cxl/mem: Register CXL memX devices

Create the /sys/bus/cxl hierarchy to enumerate:

* Memory Devices (per-endpoint control devices)

* Memory Address Space Devices (platform address ranges with
  interleaving, performance, and persistence attributes)

* Memory Regions (active provisioned memory from an address space device
  that is in use as System RAM or delegated to libnvdimm as Persistent
  Memory regions).

For now, only the per-endpoint control devices are registered on the
'cxl' bus. However, going forward it will provide a mechanism to
coordinate cross-device interleave.

Signed-off-by: Ben Widawsky <ben.widawsky@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com> (v2)
Link: https://lore.kernel.org/r/20210217040958.1354670-4-ben.widawsky@intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

1 files changed, 283 insertions, 2 deletions

diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c
index 04e15759bc9b..1c0195b07063 100644
--- a/drivers/cxl/mem.c
+++ b/drivers/cxl/mem.c
@@ -1,6 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /* Copyright(c) 2020 Intel Corporation. All rights reserved. */
 #include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/cdev.h>
+#include <linux/idr.h>
 #include <linux/pci.h>
 #include <linux/io.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
@@ -23,6 +26,12 @@
  *  - Handle and manage error conditions.
  */
 
+/*
+ * An entire PCI topology full of devices should be enough for any
+ * config
+ */
+#define CXL_MEM_MAX_DEVS 65536
+
 #define cxl_doorbell_busy(cxlm)                                                \
 	(readl((cxlm)->mbox_regs + CXLDEV_MBOX_CTRL_OFFSET) &                  \
 	 CXLDEV_MBOX_CTRL_DOORBELL)
@@ -65,6 +74,27 @@ struct mbox_cmd {
 #define CXL_MBOX_SUCCESS 0
 };
 
+/**
+ * struct cxl_memdev - CXL bus object representing a Type-3 Memory Device
+ * @dev: driver core device object
+ * @cdev: char dev core object for ioctl operations
+ * @cxlm: pointer to the parent device driver data
+ * @ops_active: active user of @cxlm in ops handlers
+ * @ops_dead: completion when all @cxlm ops users have exited
+ * @id: id number of this memdev instance.
+ */
+struct cxl_memdev {
+	struct device dev;
+	struct cdev cdev;
+	struct cxl_mem *cxlm;
+	struct percpu_ref ops_active;
+	struct completion ops_dead;
+	int id;
+};
+
+static int cxl_mem_major;
+static DEFINE_IDA(cxl_memdev_ida);
+
 static int cxl_mem_wait_for_doorbell(struct cxl_mem *cxlm)
 {
 	const unsigned long start = jiffies;
@@ -294,6 +324,33 @@ static void cxl_mem_mbox_put(struct cxl_mem *cxlm)
 	mutex_unlock(&cxlm->mbox_mutex);
 }
 
+static long cxl_memdev_ioctl(struct file *file, unsigned int cmd,
+			     unsigned long arg)
+{
+	struct cxl_memdev *cxlmd;
+	struct inode *inode;
+	int rc = -ENOTTY;
+
+	inode = file_inode(file);
+	cxlmd = container_of(inode->i_cdev, typeof(*cxlmd), cdev);
+
+	if (!percpu_ref_tryget_live(&cxlmd->ops_active))
+		return -ENXIO;
+
+	/* TODO: ioctl body */
+
+	percpu_ref_put(&cxlmd->ops_active);
+
+	return rc;
+}
+
+static const struct file_operations cxl_memdev_fops = {
+	.owner = THIS_MODULE,
+	.unlocked_ioctl = cxl_memdev_ioctl,
+	.compat_ioctl = compat_ptr_ioctl,
+	.llseek = noop_llseek,
+};
+
 /**
  * cxl_mem_mbox_send_cmd() - Send a mailbox command to a memory device.
  * @cxlm: The CXL memory device to communicate with.
@@ -512,6 +569,197 @@ static int cxl_mem_dvsec(struct pci_dev *pdev, int dvsec)
 	return 0;
 }
 
+static struct cxl_memdev *to_cxl_memdev(struct device *dev)
+{
+	return container_of(dev, struct cxl_memdev, dev);
+}
+
+static void cxl_memdev_release(struct device *dev)
+{
+	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
+
+	percpu_ref_exit(&cxlmd->ops_active);
+	ida_free(&cxl_memdev_ida, cxlmd->id);
+	kfree(cxlmd);
+}
+
+static char *cxl_memdev_devnode(struct device *dev, umode_t *mode, kuid_t *uid,
+				kgid_t *gid)
+{
+	return kasprintf(GFP_KERNEL, "cxl/%s", dev_name(dev));
+}
+
+static ssize_t firmware_version_show(struct device *dev,
+				     struct device_attribute *attr, char *buf)
+{
+	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
+	struct cxl_mem *cxlm = cxlmd->cxlm;
+
+	return sprintf(buf, "%.16s\n", cxlm->firmware_version);
+}
+static DEVICE_ATTR_RO(firmware_version);
+
+static ssize_t payload_max_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
+	struct cxl_mem *cxlm = cxlmd->cxlm;
+
+	return sprintf(buf, "%zu\n", cxlm->payload_size);
+}
+static DEVICE_ATTR_RO(payload_max);
+
+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_mem *cxlm = cxlmd->cxlm;
+	unsigned long long len = range_len(&cxlm->ram_range);
+
+	return sprintf(buf, "%#llx\n", len);
+}
+
+static struct device_attribute dev_attr_ram_size =
+	__ATTR(size, 0444, ram_size_show, NULL);
+
+static ssize_t pmem_size_show(struct device *dev, struct device_attribute *attr,
+			      char *buf)
+{
+	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
+	struct cxl_mem *cxlm = cxlmd->cxlm;
+	unsigned long long len = range_len(&cxlm->pmem_range);
+
+	return sprintf(buf, "%#llx\n", len);
+}
+
+static struct device_attribute dev_attr_pmem_size =
+	__ATTR(size, 0444, pmem_size_show, NULL);
+
+static struct attribute *cxl_memdev_attributes[] = {
+	&dev_attr_firmware_version.attr,
+	&dev_attr_payload_max.attr,
+	NULL,
+};
+
+static struct attribute *cxl_memdev_pmem_attributes[] = {
+	&dev_attr_pmem_size.attr,
+	NULL,
+};
+
+static struct attribute *cxl_memdev_ram_attributes[] = {
+	&dev_attr_ram_size.attr,
+	NULL,
+};
+
+static struct attribute_group cxl_memdev_attribute_group = {
+	.attrs = cxl_memdev_attributes,
+};
+
+static struct attribute_group cxl_memdev_ram_attribute_group = {
+	.name = "ram",
+	.attrs = cxl_memdev_ram_attributes,
+};
+
+static struct attribute_group cxl_memdev_pmem_attribute_group = {
+	.name = "pmem",
+	.attrs = cxl_memdev_pmem_attributes,
+};
+
+static const struct attribute_group *cxl_memdev_attribute_groups[] = {
+	&cxl_memdev_attribute_group,
+	&cxl_memdev_ram_attribute_group,
+	&cxl_memdev_pmem_attribute_group,
+	NULL,
+};
+
+static const struct device_type cxl_memdev_type = {
+	.name = "cxl_memdev",
+	.release = cxl_memdev_release,
+	.devnode = cxl_memdev_devnode,
+	.groups = cxl_memdev_attribute_groups,
+};
+
+static void cxlmdev_unregister(void *_cxlmd)
+{
+	struct cxl_memdev *cxlmd = _cxlmd;
+	struct device *dev = &cxlmd->dev;
+
+	percpu_ref_kill(&cxlmd->ops_active);
+	cdev_device_del(&cxlmd->cdev, dev);
+	wait_for_completion(&cxlmd->ops_dead);
+	cxlmd->cxlm = NULL;
+	put_device(dev);
+}
+
+static void cxlmdev_ops_active_release(struct percpu_ref *ref)
+{
+	struct cxl_memdev *cxlmd =
+		container_of(ref, typeof(*cxlmd), ops_active);
+
+	complete(&cxlmd->ops_dead);
+}
+
+static int cxl_mem_add_memdev(struct cxl_mem *cxlm)
+{
+	struct pci_dev *pdev = cxlm->pdev;
+	struct cxl_memdev *cxlmd;
+	struct device *dev;
+	struct cdev *cdev;
+	int rc;
+
+	cxlmd = kzalloc(sizeof(*cxlmd), GFP_KERNEL);
+	if (!cxlmd)
+		return -ENOMEM;
+	init_completion(&cxlmd->ops_dead);
+
+	/*
+	 * @cxlm is deallocated when the driver unbinds so operations
+	 * that are using it need to hold a live reference.
+	 */
+	cxlmd->cxlm = cxlm;
+	rc = percpu_ref_init(&cxlmd->ops_active, cxlmdev_ops_active_release, 0,
+			     GFP_KERNEL);
+	if (rc)
+		goto err_ref;
+
+	rc = ida_alloc_range(&cxl_memdev_ida, 0, CXL_MEM_MAX_DEVS, GFP_KERNEL);
+	if (rc < 0)
+		goto err_id;
+	cxlmd->id = rc;
+
+	dev = &cxlmd->dev;
+	device_initialize(dev);
+	dev->parent = &pdev->dev;
+	dev->bus = &cxl_bus_type;
+	dev->devt = MKDEV(cxl_mem_major, cxlmd->id);
+	dev->type = &cxl_memdev_type;
+	dev_set_name(dev, "mem%d", cxlmd->id);
+
+	cdev = &cxlmd->cdev;
+	cdev_init(cdev, &cxl_memdev_fops);
+
+	rc = cdev_device_add(cdev, dev);
+	if (rc)
+		goto err_add;
+
+	return devm_add_action_or_reset(dev->parent, cxlmdev_unregister, cxlmd);
+
+err_add:
+	ida_free(&cxl_memdev_ida, cxlmd->id);
+err_id:
+	/*
+	 * Theoretically userspace could have already entered the fops,
+	 * so flush ops_active.
+	 */
+	percpu_ref_kill(&cxlmd->ops_active);
+	wait_for_completion(&cxlmd->ops_dead);
+	percpu_ref_exit(&cxlmd->ops_active);
+err_ref:
+	kfree(cxlmd);
+
+	return rc;
+}
+
 /**
  * cxl_mem_identify() - Send the IDENTIFY command to the device.
  * @cxlm: The device to identify.
@@ -612,7 +860,11 @@ static int cxl_mem_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (rc)
 		return rc;
 
-	return cxl_mem_identify(cxlm);
+	rc = cxl_mem_identify(cxlm);
+	if (rc)
+		return rc;
+
+	return cxl_mem_add_memdev(cxlm);
 }
 
 static const struct pci_device_id cxl_mem_pci_tbl[] = {
@@ -631,5 +883,34 @@ static struct pci_driver cxl_mem_driver = {
 	},
 };
 
+static __init int cxl_mem_init(void)
+{
+	dev_t devt;
+	int rc;
+
+	rc = alloc_chrdev_region(&devt, 0, CXL_MEM_MAX_DEVS, "cxl");
+	if (rc)
+		return rc;
+
+	cxl_mem_major = MAJOR(devt);
+
+	rc = pci_register_driver(&cxl_mem_driver);
+	if (rc) {
+		unregister_chrdev_region(MKDEV(cxl_mem_major, 0),
+					 CXL_MEM_MAX_DEVS);
+		return rc;
+	}
+
+	return 0;
+}
+
+static __exit void cxl_mem_exit(void)
+{
+	pci_unregister_driver(&cxl_mem_driver);
+	unregister_chrdev_region(MKDEV(cxl_mem_major, 0), CXL_MEM_MAX_DEVS);
+}
+
 MODULE_LICENSE("GPL v2");
-module_pci_driver(cxl_mem_driver);
+module_init(cxl_mem_init);
+module_exit(cxl_mem_exit);
+MODULE_IMPORT_NS(CXL);