13 files changed, 519 insertions, 324 deletions

diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c
index 8153f8d83a16..bfba7f5019cf 100644
--- a/drivers/cxl/core/cdat.c
+++ b/drivers/cxl/core/cdat.c
@@ -258,27 +258,29 @@ static void update_perf_entry(struct device *dev, struct dsmas_entry *dent,
 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))
-			update_perf_entry(dev, dent, &mds->ram_perf);
-		else if (resource_size(&cxlds->pmem_res) &&
-			 range_contains(&pmem_range, &dent->dpa_range))
-			update_perf_entry(dev, dent, &mds->pmem_perf);
-		else
+		bool found = false;
+
+		for (int i = 0; i < cxlds->nr_partitions; i++) {
+			struct resource *res = &cxlds->part[i].res;
+			struct range range = {
+				.start = res->start,
+				.end = res->end,
+			};
+
+			if (range_contains(&range, &dent->dpa_range)) {
+				update_perf_entry(dev, dent,
+						  &cxlds->part[i].perf);
+				found = true;
+				break;
+			}
+		}
+
+		if (!found)
 			dev_dbg(dev, "no partition for dsmas dpa: %pra\n",
 				&dent->dpa_range);
 	}
@@ -343,36 +345,46 @@ static int match_cxlrd_hb(struct device *dev, void *data)
 	return 0;
 }
 
-static int cxl_qos_class_verify(struct cxl_memdev *cxlmd)
+static void 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;
-	int rc;
 
 	struct cxl_root *cxl_root __free(put_cxl_root) =
 		find_cxl_root(cxlmd->endpoint);
 
+	/*
+	 * No need to reset_dpa_perf() here as find_cxl_root() is guaranteed to
+	 * succeed when called in the cxl_endpoint_port_probe() path.
+	 */
 	if (!cxl_root)
-		return -ENODEV;
+		return;
 
 	root_port = &cxl_root->port;
 
-	/* Check that the QTG IDs are all sane between end device and root decoders */
-	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,
-				   cxlmd->endpoint->host_bridge, match_cxlrd_hb);
-	if (!rc) {
-		reset_dpa_perf(&mds->ram_perf);
-		reset_dpa_perf(&mds->pmem_perf);
+	/*
+	 * Save userspace from needing to check if a qos class has any matches
+	 * by hiding qos class info if the memdev is not mapped by a root
+	 * decoder, or the partition class does not match any root decoder
+	 * class.
+	 */
+	if (!device_for_each_child(&root_port->dev,
+				   cxlmd->endpoint->host_bridge,
+				   match_cxlrd_hb)) {
+		for (int i = 0; i < cxlds->nr_partitions; i++) {
+			struct cxl_dpa_perf *perf = &cxlds->part[i].perf;
+
+			reset_dpa_perf(perf);
+		}
+		return;
 	}
 
-	return rc;
+	for (int i = 0; i < cxlds->nr_partitions; i++) {
+		struct cxl_dpa_perf *perf = &cxlds->part[i].perf;
+
+		if (!cxl_qos_match(root_port, perf))
+			reset_dpa_perf(perf);
+	}
 }
 
 static void discard_dsmas(struct xarray *xa)
@@ -570,23 +582,18 @@ static bool dpa_perf_contains(struct cxl_dpa_perf *perf,
 	return range_contains(&perf->dpa_range, &dpa);
 }
 
-static struct cxl_dpa_perf *cxled_get_dpa_perf(struct cxl_endpoint_decoder *cxled,
-					       enum cxl_decoder_mode mode)
+static struct cxl_dpa_perf *cxled_get_dpa_perf(struct cxl_endpoint_decoder *cxled)
 {
 	struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
-	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
 	struct cxl_dpa_perf *perf;
 
-	switch (mode) {
-	case CXL_DECODER_RAM:
-		perf = &mds->ram_perf;
-		break;
-	case CXL_DECODER_PMEM:
-		perf = &mds->pmem_perf;
-		break;
-	default:
+	if (cxled->part < 0)
+		return ERR_PTR(-EINVAL);
+	perf = &cxlds->part[cxled->part].perf;
+
+	if (!perf)
 		return ERR_PTR(-EINVAL);
-	}
 
 	if (!dpa_perf_contains(perf, cxled->dpa_res))
 		return ERR_PTR(-EINVAL);
@@ -647,7 +654,7 @@ static int cxl_endpoint_gather_bandwidth(struct cxl_region *cxlr,
 	if (cxlds->rcd)
 		return -ENODEV;
 
-	perf = cxled_get_dpa_perf(cxled, cxlr->mode);
+	perf = cxled_get_dpa_perf(cxled);
 	if (IS_ERR(perf))
 		return PTR_ERR(perf);
 
@@ -1053,7 +1060,7 @@ void cxl_region_perf_data_calculate(struct cxl_region *cxlr,
 
 	lockdep_assert_held(&cxl_dpa_rwsem);
 
-	perf = cxled_get_dpa_perf(cxled, cxlr->mode);
+	perf = cxled_get_dpa_perf(cxled);
 	if (IS_ERR(perf))
 		return;
 
diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h
index c87dbfcc9403..83c690ca6fad 100644
--- a/drivers/cxl/core/core.h
+++ b/drivers/cxl/core/core.h
@@ -72,8 +72,8 @@ void __iomem *devm_cxl_iomap_block(struct device *dev, resource_size_t addr,
 				   resource_size_t length);
 
 struct dentry *cxl_debugfs_create_dir(const char *dir);
-int cxl_dpa_set_mode(struct cxl_endpoint_decoder *cxled,
-		     enum cxl_decoder_mode mode);
+int cxl_dpa_set_part(struct cxl_endpoint_decoder *cxled,
+		     enum cxl_partition_mode mode);
 int cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, unsigned long long size);
 int cxl_dpa_free(struct cxl_endpoint_decoder *cxled);
 resource_size_t cxl_dpa_size(struct cxl_endpoint_decoder *cxled);
diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c
index 50e6a45b30ba..d705dec1471e 100644
--- a/drivers/cxl/core/hdm.c
+++ b/drivers/cxl/core/hdm.c
@@ -223,6 +223,37 @@ void cxl_dpa_debug(struct seq_file *file, struct cxl_dev_state *cxlds)
 }
 EXPORT_SYMBOL_NS_GPL(cxl_dpa_debug, "CXL");
 
+/* See request_skip() kernel-doc */
+static resource_size_t __adjust_skip(struct cxl_dev_state *cxlds,
+				     const resource_size_t skip_base,
+				     const resource_size_t skip_len,
+				     const char *requester)
+{
+	const resource_size_t skip_end = skip_base + skip_len - 1;
+
+	for (int i = 0; i < cxlds->nr_partitions; i++) {
+		const struct resource *part_res = &cxlds->part[i].res;
+		resource_size_t adjust_start, adjust_end, size;
+
+		adjust_start = max(skip_base, part_res->start);
+		adjust_end = min(skip_end, part_res->end);
+
+		if (adjust_end < adjust_start)
+			continue;
+
+		size = adjust_end - adjust_start + 1;
+
+		if (!requester)
+			__release_region(&cxlds->dpa_res, adjust_start, size);
+		else if (!__request_region(&cxlds->dpa_res, adjust_start, size,
+					   requester, 0))
+			return adjust_start - skip_base;
+	}
+
+	return skip_len;
+}
+#define release_skip(c, b, l) __adjust_skip((c), (b), (l), NULL)
+
 /*
  * Must be called in a context that synchronizes against this decoder's
  * port ->remove() callback (like an endpoint decoder sysfs attribute)
@@ -241,7 +272,7 @@ static void __cxl_dpa_release(struct cxl_endpoint_decoder *cxled)
 	skip_start = res->start - cxled->skip;
 	__release_region(&cxlds->dpa_res, res->start, resource_size(res));
 	if (cxled->skip)
-		__release_region(&cxlds->dpa_res, skip_start, cxled->skip);
+		release_skip(cxlds, skip_start, cxled->skip);
 	cxled->skip = 0;
 	cxled->dpa_res = NULL;
 	put_device(&cxled->cxld.dev);
@@ -268,6 +299,58 @@ static void devm_cxl_dpa_release(struct cxl_endpoint_decoder *cxled)
 	__cxl_dpa_release(cxled);
 }
 
+/**
+ * request_skip() - Track DPA 'skip' in @cxlds->dpa_res resource tree
+ * @cxlds: CXL.mem device context that parents @cxled
+ * @cxled: Endpoint decoder establishing new allocation that skips lower DPA
+ * @skip_base: DPA < start of new DPA allocation (DPAnew)
+ * @skip_len: @skip_base + @skip_len == DPAnew
+ *
+ * DPA 'skip' arises from out-of-sequence DPA allocation events relative
+ * to free capacity across multiple partitions. It is a wasteful event
+ * as usable DPA gets thrown away, but if a deployment has, for example,
+ * a dual RAM+PMEM device, wants to use PMEM, and has unallocated RAM
+ * DPA, the free RAM DPA must be sacrificed to start allocating PMEM.
+ * See third "Implementation Note" in CXL 3.1 8.2.4.19.13 "Decoder
+ * Protection" for more details.
+ *
+ * A 'skip' always covers the last allocated DPA in a previous partition
+ * to the start of the current partition to allocate.  Allocations never
+ * start in the middle of a partition, and allocations are always
+ * de-allocated in reverse order (see cxl_dpa_free(), or natural devm
+ * unwind order from forced in-order allocation).
+ *
+ * If @cxlds->nr_partitions was guaranteed to be <= 2 then the 'skip'
+ * would always be contained to a single partition. Given
+ * @cxlds->nr_partitions may be > 2 it results in cases where the 'skip'
+ * might span "tail capacity of partition[0], all of partition[1], ...,
+ * all of partition[N-1]" to support allocating from partition[N]. That
+ * in turn interacts with the partition 'struct resource' boundaries
+ * within @cxlds->dpa_res whereby 'skip' requests need to be divided by
+ * partition. I.e. this is a quirk of using a 'struct resource' tree to
+ * detect range conflicts while also tracking partition boundaries in
+ * @cxlds->dpa_res.
+ */
+static int request_skip(struct cxl_dev_state *cxlds,
+			struct cxl_endpoint_decoder *cxled,
+			const resource_size_t skip_base,
+			const resource_size_t skip_len)
+{
+	resource_size_t skipped = __adjust_skip(cxlds, skip_base, skip_len,
+						dev_name(&cxled->cxld.dev));
+
+	if (skipped == skip_len)
+		return 0;
+
+	dev_dbg(cxlds->dev,
+		"%s: failed to reserve skipped space (%pa %pa %pa)\n",
+		dev_name(&cxled->cxld.dev), &skip_base, &skip_len, &skipped);
+
+	release_skip(cxlds, skip_base, skipped);
+
+	return -EBUSY;
+}
+
 static int __cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled,
 			     resource_size_t base, resource_size_t len,
 			     resource_size_t skipped)
@@ -277,6 +360,7 @@ static int __cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled,
 	struct cxl_dev_state *cxlds = cxlmd->cxlds;
 	struct device *dev = &port->dev;
 	struct resource *res;
+	int rc;
 
 	lockdep_assert_held_write(&cxl_dpa_rwsem);
 
@@ -305,14 +389,9 @@ static int __cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled,
 	}
 
 	if (skipped) {
-		res = __request_region(&cxlds->dpa_res, base - skipped, skipped,
-				       dev_name(&cxled->cxld.dev), 0);
-		if (!res) {
-			dev_dbg(dev,
-				"decoder%d.%d: failed to reserve skipped space\n",
-				port->id, cxled->cxld.id);
-			return -EBUSY;
-		}
+		rc = request_skip(cxlds, cxled, base - skipped, skipped);
+		if (rc)
+			return rc;
 	}
 	res = __request_region(&cxlds->dpa_res, base, len,
 			       dev_name(&cxled->cxld.dev), 0);
@@ -320,28 +399,117 @@ static int __cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled,
 		dev_dbg(dev, "decoder%d.%d: failed to reserve allocation\n",
 			port->id, cxled->cxld.id);
 		if (skipped)
-			__release_region(&cxlds->dpa_res, base - skipped,
-					 skipped);
+			release_skip(cxlds, base - skipped, skipped);
 		return -EBUSY;
 	}
 	cxled->dpa_res = res;
 	cxled->skip = skipped;
 
-	if (resource_contains(&cxlds->pmem_res, res))
-		cxled->mode = CXL_DECODER_PMEM;
-	else if (resource_contains(&cxlds->ram_res, res))
-		cxled->mode = CXL_DECODER_RAM;
-	else {
-		dev_warn(dev, "decoder%d.%d: %pr mixed mode not supported\n",
-			 port->id, cxled->cxld.id, cxled->dpa_res);
-		cxled->mode = CXL_DECODER_MIXED;
-	}
+	/*
+	 * When allocating new capacity, ->part is already set, when
+	 * discovering decoder settings at initial enumeration, ->part
+	 * is not set.
+	 */
+	if (cxled->part < 0)
+		for (int i = 0; cxlds->nr_partitions; i++)
+			if (resource_contains(&cxlds->part[i].res, res)) {
+				cxled->part = i;
+				break;
+			}
+
+	if (cxled->part < 0)
+		dev_warn(dev, "decoder%d.%d: %pr does not map any partition\n",
+			 port->id, cxled->cxld.id, res);
 
 	port->hdm_end++;
 	get_device(&cxled->cxld.dev);
 	return 0;
 }
 
+static int add_dpa_res(struct device *dev, struct resource *parent,
+		       struct resource *res, resource_size_t start,
+		       resource_size_t size, const char *type)
+{
+	int rc;
+
+	*res = (struct resource) {
+		.name = type,
+		.start = start,
+		.end =  start + size - 1,
+		.flags = IORESOURCE_MEM,
+	};
+	if (resource_size(res) == 0) {
+		dev_dbg(dev, "DPA(%s): no capacity\n", res->name);
+		return 0;
+	}
+	rc = request_resource(parent, res);
+	if (rc) {
+		dev_err(dev, "DPA(%s): failed to track %pr (%d)\n", res->name,
+			res, rc);
+		return rc;
+	}
+
+	dev_dbg(dev, "DPA(%s): %pr\n", res->name, res);
+
+	return 0;
+}
+
+static const char *cxl_mode_name(enum cxl_partition_mode mode)
+{
+	switch (mode) {
+	case CXL_PARTMODE_RAM:
+		return "ram";
+	case CXL_PARTMODE_PMEM:
+		return "pmem";
+	default:
+		return "";
+	};
+}
+
+/* if this fails the caller must destroy @cxlds, there is no recovery */
+int cxl_dpa_setup(struct cxl_dev_state *cxlds, const struct cxl_dpa_info *info)
+{
+	struct device *dev = cxlds->dev;
+
+	guard(rwsem_write)(&cxl_dpa_rwsem);
+
+	if (cxlds->nr_partitions)
+		return -EBUSY;
+
+	if (!info->size || !info->nr_partitions) {
+		cxlds->dpa_res = DEFINE_RES_MEM(0, 0);
+		cxlds->nr_partitions = 0;
+		return 0;
+	}
+
+	cxlds->dpa_res = DEFINE_RES_MEM(0, info->size);
+
+	for (int i = 0; i < info->nr_partitions; i++) {
+		const struct cxl_dpa_part_info *part = &info->part[i];
+		int rc;
+
+		cxlds->part[i].perf.qos_class = CXL_QOS_CLASS_INVALID;
+		cxlds->part[i].mode = part->mode;
+
+		/* Require ordered + contiguous partitions */
+		if (i) {
+			const struct cxl_dpa_part_info *prev = &info->part[i - 1];
+
+			if (prev->range.end + 1 != part->range.start)
+				return -EINVAL;
+		}
+		rc = add_dpa_res(dev, &cxlds->dpa_res, &cxlds->part[i].res,
+				 part->range.start, range_len(&part->range),
+				 cxl_mode_name(part->mode));
+		if (rc)
+			return rc;
+		cxlds->nr_partitions++;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cxl_dpa_setup);
+
 int devm_cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled,
 				resource_size_t base, resource_size_t len,
 				resource_size_t skipped)
@@ -418,53 +586,46 @@ out:
 	return rc;
 }
 
-int cxl_dpa_set_mode(struct cxl_endpoint_decoder *cxled,
-		     enum cxl_decoder_mode mode)
+int cxl_dpa_set_part(struct cxl_endpoint_decoder *cxled,
+		     enum cxl_partition_mode mode)
 {
 	struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
 	struct cxl_dev_state *cxlds = cxlmd->cxlds;
 	struct device *dev = &cxled->cxld.dev;
-
-	switch (mode) {
-	case CXL_DECODER_RAM:
-	case CXL_DECODER_PMEM:
-		break;
-	default:
-		dev_dbg(dev, "unsupported mode: %d\n", mode);
-		return -EINVAL;
-	}
+	int part;
 
 	guard(rwsem_write)(&cxl_dpa_rwsem);
 	if (cxled->cxld.flags & CXL_DECODER_F_ENABLE)
 		return -EBUSY;
 
-	/*
-	 * Only allow modes that are supported by the current partition
-	 * configuration
-	 */
-	if (mode == CXL_DECODER_PMEM && !resource_size(&cxlds->pmem_res)) {
-		dev_dbg(dev, "no available pmem capacity\n");
-		return -ENXIO;
+	for (part = 0; part < cxlds->nr_partitions; part++)
+		if (cxlds->part[part].mode == mode)
+			break;
+
+	if (part >= cxlds->nr_partitions) {
+		dev_dbg(dev, "unsupported mode: %d\n", mode);
+		return -EINVAL;
 	}
-	if (mode == CXL_DECODER_RAM && !resource_size(&cxlds->ram_res)) {
-		dev_dbg(dev, "no available ram capacity\n");
+
+	if (!resource_size(&cxlds->part[part].res)) {
+		dev_dbg(dev, "no available capacity for mode: %d\n", mode);
 		return -ENXIO;
 	}
 
-	cxled->mode = mode;
+	cxled->part = part;
 	return 0;
 }
 
 int cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, unsigned long long size)
 {
 	struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
-	resource_size_t free_ram_start, free_pmem_start;
 	struct cxl_port *port = cxled_to_port(cxled);
 	struct cxl_dev_state *cxlds = cxlmd->cxlds;
 	struct device *dev = &cxled->cxld.dev;
-	resource_size_t start, avail, skip;
+	struct resource *res, *prev = NULL;
+	resource_size_t start, avail, skip, skip_start;
 	struct resource *p, *last;
-	int rc;
+	int part, rc;
 
 	down_write(&cxl_dpa_rwsem);
 	if (cxled->cxld.region) {
@@ -480,50 +641,50 @@ int cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, unsigned long long size)
 		goto out;
 	}
 
-	for (p = cxlds->ram_res.child, last = NULL; p; p = p->sibling)
-		last = p;
-	if (last)
-		free_ram_start = last->end + 1;
-	else
-		free_ram_start = cxlds->ram_res.start;
+	part = cxled->part;
+	if (part < 0) {
+		dev_dbg(dev, "partition not set\n");
+		rc = -EBUSY;
+		goto out;
+	}
 
-	for (p = cxlds->pmem_res.child, last = NULL; p; p = p->sibling)
+	res = &cxlds->part[part].res;
+	for (p = res->child, last = NULL; p; p = p->sibling)
 		last = p;
 	if (last)
-		free_pmem_start = last->end + 1;
+		start = last->end + 1;
 	else
-		free_pmem_start = cxlds->pmem_res.start;
-
-	if (cxled->mode == CXL_DECODER_RAM) {
-		start = free_ram_start;
-		avail = cxlds->ram_res.end - start + 1;
-		skip = 0;
-	} else if (cxled->mode == CXL_DECODER_PMEM) {
-		resource_size_t skip_start, skip_end;
-
-		start = free_pmem_start;
-		avail = cxlds->pmem_res.end - start + 1;
-		skip_start = free_ram_start;
+		start = res->start;
 
-		/*
-		 * If some pmem is already allocated, then that allocation
-		 * already handled the skip.
-		 */
-		if (cxlds->pmem_res.child &&
-		    skip_start == cxlds->pmem_res.child->start)
-			skip_end = skip_start - 1;
-		else
-			skip_end = start - 1;
-		skip = skip_end - skip_start + 1;
-	} else {
-		dev_dbg(dev, "mode not set\n");
-		rc = -EINVAL;
-		goto out;
+	/*
+	 * To allocate at partition N, a skip needs to be calculated for all
+	 * unallocated space at lower partitions indices.
+	 *
+	 * If a partition has any allocations, the search can end because a
+	 * previous cxl_dpa_alloc() invocation is assumed to have accounted for
+	 * all previous partitions.
+	 */
+	skip_start = CXL_RESOURCE_NONE;
+	for (int i = part; i; i--) {
+		prev = &cxlds->part[i - 1].res;
+		for (p = prev->child, last = NULL; p; p = p->sibling)
+			last = p;
+		if (last) {
+			skip_start = last->end + 1;
+			break;
+		}
+		skip_start = prev->start;
 	}
 
+	avail = res->end - start + 1;
+	if (skip_start == CXL_RESOURCE_NONE)
+		skip = 0;
+	else
+		skip = res->start - skip_start;
+
 	if (size > avail) {
 		dev_dbg(dev, "%pa exceeds available %s capacity: %pa\n", &size,
-			cxl_decoder_mode_name(cxled->mode), &avail);
+			res->name, &avail);
 		rc = -ENOSPC;
 		goto out;
 	}
diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index 548564c770c0..62bb3653362f 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -1241,55 +1241,39 @@ int cxl_mem_sanitize(struct cxl_memdev *cxlmd, u16 cmd)
 	return rc;
 }
 
-static int add_dpa_res(struct device *dev, struct resource *parent,
-		       struct resource *res, resource_size_t start,
-		       resource_size_t size, const char *type)
+static void add_part(struct cxl_dpa_info *info, u64 start, u64 size, enum cxl_partition_mode mode)
 {
-	int rc;
+	int i = info->nr_partitions;
 
-	res->name = type;
-	res->start = start;
-	res->end = start + size - 1;
-	res->flags = IORESOURCE_MEM;
-	if (resource_size(res) == 0) {
-		dev_dbg(dev, "DPA(%s): no capacity\n", res->name);
-		return 0;
-	}
-	rc = request_resource(parent, res);
-	if (rc) {
-		dev_err(dev, "DPA(%s): failed to track %pr (%d)\n", res->name,
-			res, rc);
-		return rc;
-	}
-
-	dev_dbg(dev, "DPA(%s): %pr\n", res->name, res);
+	if (size == 0)
+		return;
 
-	return 0;
+	info->part[i].range = (struct range) {
+		.start = start,
+		.end = start + size - 1,
+	};
+	info->part[i].mode = mode;
+	info->nr_partitions++;
 }
 
-int cxl_mem_create_range_info(struct cxl_memdev_state *mds)
+int cxl_mem_dpa_fetch(struct cxl_memdev_state *mds, struct cxl_dpa_info *info)
 {
 	struct cxl_dev_state *cxlds = &mds->cxlds;
 	struct device *dev = cxlds->dev;
 	int rc;
 
 	if (!cxlds->media_ready) {
-		cxlds->dpa_res = DEFINE_RES_MEM(0, 0);
-		cxlds->ram_res = DEFINE_RES_MEM(0, 0);
-		cxlds->pmem_res = DEFINE_RES_MEM(0, 0);
+		info->size = 0;
 		return 0;
 	}
 
-	cxlds->dpa_res = DEFINE_RES_MEM(0, mds->total_bytes);
+	info->size = mds->total_bytes;
 
 	if (mds->partition_align_bytes == 0) {
-		rc = add_dpa_res(dev, &cxlds->dpa_res, &cxlds->ram_res, 0,
-				 mds->volatile_only_bytes, "ram");
-		if (rc)
-			return rc;
-		return add_dpa_res(dev, &cxlds->dpa_res, &cxlds->pmem_res,
-				   mds->volatile_only_bytes,
-				   mds->persistent_only_bytes, "pmem");
+		add_part(info, 0, mds->volatile_only_bytes, CXL_PARTMODE_RAM);
+		add_part(info, mds->volatile_only_bytes,
+			 mds->persistent_only_bytes, CXL_PARTMODE_PMEM);
+		return 0;
 	}
 
 	rc = cxl_mem_get_partition_info(mds);
@@ -1298,15 +1282,13 @@ int cxl_mem_create_range_info(struct cxl_memdev_state *mds)
 		return rc;
 	}
 
-	rc = add_dpa_res(dev, &cxlds->dpa_res, &cxlds->ram_res, 0,
-			 mds->active_volatile_bytes, "ram");
-	if (rc)
-		return rc;
-	return add_dpa_res(dev, &cxlds->dpa_res, &cxlds->pmem_res,
-			   mds->active_volatile_bytes,
-			   mds->active_persistent_bytes, "pmem");
+	add_part(info, 0, mds->active_volatile_bytes, CXL_PARTMODE_RAM);
+	add_part(info, mds->active_volatile_bytes, mds->active_persistent_bytes,
+		 CXL_PARTMODE_PMEM);
+
+	return 0;
 }
-EXPORT_SYMBOL_NS_GPL(cxl_mem_create_range_info, "CXL");
+EXPORT_SYMBOL_NS_GPL(cxl_mem_dpa_fetch, "CXL");
 
 int cxl_set_timestamp(struct cxl_memdev_state *mds)
 {
@@ -1450,8 +1432,6 @@ 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;
-	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 ae3dfcbe8938..63c6c681125d 100644
--- a/drivers/cxl/core/memdev.c
+++ b/drivers/cxl/core/memdev.c
@@ -75,12 +75,20 @@ static ssize_t label_storage_size_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(label_storage_size);
 
+static resource_size_t cxl_ram_size(struct cxl_dev_state *cxlds)
+{
+	/* Static RAM is only expected at partition 0. */
+	if (cxlds->part[0].mode != CXL_PARTMODE_RAM)
+		return 0;
+	return resource_size(&cxlds->part[0].res);
+}
+
 static ssize_t ram_size_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;
-	unsigned long long len = resource_size(&cxlds->ram_res);
+	unsigned long long len = cxl_ram_size(cxlds);
 
 	return sysfs_emit(buf, "%#llx\n", len);
 }
@@ -93,7 +101,7 @@ static ssize_t pmem_size_show(struct device *dev, struct device_attribute *attr,
 {
 	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
 	struct cxl_dev_state *cxlds = cxlmd->cxlds;
-	unsigned long long len = resource_size(&cxlds->pmem_res);
+	unsigned long long len = cxl_pmem_size(cxlds);
 
 	return sysfs_emit(buf, "%#llx\n", len);
 }
@@ -198,22 +206,17 @@ static int cxl_get_poison_by_memdev(struct cxl_memdev *cxlmd)
 	int rc = 0;
 
 	/* CXL 3.0 Spec 8.2.9.8.4.1 Separate pmem and ram poison requests */
-	if (resource_size(&cxlds->pmem_res)) {
-		offset = cxlds->pmem_res.start;
-		length = resource_size(&cxlds->pmem_res);
-		rc = cxl_mem_get_poison(cxlmd, offset, length, NULL);
-		if (rc)
-			return rc;
-	}
-	if (resource_size(&cxlds->ram_res)) {
-		offset = cxlds->ram_res.start;
-		length = resource_size(&cxlds->ram_res);
+	for (int i = 0; i < cxlds->nr_partitions; i++) {
+		const struct resource *res = &cxlds->part[i].res;
+
+		offset = res->start;
+		length = resource_size(res);
 		rc = cxl_mem_get_poison(cxlmd, offset, length, NULL);
 		/*
 		 * Invalid Physical Address is not an error for
 		 * volatile addresses. Device support is optional.
 		 */
-		if (rc == -EFAULT)
+		if (rc == -EFAULT && cxlds->part[i].mode == CXL_PARTMODE_RAM)
 			rc = 0;
 	}
 	return rc;
@@ -404,14 +407,21 @@ static struct attribute *cxl_memdev_attributes[] = {
 	NULL,
 };
 
+static struct cxl_dpa_perf *to_pmem_perf(struct cxl_dev_state *cxlds)
+{
+	for (int i = 0; i < cxlds->nr_partitions; i++)
+		if (cxlds->part[i].mode == CXL_PARTMODE_PMEM)
+			return &cxlds->part[i].perf;
+	return 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);
+	return sysfs_emit(buf, "%d\n", to_pmem_perf(cxlds)->qos_class);
 }
 
 static struct device_attribute dev_attr_pmem_qos_class =
@@ -423,14 +433,20 @@ static struct attribute *cxl_memdev_pmem_attributes[] = {
 	NULL,
 };
 
+static struct cxl_dpa_perf *to_ram_perf(struct cxl_dev_state *cxlds)
+{
+	if (cxlds->part[0].mode != CXL_PARTMODE_RAM)
+		return NULL;
+	return &cxlds->part[0].perf;
+}
+
 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);
+	return sysfs_emit(buf, "%d\n", to_ram_perf(cxlds)->qos_class);
 }
 
 static struct device_attribute dev_attr_ram_qos_class =
@@ -466,11 +482,11 @@ 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);
+	struct cxl_dpa_perf *perf = to_ram_perf(cxlmd->cxlds);
 
-	if (a == &dev_attr_ram_qos_class.attr)
-		if (mds->ram_perf.qos_class == CXL_QOS_CLASS_INVALID)
-			return 0;
+	if (a == &dev_attr_ram_qos_class.attr &&
+	    (!perf || perf->qos_class == CXL_QOS_CLASS_INVALID))
+		return 0;
 
 	return a->mode;
 }
@@ -485,11 +501,11 @@ 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);
+	struct cxl_dpa_perf *perf = to_pmem_perf(cxlmd->cxlds);
 
-	if (a == &dev_attr_pmem_qos_class.attr)
-		if (mds->pmem_perf.qos_class == CXL_QOS_CLASS_INVALID)
-			return 0;
+	if (a == &dev_attr_pmem_qos_class.attr &&
+	    (!perf || perf->qos_class == CXL_QOS_CLASS_INVALID))
+		return 0;
 
 	return a->mode;
 }
diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index 7ed6e8f374af..194892bb1396 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -194,25 +194,35 @@ static ssize_t mode_show(struct device *dev, struct device_attribute *attr,
 			 char *buf)
 {
 	struct cxl_endpoint_decoder *cxled = to_cxl_endpoint_decoder(dev);
+	struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	/* without @cxl_dpa_rwsem, make sure @part is not reloaded */
+	int part = READ_ONCE(cxled->part);
+	const char *desc;
+
+	if (part < 0)
+		desc = "none";
+	else
+		desc = cxlds->part[part].res.name;
 
-	return sysfs_emit(buf, "%s\n", cxl_decoder_mode_name(cxled->mode));
+	return sysfs_emit(buf, "%s\n", desc);
 }
 
 static ssize_t mode_store(struct device *dev, struct device_attribute *attr,
 			  const char *buf, size_t len)
 {
 	struct cxl_endpoint_decoder *cxled = to_cxl_endpoint_decoder(dev);
-	enum cxl_decoder_mode mode;
+	enum cxl_partition_mode mode;
 	ssize_t rc;
 
 	if (sysfs_streq(buf, "pmem"))
-		mode = CXL_DECODER_PMEM;
+		mode = CXL_PARTMODE_PMEM;
 	else if (sysfs_streq(buf, "ram"))
-		mode = CXL_DECODER_RAM;
+		mode = CXL_PARTMODE_RAM;
 	else
 		return -EINVAL;
 
-	rc = cxl_dpa_set_mode(cxled, mode);
+	rc = cxl_dpa_set_part(cxled, mode);
 	if (rc)
 		return rc;
 
@@ -1899,6 +1909,7 @@ struct cxl_endpoint_decoder *cxl_endpoint_decoder_alloc(struct cxl_port *port)
 		return ERR_PTR(-ENOMEM);
 
 	cxled->pos = -1;
+	cxled->part = -1;
 	cxld = &cxled->cxld;
 	rc = cxl_decoder_init(port, cxld);
 	if (rc)	 {
diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index e8d11a988fd9..84ce625b8591 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -144,7 +144,7 @@ static ssize_t uuid_show(struct device *dev, struct device_attribute *attr,
 	rc = down_read_interruptible(&cxl_region_rwsem);
 	if (rc)
 		return rc;
-	if (cxlr->mode != CXL_DECODER_PMEM)
+	if (cxlr->mode != CXL_PARTMODE_PMEM)
 		rc = sysfs_emit(buf, "\n");
 	else
 		rc = sysfs_emit(buf, "%pUb\n", &p->uuid);
@@ -441,7 +441,7 @@ static umode_t cxl_region_visible(struct kobject *kobj, struct attribute *a,
 	 * Support tooling that expects to find a 'uuid' attribute for all
 	 * regions regardless of mode.
 	 */
-	if (a == &dev_attr_uuid.attr && cxlr->mode != CXL_DECODER_PMEM)
+	if (a == &dev_attr_uuid.attr && cxlr->mode != CXL_PARTMODE_PMEM)
 		return 0444;
 	return a->mode;
 }
@@ -603,8 +603,16 @@ static ssize_t mode_show(struct device *dev, struct device_attribute *attr,
 			 char *buf)
 {
 	struct cxl_region *cxlr = to_cxl_region(dev);
+	const char *desc;
 
-	return sysfs_emit(buf, "%s\n", cxl_decoder_mode_name(cxlr->mode));
+	if (cxlr->mode == CXL_PARTMODE_RAM)
+		desc = "ram";
+	else if (cxlr->mode == CXL_PARTMODE_PMEM)
+		desc = "pmem";
+	else
+		desc = "";
+
+	return sysfs_emit(buf, "%s\n", desc);
 }
 static DEVICE_ATTR_RO(mode);
 
@@ -630,7 +638,7 @@ static int alloc_hpa(struct cxl_region *cxlr, resource_size_t size)
 
 	/* ways, granularity and uuid (if PMEM) need to be set before HPA */
 	if (!p->interleave_ways || !p->interleave_granularity ||
-	    (cxlr->mode == CXL_DECODER_PMEM && uuid_is_null(&p->uuid)))
+	    (cxlr->mode == CXL_PARTMODE_PMEM && uuid_is_null(&p->uuid)))
 		return -ENXIO;
 
 	div64_u64_rem(size, (u64)SZ_256M * p->interleave_ways, &remainder);
@@ -1888,6 +1896,7 @@ static int cxl_region_attach(struct cxl_region *cxlr,
 {
 	struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(cxlr->dev.parent);
 	struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
 	struct cxl_region_params *p = &cxlr->params;
 	struct cxl_port *ep_port, *root_port;
 	struct cxl_dport *dport;
@@ -1902,17 +1911,17 @@ static int cxl_region_attach(struct cxl_region *cxlr,
 		return rc;
 	}
 
-	if (cxled->mode != cxlr->mode) {
-		dev_dbg(&cxlr->dev, "%s region mode: %d mismatch: %d\n",
-			dev_name(&cxled->cxld.dev), cxlr->mode, cxled->mode);
-		return -EINVAL;
-	}
-
-	if (cxled->mode == CXL_DECODER_DEAD) {
+	if (cxled->part < 0) {
 		dev_dbg(&cxlr->dev, "%s dead\n", dev_name(&cxled->cxld.dev));
 		return -ENODEV;
 	}
 
+	if (cxlds->part[cxled->part].mode != cxlr->mode) {
+		dev_dbg(&cxlr->dev, "%s region mode: %d mismatch\n",
+			dev_name(&cxled->cxld.dev), cxlr->mode);
+		return -EINVAL;
+	}
+
 	/* all full of members, or interleave config not established? */
 	if (p->state > CXL_CONFIG_INTERLEAVE_ACTIVE) {
 		dev_dbg(&cxlr->dev, "region already active\n");
@@ -2115,7 +2124,7 @@ out:
 void cxl_decoder_kill_region(struct cxl_endpoint_decoder *cxled)
 {
 	down_write(&cxl_region_rwsem);
-	cxled->mode = CXL_DECODER_DEAD;
+	cxled->part = -1;
 	cxl_region_detach(cxled);
 	up_write(&cxl_region_rwsem);
 }
@@ -2471,7 +2480,7 @@ static int cxl_region_calculate_adistance(struct notifier_block *nb,
  */
 static struct cxl_region *devm_cxl_add_region(struct cxl_root_decoder *cxlrd,
 					      int id,
-					      enum cxl_decoder_mode mode,
+					      enum cxl_partition_mode mode,
 					      enum cxl_decoder_type type)
 {
 	struct cxl_port *port = to_cxl_port(cxlrd->cxlsd.cxld.dev.parent);
@@ -2525,13 +2534,13 @@ static ssize_t create_ram_region_show(struct device *dev,
 }
 
 static struct cxl_region *__create_region(struct cxl_root_decoder *cxlrd,
-					  enum cxl_decoder_mode mode, int id)
+					  enum cxl_partition_mode mode, int id)
 {
 	int rc;
 
 	switch (mode) {
-	case CXL_DECODER_RAM:
-	case CXL_DECODER_PMEM:
+	case CXL_PARTMODE_RAM:
+	case CXL_PARTMODE_PMEM:
 		break;
 	default:
 		dev_err(&cxlrd->cxlsd.cxld.dev, "unsupported mode %d\n", mode);
@@ -2551,7 +2560,7 @@ static struct cxl_region *__create_region(struct cxl_root_decoder *cxlrd,
 }
 
 static ssize_t create_region_store(struct device *dev, const char *buf,
-				   size_t len, enum cxl_decoder_mode mode)
+				   size_t len, enum cxl_partition_mode mode)
 {
 	struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(dev);
 	struct cxl_region *cxlr;
@@ -2572,7 +2581,7 @@ static ssize_t create_pmem_region_store(struct device *dev,
 					struct device_attribute *attr,
 					const char *buf, size_t len)
 {
-	return create_region_store(dev, buf, len, CXL_DECODER_PMEM);
+	return create_region_store(dev, buf, len, CXL_PARTMODE_PMEM);
 }
 DEVICE_ATTR_RW(create_pmem_region);
 
@@ -2580,7 +2589,7 @@ static ssize_t create_ram_region_store(struct device *dev,
 				       struct device_attribute *attr,
 				       const char *buf, size_t len)
 {
-	return create_region_store(dev, buf, len, CXL_DECODER_RAM);
+	return create_region_store(dev, buf, len, CXL_PARTMODE_RAM);
 }
 DEVICE_ATTR_RW(create_ram_region);
 
@@ -2678,7 +2687,7 @@ EXPORT_SYMBOL_NS_GPL(to_cxl_pmem_region, "CXL");
 
 struct cxl_poison_context {
 	struct cxl_port *port;
-	enum cxl_decoder_mode mode;
+	int part;
 	u64 offset;
 };
 
@@ -2686,47 +2695,45 @@ static int cxl_get_poison_unmapped(struct cxl_memdev *cxlmd,
 				   struct cxl_poison_context *ctx)
 {
 	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	const struct resource *res;
+	struct resource *p, *last;
 	u64 offset, length;
 	int rc = 0;
 
+	if (ctx->part < 0)
+		return 0;
+
 	/*
-	 * Collect poison for the remaining unmapped resources
-	 * after poison is collected by committed endpoints.
-	 *
-	 * Knowing that PMEM must always follow RAM, get poison
-	 * for unmapped resources based on the last decoder's mode:
-	 *	ram: scan remains of ram range, then any pmem range
-	 *	pmem: scan remains of pmem range
+	 * Collect poison for the remaining unmapped resources after
+	 * poison is collected by committed endpoints decoders.
 	 */
-
-	if (ctx->mode == CXL_DECODER_RAM) {
-		offset = ctx->offset;
-		length = resource_size(&cxlds->ram_res) - offset;
+	for (int i = ctx->part; i < cxlds->nr_partitions; i++) {
+		res = &cxlds->part[i].res;
+		for (p = res->child, last = NULL; p; p = p->sibling)
+			last = p;
+		if (last)
+			offset = last->end + 1;
+		else
+			offset = res->start;
+		length = res->end - offset + 1;
+		if (!length)
+			break;
 		rc = cxl_mem_get_poison(cxlmd, offset, length, NULL);
-		if (rc == -EFAULT)
-			rc = 0;
+		if (rc == -EFAULT && cxlds->part[i].mode == CXL_PARTMODE_RAM)
+			continue;
 		if (rc)
-			return rc;
-	}
-	if (ctx->mode == CXL_DECODER_PMEM) {
-		offset = ctx->offset;
-		length = resource_size(&cxlds->dpa_res) - offset;
-		if (!length)
-			return 0;
-	} else if (resource_size(&cxlds->pmem_res)) {
-		offset = cxlds->pmem_res.start;
-		length = resource_size(&cxlds->pmem_res);
-	} else {
-		return 0;
+			break;
 	}
 
-	return cxl_mem_get_poison(cxlmd, offset, length, NULL);
+	return rc;
 }
 
 static int poison_by_decoder(struct device *dev, void *arg)
 {
 	struct cxl_poison_context *ctx = arg;
 	struct cxl_endpoint_decoder *cxled;
+	enum cxl_partition_mode mode;
+	struct cxl_dev_state *cxlds;
 	struct cxl_memdev *cxlmd;
 	u64 offset, length;
 	int rc = 0;
@@ -2735,27 +2742,18 @@ static int poison_by_decoder(struct device *dev, void *arg)
 		return rc;
 
 	cxled = to_cxl_endpoint_decoder(dev);
-	if (!cxled->dpa_res || !resource_size(cxled->dpa_res))
-		return rc;
-
-	/*
-	 * Regions are only created with single mode decoders: pmem or ram.
-	 * Linux does not support mixed mode decoders. This means that
-	 * reading poison per endpoint decoder adheres to the requirement
-	 * that poison reads of pmem and ram must be separated.
-	 * CXL 3.0 Spec 8.2.9.8.4.1
-	 */
-	if (cxled->mode == CXL_DECODER_MIXED) {
-		dev_dbg(dev, "poison list read unsupported in mixed mode\n");
+	if (!cxled->dpa_res)
 		return rc;
-	}
 
 	cxlmd = cxled_to_memdev(cxled);
+	cxlds = cxlmd->cxlds;
+	mode = cxlds->part[cxled->part].mode;
+
 	if (cxled->skip) {
 		offset = cxled->dpa_res->start - cxled->skip;
 		length = cxled->skip;
 		rc = cxl_mem_get_poison(cxlmd, offset, length, NULL);
-		if (rc == -EFAULT && cxled->mode == CXL_DECODER_RAM)
+		if (rc == -EFAULT && mode == CXL_PARTMODE_RAM)
 			rc = 0;
 		if (rc)
 			return rc;
@@ -2764,7 +2762,7 @@ static int poison_by_decoder(struct device *dev, void *arg)
 	offset = cxled->dpa_res->start;
 	length = cxled->dpa_res->end - offset + 1;
 	rc = cxl_mem_get_poison(cxlmd, offset, length, cxled->cxld.region);
-	if (rc == -EFAULT && cxled->mode == CXL_DECODER_RAM)
+	if (rc == -EFAULT && mode == CXL_PARTMODE_RAM)
 		rc = 0;
 	if (rc)
 		return rc;
@@ -2772,7 +2770,7 @@ static int poison_by_decoder(struct device *dev, void *arg)
 	/* Iterate until commit_end is reached */
 	if (cxled->cxld.id == ctx->port->commit_end) {
 		ctx->offset = cxled->dpa_res->end + 1;
-		ctx->mode = cxled->mode;
+		ctx->part = cxled->part;
 		return 1;
 	}
 
@@ -2785,7 +2783,8 @@ int cxl_get_poison_by_endpoint(struct cxl_port *port)
 	int rc = 0;
 
 	ctx = (struct cxl_poison_context) {
-		.port = port
+		.port = port,
+		.part = -1,
 	};
 
 	rc = device_for_each_child(&port->dev, &ctx, poison_by_decoder);
@@ -3230,14 +3229,18 @@ static struct cxl_region *construct_region(struct cxl_root_decoder *cxlrd,
 {
 	struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
 	struct cxl_port *port = cxlrd_to_port(cxlrd);
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
 	struct range *hpa = &cxled->cxld.hpa_range;
+	int rc, part = READ_ONCE(cxled->part);
 	struct cxl_region_params *p;
 	struct cxl_region *cxlr;
 	struct resource *res;
-	int rc;
+
+	if (part < 0)
+		return ERR_PTR(-EBUSY);
 
 	do {
-		cxlr = __create_region(cxlrd, cxled->mode,
+		cxlr = __create_region(cxlrd, cxlds->part[part].mode,
 				       atomic_read(&cxlrd->region_id));
 	} while (IS_ERR(cxlr) && PTR_ERR(cxlr) == -EBUSY);
 
@@ -3440,9 +3443,9 @@ out:
 		return rc;
 
 	switch (cxlr->mode) {
-	case CXL_DECODER_PMEM:
+	case CXL_PARTMODE_PMEM:
 		return devm_cxl_add_pmem_region(cxlr);
-	case CXL_DECODER_RAM:
+	case CXL_PARTMODE_RAM:
 		/*
 		 * The region can not be manged by CXL if any portion of
 		 * it is already online as 'System RAM'
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index bbbaa0d0a670..94a34833eedd 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -373,32 +373,6 @@ struct cxl_decoder {
 };
 
 /*
- * CXL_DECODER_DEAD prevents endpoints from being reattached to regions
- * while cxld_unregister() is running
- */
-enum cxl_decoder_mode {
-	CXL_DECODER_NONE,
-	CXL_DECODER_RAM,
-	CXL_DECODER_PMEM,
-	CXL_DECODER_MIXED,
-	CXL_DECODER_DEAD,
-};
-
-static inline const char *cxl_decoder_mode_name(enum cxl_decoder_mode mode)
-{
-	static const char * const names[] = {
-		[CXL_DECODER_NONE] = "none",
-		[CXL_DECODER_RAM] = "ram",
-		[CXL_DECODER_PMEM] = "pmem",
-		[CXL_DECODER_MIXED] = "mixed",
-	};
-
-	if (mode >= CXL_DECODER_NONE && mode <= CXL_DECODER_MIXED)
-		return names[mode];
-	return "mixed";
-}
-
-/*
  * Track whether this decoder is reserved for region autodiscovery, or
  * free for userspace provisioning.
  */
@@ -412,16 +386,16 @@ enum cxl_decoder_state {
  * @cxld: base cxl_decoder_object
  * @dpa_res: actively claimed DPA span of this decoder
  * @skip: offset into @dpa_res where @cxld.hpa_range maps
- * @mode: which memory type / access-mode-partition this decoder targets
  * @state: autodiscovery state
+ * @part: partition index this decoder maps
  * @pos: interleave position in @cxld.region
  */
 struct cxl_endpoint_decoder {
 	struct cxl_decoder cxld;
 	struct resource *dpa_res;
 	resource_size_t skip;
-	enum cxl_decoder_mode mode;
 	enum cxl_decoder_state state;
+	int part;
 	int pos;
 };
 
@@ -506,6 +480,11 @@ struct cxl_region_params {
 	int nr_targets;
 };
 
+enum cxl_partition_mode {
+	CXL_PARTMODE_RAM,
+	CXL_PARTMODE_PMEM,
+};
+
 /*
  * Indicate whether this region has been assembled by autodetection or
  * userspace assembly. Prevent endpoint decoders outside of automatic
@@ -525,7 +504,7 @@ struct cxl_region_params {
  * struct cxl_region - CXL region
  * @dev: This region's device
  * @id: This region's id. Id is globally unique across all regions
- * @mode: Endpoint decoder allocation / access mode
+ * @mode: Operational mode of the mapped capacity
  * @type: Endpoint decoder target type
  * @cxl_nvb: nvdimm bridge for coordinating @cxlr_pmem setup / shutdown
  * @cxlr_pmem: (for pmem regions) cached copy of the nvdimm bridge
@@ -538,7 +517,7 @@ struct cxl_region_params {
 struct cxl_region {
 	struct device dev;
 	int id;
-	enum cxl_decoder_mode mode;
+	enum cxl_partition_mode mode;
 	enum cxl_decoder_type type;
 	struct cxl_nvdimm_bridge *cxl_nvb;
 	struct cxl_pmem_region *cxlr_pmem;
diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
index 2a25d1957ddb..36a091597066 100644
--- a/drivers/cxl/cxlmem.h
+++ b/drivers/cxl/cxlmem.h
@@ -97,6 +97,19 @@ int devm_cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled,
 			 resource_size_t base, resource_size_t len,
 			 resource_size_t skipped);
 
+#define CXL_NR_PARTITIONS_MAX 2
+
+struct cxl_dpa_info {
+	u64 size;
+	struct cxl_dpa_part_info {
+		struct range range;
+		enum cxl_partition_mode mode;
+	} part[CXL_NR_PARTITIONS_MAX];
+	int nr_partitions;
+};
+
+int cxl_dpa_setup(struct cxl_dev_state *cxlds, const struct cxl_dpa_info *info);
+
 static inline struct cxl_ep *cxl_ep_load(struct cxl_port *port,
 					 struct cxl_memdev *cxlmd)
 {
@@ -409,6 +422,18 @@ struct cxl_dpa_perf {
 };
 
 /**
+ * struct cxl_dpa_partition - DPA partition descriptor
+ * @res: shortcut to the partition in the DPA resource tree (cxlds->dpa_res)
+ * @perf: performance attributes of the partition from CDAT
+ * @mode: operation mode for the DPA capacity, e.g. ram, pmem, dynamic...
+ */
+struct cxl_dpa_partition {
+	struct resource res;
+	struct cxl_dpa_perf perf;
+	enum cxl_partition_mode mode;
+};
+
+/**
  * struct cxl_dev_state - The driver device state
  *
  * cxl_dev_state represents the CXL driver/device state.  It provides an
@@ -423,8 +448,8 @@ struct cxl_dpa_perf {
  * @rcd: operating in RCD mode (CXL 3.0 9.11.8 CXL Devices Attached to an RCH)
  * @media_ready: Indicate whether the device media is usable
  * @dpa_res: Overall DPA resource tree for the device
- * @pmem_res: Active Persistent memory capacity configuration
- * @ram_res: Active Volatile memory capacity configuration
+ * @part: DPA partition array
+ * @nr_partitions: Number of DPA partitions
  * @serial: PCIe Device Serial Number
  * @type: Generic Memory Class device or Vendor Specific Memory device
  * @cxl_mbox: CXL mailbox context
@@ -438,13 +463,25 @@ struct cxl_dev_state {
 	bool rcd;
 	bool media_ready;
 	struct resource dpa_res;
-	struct resource pmem_res;
-	struct resource ram_res;
+	struct cxl_dpa_partition part[CXL_NR_PARTITIONS_MAX];
+	unsigned int nr_partitions;
 	u64 serial;
 	enum cxl_devtype type;
 	struct cxl_mailbox cxl_mbox;
 };
 
+static inline resource_size_t cxl_pmem_size(struct cxl_dev_state *cxlds)
+{
+	/*
+	 * Static PMEM may be at partition index 0 when there is no static RAM
+	 * capacity.
+	 */
+	for (int i = 0; i < cxlds->nr_partitions; i++)
+		if (cxlds->part[i].mode == CXL_PARTMODE_PMEM)
+			return resource_size(&cxlds->part[i].res);
+	return 0;
+}
+
 static inline struct cxl_dev_state *mbox_to_cxlds(struct cxl_mailbox *cxl_mbox)
 {
 	return dev_get_drvdata(cxl_mbox->host);
@@ -471,8 +508,6 @@ static inline struct cxl_dev_state *mbox_to_cxlds(struct cxl_mailbox *cxl_mbox)
  * @active_persistent_bytes: sum of hard + soft persistent
  * @next_volatile_bytes: volatile capacity change pending device reset
  * @next_persistent_bytes: persistent capacity change pending device reset
- * @ram_perf: performance data entry matched to RAM partition
- * @pmem_perf: performance data entry matched to PMEM partition
  * @event: event log driver state
  * @poison: poison driver state info
  * @security: security driver state info
@@ -496,9 +531,6 @@ struct cxl_memdev_state {
 	u64 next_volatile_bytes;
 	u64 next_persistent_bytes;
 
-	struct cxl_dpa_perf ram_perf;
-	struct cxl_dpa_perf pmem_perf;
-
 	struct cxl_event_state event;
 	struct cxl_poison_state poison;
 	struct cxl_security_state security;
@@ -818,7 +850,7 @@ int cxl_internal_send_cmd(struct cxl_mailbox *cxl_mbox,
 int cxl_dev_state_identify(struct cxl_memdev_state *mds);
 int cxl_await_media_ready(struct cxl_dev_state *cxlds);
 int cxl_enumerate_cmds(struct cxl_memdev_state *mds);
-int cxl_mem_create_range_info(struct cxl_memdev_state *mds);
+int cxl_mem_dpa_fetch(struct cxl_memdev_state *mds, struct cxl_dpa_info *info);
 struct cxl_memdev_state *cxl_memdev_state_create(struct device *dev);
 void set_exclusive_cxl_commands(struct cxl_memdev_state *mds,
 				unsigned long *cmds);
diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c
index 2f03a4d5606e..9675243bd05b 100644
--- a/drivers/cxl/mem.c
+++ b/drivers/cxl/mem.c
@@ -152,7 +152,7 @@ static int cxl_mem_probe(struct device *dev)
 		return -ENXIO;
 	}
 
-	if (resource_size(&cxlds->pmem_res) && IS_ENABLED(CONFIG_CXL_PMEM)) {
+	if (cxl_pmem_size(cxlds) && IS_ENABLED(CONFIG_CXL_PMEM)) {
 		rc = devm_cxl_add_nvdimm(parent_port, cxlmd);
 		if (rc) {
 			if (rc == -ENODEV)
diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c
index a96e54c6259e..b2c943a4de0a 100644
--- a/drivers/cxl/pci.c
+++ b/drivers/cxl/pci.c
@@ -903,6 +903,7 @@ __ATTRIBUTE_GROUPS(cxl_rcd);
 static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct pci_host_bridge *host_bridge = pci_find_host_bridge(pdev->bus);
+	struct cxl_dpa_info range_info = { 0 };
 	struct cxl_memdev_state *mds;
 	struct cxl_dev_state *cxlds;
 	struct cxl_register_map map;
@@ -993,7 +994,11 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (rc)
 		return rc;
 
-	rc = cxl_mem_create_range_info(mds);
+	rc = cxl_mem_dpa_fetch(mds, &range_info);
+	if (rc)
+		return rc;
+
+	rc = cxl_dpa_setup(cxlds, &range_info);
 	if (rc)
 		return rc;
 
diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c
index cc8948f49117..083a66a52731 100644
--- a/tools/testing/cxl/test/cxl.c
+++ b/tools/testing/cxl/test/cxl.c
@@ -1000,25 +1000,21 @@ static void mock_cxl_endpoint_parse_cdat(struct cxl_port *port)
 		find_cxl_root(port);
 	struct cxl_memdev *cxlmd = to_cxl_memdev(port->uport_dev);
 	struct cxl_dev_state *cxlds = cxlmd->cxlds;
-	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
 	struct access_coordinate ep_c[ACCESS_COORDINATE_MAX];
-	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,
-	};
 
 	if (!cxl_root)
 		return;
 
-	if (range_len(&ram_range))
-		dpa_perf_setup(port, &ram_range, &mds->ram_perf);
+	for (int i = 0; i < cxlds->nr_partitions; i++) {
+		struct resource *res = &cxlds->part[i].res;
+		struct cxl_dpa_perf *perf = &cxlds->part[i].perf;
+		struct range range = {
+			.start = res->start,
+			.end = res->end,
+		};
 
-	if (range_len(&pmem_range))
-		dpa_perf_setup(port, &pmem_range, &mds->pmem_perf);
+		dpa_perf_setup(port, &range, perf);
+	}
 
 	cxl_memdev_update_perf(cxlmd);
 
diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c
index 8d731bd63988..495199238335 100644
--- a/tools/testing/cxl/test/mem.c
+++ b/tools/testing/cxl/test/mem.c
@@ -1494,6 +1494,7 @@ static int cxl_mock_mem_probe(struct platform_device *pdev)
 	struct cxl_dev_state *cxlds;
 	struct cxl_mockmem_data *mdata;
 	struct cxl_mailbox *cxl_mbox;
+	struct cxl_dpa_info range_info = { 0 };
 	int rc;
 
 	mdata = devm_kzalloc(dev, sizeof(*mdata), GFP_KERNEL);
@@ -1554,7 +1555,11 @@ static int cxl_mock_mem_probe(struct platform_device *pdev)
 	if (rc)
 		return rc;
 
-	rc = cxl_mem_create_range_info(mds);
+	rc = cxl_mem_dpa_fetch(mds, &range_info);
+	if (rc)
+		return rc;
+
+	rc = cxl_dpa_setup(cxlds, &range_info);
 	if (rc)
 		return rc;