cxl/mem: Fix no cxl_nvd during pmem region auto-assembling

JIRA: https://issues.redhat.com/browse/RHEL-51364
CVE: CVE-2024-41085

When CXL subsystem is auto-assembling a pmem region during cxl
endpoint port probing, always hit below calltrace.

 BUG: kernel NULL pointer dereference, address: 0000000000000078
 #PF: supervisor read access in kernel mode
 #PF: error_code(0x0000) - not-present page
 RIP: 0010:cxl_pmem_region_probe+0x22e/0x360 [cxl_pmem]
 Call Trace:
  <TASK>
  ? __die+0x24/0x70
  ? page_fault_oops+0x82/0x160
  ? do_user_addr_fault+0x65/0x6b0
  ? exc_page_fault+0x7d/0x170
  ? asm_exc_page_fault+0x26/0x30
  ? cxl_pmem_region_probe+0x22e/0x360 [cxl_pmem]
  ? cxl_pmem_region_probe+0x1ac/0x360 [cxl_pmem]
  cxl_bus_probe+0x1b/0x60 [cxl_core]
  really_probe+0x173/0x410
  ? __pfx___device_attach_driver+0x10/0x10
  __driver_probe_device+0x80/0x170
  driver_probe_device+0x1e/0x90
  __device_attach_driver+0x90/0x120
  bus_for_each_drv+0x84/0xe0
  __device_attach+0xbc/0x1f0
  bus_probe_device+0x90/0xa0
  device_add+0x51c/0x710
  devm_cxl_add_pmem_region+0x1b5/0x380 [cxl_core]
  cxl_bus_probe+0x1b/0x60 [cxl_core]

The cxl_nvd of the memdev needs to be available during the pmem region
probe. Currently the cxl_nvd is registered after the endpoint port probe.
The endpoint probe, in the case of autoassembly of regions, can cause a
pmem region probe requiring the not yet available cxl_nvd. Adjust the
sequence so this dependency is met.

This requires adding a port parameter to cxl_find_nvdimm_bridge() that
can be used to query the ancestor root port. The endpoint port is not
yet available, but will share a common ancestor with its parent, so
start the query from there instead.

Fixes: f17b558 ("cxl/pmem: Refactor nvdimm device registration, delete the workqueue")
Co-developed-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Li Ming <ming4.li@intel.com>
Tested-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Alison Schofield <alison.schofield@intel.com>
Link: https://patch.msgid.link/20240612064423.2567625-1-ming4.li@intel.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
(cherry picked from commit 84ec985)

Conflicts:	(context fixups, revisions to build correctly)
	drivers/cxl/core/pmem.c
	drivers/cxl/core/region.c
Signed-off-by: John W. Linville <linville@redhat.com>

Author: John W. Linville

drivers/cxl/core/pmem.c

@@ -62,16 +62,21 @@ static int match_nvdimm_bridge(struct device *dev, void *data)
 	return is_cxl_nvdimm_bridge(dev);
 }
 
-struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(struct cxl_memdev *cxlmd)
+/**
+ * cxl_find_nvdimm_bridge() - find a bridge device relative to a port
+ * @port: any descendant port of an nvdimm-bridge associated
+ *        root-cxl-port
+ */
+struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(struct cxl_port *port)
 {
-	struct cxl_port *port = find_cxl_root(cxlmd->endpoint);
+	struct cxl_port *root_port = find_cxl_root(port);
 	struct device *dev;
 
-	if (!port)
+	if (!root_port)
 		return NULL;
 
-	dev = device_find_child(&port->dev, NULL, match_nvdimm_bridge);
-	put_device(&port->dev);
+	dev = device_find_child(&root_port->dev, NULL, match_nvdimm_bridge);
+	put_device(&root_port->dev);
 
 	if (!dev)
 		return NULL;
@@ -242,18 +247,20 @@ static void cxlmd_release_nvdimm(void *_cxlmd)
 
 /**
  * devm_cxl_add_nvdimm() - add a bridge between a cxl_memdev and an nvdimm
+ * @parent_port: parent port for the (to be added) @cxlmd endpoint port
  * @cxlmd: cxl_memdev instance that will perform LIBNVDIMM operations
  *
  * Return: 0 on success negative error code on failure.
  */
-int devm_cxl_add_nvdimm(struct cxl_memdev *cxlmd)
+int devm_cxl_add_nvdimm(struct cxl_port *parent_port,
+			struct cxl_memdev *cxlmd)
 {
 	struct cxl_nvdimm_bridge *cxl_nvb;
 	struct cxl_nvdimm *cxl_nvd;
 	struct device *dev;
 	int rc;
 
-	cxl_nvb = cxl_find_nvdimm_bridge(cxlmd);
+	cxl_nvb = cxl_find_nvdimm_bridge(parent_port);
 	if (!cxl_nvb)
 		return -ENODEV;
 

drivers/cxl/core/region.c

@@ -2517,7 +2517,7 @@ static struct cxl_pmem_region *cxl_pmem_region_alloc(struct cxl_region *cxlr)
 		 * bridge for one device is the same for all.
 		 */
 		if (i == 0) {
-			cxl_nvb = cxl_find_nvdimm_bridge(cxlmd);
+			cxl_nvb = cxl_find_nvdimm_bridge(cxlmd->endpoint);
 			if (!cxl_nvb) {
 				kfree(cxlr_pmem);
 				cxlr_pmem = ERR_PTR(-ENODEV);

drivers/cxl/cxl.h

@@ -784,8 +784,8 @@ struct cxl_nvdimm_bridge *devm_cxl_add_nvdimm_bridge(struct device *host,
 struct cxl_nvdimm *to_cxl_nvdimm(struct device *dev);
 bool is_cxl_nvdimm(struct device *dev);
 bool is_cxl_nvdimm_bridge(struct device *dev);
-int devm_cxl_add_nvdimm(struct cxl_memdev *cxlmd);
-struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(struct cxl_memdev *cxlmd);
+int devm_cxl_add_nvdimm(struct cxl_port *parent_port, struct cxl_memdev *cxlmd);
+struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(struct cxl_port *port);
 
 #ifdef CONFIG_CXL_REGION
 bool is_cxl_pmem_region(struct device *dev);

drivers/cxl/mem.c

@@ -153,6 +153,15 @@ static int cxl_mem_probe(struct device *dev)
 		return -ENXIO;
 	}
 
+	if (resource_size(&cxlds->pmem_res) && IS_ENABLED(CONFIG_CXL_PMEM)) {
+		rc = devm_cxl_add_nvdimm(parent_port, cxlmd);
+		if (rc) {
+			if (rc == -ENODEV)
+				dev_info(dev, "PMEM disabled by platform\n");
+			return rc;
+		}
+	}
+
 	if (dport->rch)
 		endpoint_parent = parent_port->uport_dev;
 	else
@@ -173,14 +182,6 @@ static int cxl_mem_probe(struct device *dev)
 	if (rc)
 		return rc;
 
-	if (resource_size(&cxlds->pmem_res) && IS_ENABLED(CONFIG_CXL_PMEM)) {
-		rc = devm_cxl_add_nvdimm(cxlmd);
-		if (rc == -ENODEV)
-			dev_info(dev, "PMEM disabled by platform\n");
-		else
-			return rc;
-	}
-
 	/*
 	 * The kernel may be operating out of CXL memory on this device,
 	 * there is no spec defined way to determine whether this device