Message-ID: <20260108203755.1163107-9-gourry@gourry.net>
Date: Thu,  8 Jan 2026 15:37:55 -0500
From: Gregory Price <gourry@...rry.net>
To: linux-mm@...ck.org,
	cgroups@...r.kernel.org,
	linux-cxl@...r.kernel.org
Cc: linux-doc@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	linux-fsdevel@...r.kernel.org,
	kernel-team@...a.com,
	longman@...hat.com,
	tj@...nel.org,
	hannes@...xchg.org,
	mkoutny@...e.com,
	corbet@....net,
	gregkh@...uxfoundation.org,
	rafael@...nel.org,
	dakr@...nel.org,
	dave@...olabs.net,
	jonathan.cameron@...wei.com,
	dave.jiang@...el.com,
	alison.schofield@...el.com,
	vishal.l.verma@...el.com,
	ira.weiny@...el.com,
	dan.j.williams@...el.com,
	akpm@...ux-foundation.org,
	vbabka@...e.cz,
	surenb@...gle.com,
	mhocko@...e.com,
	jackmanb@...gle.com,
	ziy@...dia.com,
	david@...nel.org,
	lorenzo.stoakes@...cle.com,
	Liam.Howlett@...cle.com,
	rppt@...nel.org,
	axelrasmussen@...gle.com,
	yuanchu@...gle.com,
	weixugc@...gle.com,
	yury.norov@...il.com,
	linux@...musvillemoes.dk,
	rientjes@...gle.com,
	shakeel.butt@...ux.dev,
	chrisl@...nel.org,
	kasong@...cent.com,
	shikemeng@...weicloud.com,
	nphamcs@...il.com,
	bhe@...hat.com,
	baohua@...nel.org,
	yosry.ahmed@...ux.dev,
	chengming.zhou@...ux.dev,
	roman.gushchin@...ux.dev,
	muchun.song@...ux.dev,
	osalvador@...e.de,
	matthew.brost@...el.com,
	joshua.hahnjy@...il.com,
	rakie.kim@...com,
	byungchul@...com,
	gourry@...rry.net,
	ying.huang@...ux.alibaba.com,
	apopple@...dia.com,
	cl@...two.org,
	harry.yoo@...cle.com,
	zhengqi.arch@...edance.com
Subject: [RFC PATCH v3 8/8] drivers/cxl: add zswap private_region type

Add a sample type of a zswap region, which registers itself as a valid
target node with mm/zswap.  Zswap will callback into the driver on new
page allocation and free.

On cxl_zswap_page_allocated(), we would check whether the worst case vs
current compression ratio is safe to allow new writes.

On cxl_zswap_page_freed(), zero the page to adjust the ratio down.

A device driver registering a Zswap private region would need to provide
an indicator to this component whether to allow new allocations - this
would probably be done via an interrupt setting a bit which says the
compression ratio has reached some conservative threshold.

Signed-off-by: Gregory Price <gourry@...rry.net>
---
 drivers/cxl/core/private_region/Makefile      |   3 +
 .../cxl/core/private_region/private_region.c  |  10 ++
 .../cxl/core/private_region/private_region.h  |   4 +
 drivers/cxl/core/private_region/zswap.c       | 127 ++++++++++++++++++
 drivers/cxl/cxl.h                             |   2 +
 5 files changed, 146 insertions(+)
 create mode 100644 drivers/cxl/core/private_region/zswap.c

diff --git a/drivers/cxl/core/private_region/Makefile b/drivers/cxl/core/private_region/Makefile
index d17498129ba6..ba495cd3f89f 100644
--- a/drivers/cxl/core/private_region/Makefile
+++ b/drivers/cxl/core/private_region/Makefile
@@ -7,3 +7,6 @@ ccflags-y += -I$(srctree)/drivers/cxl
 
 # Core dispatch and sysfs
 obj-$(CONFIG_CXL_REGION) += private_region.o
+
+# Type-specific implementations
+obj-$(CONFIG_CXL_REGION) += zswap.o
diff --git a/drivers/cxl/core/private_region/private_region.c b/drivers/cxl/core/private_region/private_region.c
index ead48abb9fc7..da5fb3d264e1 100644
--- a/drivers/cxl/core/private_region/private_region.c
+++ b/drivers/cxl/core/private_region/private_region.c
@@ -16,6 +16,8 @@
 static const char *private_type_to_string(enum cxl_private_region_type type)
 {
 	switch (type) {
+	case CXL_PRIVATE_ZSWAP:
+		return "zswap";
 	default:
 		return "";
 	}
@@ -23,6 +25,8 @@ static const char *private_type_to_string(enum cxl_private_region_type type)
 
 static enum cxl_private_region_type string_to_private_type(const char *str)
 {
+	if (sysfs_streq(str, "zswap"))
+		return CXL_PRIVATE_ZSWAP;
 	return CXL_PRIVATE_NONE;
 }
 
@@ -88,6 +92,9 @@ int cxl_register_private_region(struct cxl_region *cxlr)
 
 	/* Call type-specific registration which sets memtype and callbacks */
 	switch (cxlr->private_type) {
+	case CXL_PRIVATE_ZSWAP:
+		rc = cxl_register_zswap_region(cxlr);
+		break;
 	default:
 		dev_dbg(&cxlr->dev, "unsupported private_type: %d\n",
 			cxlr->private_type);
@@ -113,6 +120,9 @@ void cxl_unregister_private_region(struct cxl_region *cxlr)
 
 	/* Dispatch to type-specific cleanup */
 	switch (cxlr->private_type) {
+	case CXL_PRIVATE_ZSWAP:
+		cxl_unregister_zswap_region(cxlr);
+		break;
 	default:
 		break;
 	}
diff --git a/drivers/cxl/core/private_region/private_region.h b/drivers/cxl/core/private_region/private_region.h
index 9b34e51d8df4..84d43238dbe1 100644
--- a/drivers/cxl/core/private_region/private_region.h
+++ b/drivers/cxl/core/private_region/private_region.h
@@ -7,4 +7,8 @@ struct cxl_region;
 int cxl_register_private_region(struct cxl_region *cxlr);
 void cxl_unregister_private_region(struct cxl_region *cxlr);
 
+/* Type-specific registration functions - called from region.c dispatch */
+int cxl_register_zswap_region(struct cxl_region *cxlr);
+void cxl_unregister_zswap_region(struct cxl_region *cxlr);
+
 #endif /* __CXL_PRIVATE_REGION_H__ */
diff --git a/drivers/cxl/core/private_region/zswap.c b/drivers/cxl/core/private_region/zswap.c
new file mode 100644
index 000000000000..c213abe2fad7
--- /dev/null
+++ b/drivers/cxl/core/private_region/zswap.c
@@ -0,0 +1,127 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * CXL Private Region - zswap type implementation
+ *
+ * This file implements the zswap private region type for CXL devices.
+ * It handles registration/unregistration of CXL regions as zswap
+ * compressed memory targets.
+ */
+
+#include <linux/device.h>
+#include <linux/highmem.h>
+#include <linux/node.h>
+#include <linux/zswap.h>
+#include <linux/memory_hotplug.h>
+#include "../../cxl.h"
+#include "../core.h"
+#include "private_region.h"
+
+/*
+ * CXL zswap region page_allocated callback
+ *
+ * This callback is invoked by zswap when a page is allocated from a private
+ * node to validate that the page is safe to use. For a real compressed memory
+ * device, this would check the device's compression ratio and return an error
+ * if the page cannot safely store data.
+ *
+ * Currently this is a placeholder that always succeeds. A real implementation
+ * would query the device hardware to determine if sufficient compression
+ * headroom exists.
+ */
+static int cxl_zswap_page_allocated(struct page *page, void *data)
+{
+	struct cxl_region *cxlr = data;
+
+	/*
+	 * TODO: Query the CXL device to check if this page allocation is safe.
+	 *
+	 * A real compressed memory device would track its compression ratio
+	 * and report whether it has headroom to accept new data. If the
+	 * compression ratio is too low (device is near capacity), this should
+	 * return -ENOSPC to tell zswap to try another node.
+	 *
+	 * For now, always succeed since we're testing with regular memory.
+	 */
+	dev_dbg(&cxlr->dev, "page_allocated callback for nid %d\n",
+		page_to_nid(page));
+
+	return 0;
+}
+
+/*
+ * CXL zswap region page_freed callback
+ *
+ * This callback is invoked when a page from a private node is being freed.
+ * We zero the page before returning it to the allocator so that the compressed
+ * memory device can reclaim capacity - zeroed pages achieve excellent
+ * compression ratios.
+ */
+static void cxl_zswap_page_freed(struct page *page, void *data)
+{
+	struct cxl_region *cxlr = data;
+
+	/*
+	 * Zero the page to improve the device's compression ratio.
+	 * Zeroed pages compress extremely well, reclaiming device capacity.
+	 */
+	clear_highpage(page);
+
+	dev_dbg(&cxlr->dev, "page_freed callback for nid %d\n",
+		page_to_nid(page));
+}
+
+/*
+ * Unregister a zswap region from the zswap subsystem.
+ *
+ * This function removes the node from zswap direct nodes and unregisters
+ * the private node operations.
+ */
+void cxl_unregister_zswap_region(struct cxl_region *cxlr)
+{
+	int nid;
+
+	if (!cxlr->private ||
+	    cxlr->private_ops.memtype != NODE_MEM_ZSWAP)
+		return;
+
+	if (!cxlr->params.res)
+		return;
+
+	nid = phys_to_target_node(cxlr->params.res->start);
+
+	zswap_remove_direct_node(nid);
+	node_unregister_private(nid, &cxlr->private_ops);
+
+	dev_dbg(&cxlr->dev, "unregistered zswap region for nid %d\n", nid);
+}
+
+/*
+ * Register a zswap region with the zswap subsystem.
+ *
+ * This function sets up the memtype, page_allocated callback, and
+ * registers the node with zswap as a direct compression target.
+ * The caller is responsible for adding the dax region after this succeeds.
+ */
+int cxl_register_zswap_region(struct cxl_region *cxlr)
+{
+	int nid, rc;
+
+	if (!cxlr->private || !cxlr->params.res)
+		return -EINVAL;
+
+	nid = phys_to_target_node(cxlr->params.res->start);
+
+	/* Register with node subsystem as zswap memory */
+	cxlr->private_ops.memtype = NODE_MEM_ZSWAP;
+	cxlr->private_ops.page_allocated = cxl_zswap_page_allocated;
+	cxlr->private_ops.page_freed = cxl_zswap_page_freed;
+	rc = node_register_private(nid, &cxlr->private_ops);
+	if (rc)
+		return rc;
+
+	/* Register this node with zswap as a direct compression target */
+	zswap_add_direct_node(nid);
+
+	dev_dbg(&cxlr->dev, "registered zswap region for nid %d\n", nid);
+	return 0;
+}
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index b276956ff88d..89d8ae4e796c 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -534,9 +534,11 @@ enum cxl_partition_mode {
 /**
  * enum cxl_private_region_type - CXL private region types
  * @CXL_PRIVATE_NONE: No private region type set
+ * @CXL_PRIVATE_ZSWAP: Region used for zswap compressed memory
  */
 enum cxl_private_region_type {
 	CXL_PRIVATE_NONE,
+	CXL_PRIVATE_ZSWAP,
 };
 
 /**
-- 
2.52.0

Powered by blists - more mailing lists