute_group cxl_memdev_pmem_attribute_group = {
 	.name = "pmem",
 	.attrs = cxl_memdev_pmem_attributes,
+	.is_visible = cxl_pmem_visible,
 };
 
 static umode_t cxl_memdev_security_visible(struct kobject *kobj,
@@ -519,6 +575,13 @@ static const struct attribute_group *cxl_memdev_attribute_groups[] = {
 	NULL,
 };
 
+void cxl_memdev_update_perf(struct cxl_memdev *cxlmd)
+{
+	sysfs_update_group(&cxlmd->dev.kobj, &cxl_memdev_ram_attribute_group);
+	sysfs_update_group(&cxlmd->dev.kobj, &cxl_memdev_pmem_attribute_group);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_memdev_update_perf, CXL);
+
 static const struct device_type cxl_memdev_type = {
 	.name = "cxl_memdev",
 	.release = cxl_memdev_release,
diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
index 6c9c8d92f8f7..e9e6c81ce034 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -477,9 +477,9 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm,
 		allowed++;
 	}
 
-	if (!allowed) {
-		cxl_set_mem_enable(cxlds, 0);
-		info->mem_enabled = 0;
+	if (!allowed && info->mem_enabled) {
+		dev_err(dev, "Range register decodes outside platform defined CXL ranges.\n");
+		return -ENXIO;
 	}
 
 	/*
@@ -932,11 +932,21 @@ static void cxl_handle_rdport_errors(struct cxl_dev_state *cxlds) { }
 void cxl_cor_error_detected(struct pci_dev *pdev)
 {
 	struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
+	struct device *dev = &cxlds->cxlmd->dev;
+
+	scoped_guard(device, dev) {
+		if (!dev->driver) {
+			dev_warn(&pdev->dev,
+				 "%s: memdev disabled, abort error handling\n",
+				 dev_name(dev));
+			return;
+		}
 
-	if (cxlds->rcd)
-		cxl_handle_rdport_errors(cxlds);
+		if (cxlds->rcd)
+			cxl_handle_rdport_errors(cxlds);
 
-	cxl_handle_endpoint_cor_ras(cxlds);
+		cxl_handle_endpoint_cor_ras(cxlds);
+	}
 }
 EXPORT_SYMBOL_NS_GPL(cxl_cor_error_detected, CXL);
 
@@ -948,16 +958,25 @@ pci_ers_result_t cxl_error_detected(struct pci_dev *pdev,
 	struct device *dev = &cxlmd->dev;
 	bool ue;
 
-	if (cxlds->rcd)
-		cxl_handle_rdport_errors(cxlds);
+	scoped_guard(device, dev) {
+		if (!dev->driver) {
+			dev_warn(&pdev->dev,
+				 "%s: memdev disabled, abort error handling\n",
+				 dev_name(dev));
+			return PCI_ERS_RESULT_DISCONNECT;
+		}
+
+		if (cxlds->rcd)
+			cxl_handle_rdport_errors(cxlds);
+		/*
+		 * A frozen channel indicates an impending reset which is fatal to
+		 * CXL.mem operation, and will likely crash the system. On the off
+		 * chance the situation is recoverable dump the status of the RAS
+		 * capability registers and bounce the active state of the memdev.
+		 */
+		ue = cxl_handle_endpoint_ras(cxlds);
+	}
 
-	/*
-	 * A frozen channel indicates an impending reset which is fatal to
-	 * CXL.mem operation, and will likely crash the system. On the off
-	 * chance the situation is recoverable dump the status of the RAS
-	 * capability registers and bounce the active state of the memdev.
-	 */
-	ue = cxl_handle_endpoint_ras(cxlds);
 
 	switch (state) {
 	case pci_channel_io_normal:
diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index 0f05692bfec3..4c7fd2d5cccb 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -525,7 +525,7 @@ static int alloc_hpa(struct cxl_region *cxlr, resource_size_t size)
 	struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(cxlr->dev.parent);
 	struct cxl_region_params *p = &cxlr->params;
 	struct resource *res;
-	u32 remainder = 0;
+	u64 remainder = 0;
 
 	lockdep_assert_held_write(&cxl_region_rwsem);
 
@@ -545,7 +545,7 @@ static int alloc_hpa(struct cxl_region *cxlr, resource_size_t size)
 	    (cxlr->mode == CXL_DECODER_PMEM && uuid_is_null(&p->uuid)))
 		return -ENXIO;
 
-	div_u64_rem(size, SZ_256M * p->interleave_ways, &remainder);
+	div64_u64_rem(size, (u64)SZ_256M * p->interleave_ways, &remainder);
 	if (remainder)
 		return -EINVAL;
 
@@ -730,12 +730,17 @@ static int match_auto_decoder(struct device *dev, void *data)
 	return 0;
 }
 
-static struct cxl_decoder *cxl_region_find_decoder(struct cxl_port *port,
-						   struct cxl_region *cxlr)
+static struct cxl_decoder *
+cxl_region_find_decoder(struct cxl_port *port,
+			struct cxl_endpoint_decoder *cxled,
+			struct cxl_region *cxlr)
 {
 	struct device *dev;
 	int id = 0;
 
+	if (port == cxled_to_port(cxled))
+		return &cxled->cxld;
+
 	if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags))
 		dev = device_find_child(&port->dev, &cxlr->params,
 					match_auto_decoder);
@@ -753,8 +758,31 @@ static struct cxl_decoder *cxl_region_find_decoder(struct cxl_port *port,
 	return to_cxl_decoder(dev);
 }
 
-static struct cxl_region_ref *alloc_region_ref(struct cxl_port *port,
-					       struct cxl_region *cxlr)
+static bool auto_order_ok(struct cxl_port *port, struct cxl_region *cxlr_iter,
+			  struct cxl_decoder *cxld)
+{
+	struct cxl_region_ref *rr = cxl_rr_load(port, cxlr_iter);
+	struct cxl_decoder *cxld_iter = rr->decoder;
+
+	/*
+	 * Allow the out of order assembly of auto-discovered regions.
+	 * Per CXL Spec 3.1 8.2.4.20.12 software must commit decoders
+	 * in HPA order. Confirm that the decoder with the lesser HPA
+	 * starting address has the lesser id.
+	 */
+	dev_dbg(&cxld->dev, "check for HPA violation %s:%d < %s:%d\n",
+		dev_name(&cxld->dev), cxld->id,
+		dev_name(&cxld_iter->dev), cxld_iter->id);
+
+	if (cxld_iter->id > cxld->id)
+		return true;
+
+	return false;
+}
+
+static struct cxl_region_ref *
+alloc_region_ref(struct cxl_port *port, struct cxl_region *cxlr,
+		 struct cxl_endpoint_decoder *cxled)
 {
 	struct cxl_region_params *p = &cxlr->params;
 	struct cxl_region_ref *cxl_rr, *iter;
@@ -764,16 +792,21 @@ static struct cxl_region_ref *alloc_region_ref(struct cxl_port *port,
 	xa_for_each(&port->regions, index, iter) {
 		struct cxl_region_params *ip = &iter->region->params;
 
-		if (!ip->res)
+		if (!ip->res || ip->res->start < p->res->start)
 			continue;
 
-		if (ip->res->start > p->res->start) {
-			dev_dbg(&cxlr->dev,
-				"%s: HPA order violation %s:%pr vs %pr\n",
-				dev_name(&port->dev),
-				dev_name(&iter->region->dev), ip->res, p->res);
-			return ERR_PTR(-EBUSY);
+		if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags)) {
+			struct cxl_decoder *cxld;
+
+			cxld = cxl_region_find_decoder(port, cxled, cxlr);
+			if (auto_order_ok(port, iter->region, cxld))
+				continue;
 		}
+		dev_dbg(&cxlr->dev, "%s: HPA order violation %s:%pr vs %pr\n",
+			dev_name(&port->dev),
+			dev_name(&iter->region->dev), ip->res, p->res);
+
+		return ERR_PTR(-EBUSY);
 	}
 
 	cxl_rr = kzalloc(sizeof(*cxl_rr), GFP_KERNEL);
@@ -853,10 +886,7 @@ static int cxl_rr_alloc_decoder(struct cxl_port *port, struct cxl_region *cxlr,
 {
 	struct cxl_decoder *cxld;
 
-	if (port == cxled_to_port(cxled))
-		cxld = &cxled->cxld;
-	else
-		cxld = cxl_region_find_decoder(port, cxlr);
+	cxld = cxl_region_find_decoder(port, cxled, cxlr);
 	if (!cxld) {
 		dev_dbg(&cxlr->dev, "%s: no decoder available\n",
 			dev_name(&port->dev));
@@ -953,7 +983,7 @@ static int cxl_port_attach_region(struct cxl_port *port,
 			nr_targets_inc = true;
 		}
 	} else {
-		cxl_rr = alloc_region_ref(port, cxlr);
+		cxl_rr = alloc_region_ref(port, cxlr, cxled);
 		if (IS_ERR(cxl_rr)) {
 			dev_dbg(&cxlr->dev,
 				"%s: failed to allocate region reference\n",
diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h
index 89445435303a..bdf117a33744 100644
--- a/drivers/cxl/core/trace.h
+++ b/drivers/cxl/core/trace.h
@@ -338,7 +338,7 @@ TRACE_EVENT(cxl_general_media,
 
 	TP_fast_assign(
 		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
-		memcpy(&__entry->hdr_uuid, &CXL_EVENT_GEN_MEDIA_UUID, sizeof(uuid_t));
+		__entry->hdr_uuid = CXL_EVENT_GEN_MEDIA_UUID;
 
 		/* General Media */
 		__entry->dpa = le64_to_cpu(rec->phys_addr);
@@ -425,7 +425,7 @@ TRACE_EVENT(cxl_dram,
 
 	TP_fast_assign(
 		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
-		memcpy(&__entry->hdr_uuid, &CXL_EVENT_DRAM_UUID, sizeof(uuid_t));
+		__entry->hdr_uuid = CXL_EVENT_DRAM_UUID;
 
 		/* DRAM */
 		__entry->dpa = le64_to_cpu(rec->phys_addr);
@@ -573,7 +573,7 @@ TRACE_EVENT(cxl_memory_module,
 
 	TP_fast_assign(
 		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
-		memcpy(&__entry->hdr_uuid, &CXL_EVENT_MEM_MODULE_UUID, sizeof(uuid_t));
+		__entry->hdr_uuid = CXL_EVENT_MEM_MODULE_UUID;
 
 		/* Memory Module Event */
 		__entry->event_type = rec->event_type;