Merge branch 'for-6.5/cxl-background' into for-6.5/cxl

Pick up the sanitization work and the infrastructure for other
background commands for 6.5. Sanitization has a different completion
path than typical background commands so it was important to have both
thought out and implemented before either went upstream.

Documentation/ABI/testing/sysfs-bus-cxl

@@ -58,6 +58,43 @@ Description:
 		affinity for this device.
 
 
+What:		/sys/bus/cxl/devices/memX/security/state
+Date:		June, 2023
+KernelVersion:	v6.5
+Contact:	linux-cxl@vger.kernel.org
+Description:
+		(RO) Reading this file will display the CXL security state for
+		that device. Such states can be: 'disabled', 'sanitize', when
+		a sanitization is currently underway; or those available only
+		for persistent memory: 'locked', 'unlocked' or 'frozen'. This
+		sysfs entry is select/poll capable from userspace to notify
+		upon completion of a sanitize operation.
+
+
+What:           /sys/bus/cxl/devices/memX/security/sanitize
+Date:           June, 2023
+KernelVersion:  v6.5
+Contact:        linux-cxl@vger.kernel.org
+Description:
+		(WO) Write a boolean 'true' string value to this attribute to
+		sanitize the device to securely re-purpose or decommission it.
+		This is done by ensuring that all user data and meta-data,
+		whether it resides in persistent capacity, volatile capacity,
+		or the LSA, is made permanently unavailable by whatever means
+		is appropriate for the media type. This functionality requires
+		the device to be not be actively decoding any HPA ranges.
+
+
+What            /sys/bus/cxl/devices/memX/security/erase
+Date:           June, 2023
+KernelVersion:  v6.5
+Contact:        linux-cxl@vger.kernel.org
+Description:
+		(WO) Write a boolean 'true' string value to this attribute to
+		secure erase user data by changing the media encryption keys for
+		all user data areas of the device.
+
+
 What:		/sys/bus/cxl/devices/*/devtype
 Date:		June, 2021
 KernelVersion:	v5.14

drivers/cxl/core/mbox.c

@@ -220,7 +220,8 @@ int cxl_internal_send_cmd(struct cxl_dev_state *cxlds,
 	if (rc)
 		return rc;
 
-	if (mbox_cmd->return_code != CXL_MBOX_CMD_RC_SUCCESS)
+	if (mbox_cmd->return_code != CXL_MBOX_CMD_RC_SUCCESS &&
+	    mbox_cmd->return_code != CXL_MBOX_CMD_RC_BACKGROUND)
 		return cxl_mbox_cmd_rc2errno(mbox_cmd);
 
 	if (!out_size)
@@ -1074,6 +1075,65 @@ int cxl_dev_state_identify(struct cxl_dev_state *cxlds)
 }
 EXPORT_SYMBOL_NS_GPL(cxl_dev_state_identify, CXL);
 
+/**
+ * cxl_mem_sanitize() - Send a sanitization command to the device.
+ * @cxlds: The device data for the operation
+ * @cmd: The specific sanitization command opcode
+ *
+ * Return: 0 if the command was executed successfully, regardless of
+ * whether or not the actual security operation is done in the background,
+ * such as for the Sanitize case.
+ * Error return values can be the result of the mailbox command, -EINVAL
+ * when security requirements are not met or invalid contexts.
+ *
+ * See CXL 3.0 @8.2.9.8.5.1 Sanitize and @8.2.9.8.5.2 Secure Erase.
+ */
+int cxl_mem_sanitize(struct cxl_dev_state *cxlds, u16 cmd)
+{
+	int rc;
+	u32 sec_out = 0;
+	struct cxl_get_security_output {
+		__le32 flags;
+	} out;
+	struct cxl_mbox_cmd sec_cmd = {
+		.opcode = CXL_MBOX_OP_GET_SECURITY_STATE,
+		.payload_out = &out,
+		.size_out = sizeof(out),
+	};
+	struct cxl_mbox_cmd mbox_cmd = { .opcode = cmd };
+
+	if (cmd != CXL_MBOX_OP_SANITIZE && cmd != CXL_MBOX_OP_SECURE_ERASE)
+		return -EINVAL;
+
+	rc = cxl_internal_send_cmd(cxlds, &sec_cmd);
+	if (rc < 0) {
+		dev_err(cxlds->dev, "Failed to get security state : %d", rc);
+		return rc;
+	}
+
+	/*
+	 * Prior to using these commands, any security applied to
+	 * the user data areas of the device shall be DISABLED (or
+	 * UNLOCKED for secure erase case).
+	 */
+	sec_out = le32_to_cpu(out.flags);
+	if (sec_out & CXL_PMEM_SEC_STATE_USER_PASS_SET)
+		return -EINVAL;
+
+	if (cmd == CXL_MBOX_OP_SECURE_ERASE &&
+	    sec_out & CXL_PMEM_SEC_STATE_LOCKED)
+		return -EINVAL;
+
+	rc = cxl_internal_send_cmd(cxlds, &mbox_cmd);
+	if (rc < 0) {
+		dev_err(cxlds->dev, "Failed to sanitize device : %d", rc);
+		return rc;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_mem_sanitize, CXL);
+
 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)

drivers/cxl/core/memdev.c

 // SPDX-License-Identifier: GPL-2.0-only
 /* Copyright(c) 2020 Intel Corporation. */
 
+#include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/device.h>
 #include <linux/slab.h>
 #include <linux/idr.h>
@@ -107,6 +108,88 @@ static ssize_t numa_node_show(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RO(numa_node);
 
+static ssize_t security_state_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 state = cxlds->security.state;
+	u64 reg = readq(cxlds->regs.mbox + CXLDEV_MBOX_BG_CMD_STATUS_OFFSET);
+	u32 pct = FIELD_GET(CXLDEV_MBOX_BG_CMD_COMMAND_PCT_MASK, reg);
+	u16 cmd = FIELD_GET(CXLDEV_MBOX_BG_CMD_COMMAND_OPCODE_MASK, reg);
+
+	if (cmd == CXL_MBOX_OP_SANITIZE && pct != 100)
+		return sysfs_emit(buf, "sanitize\n");
+
+	if (!(state & CXL_PMEM_SEC_STATE_USER_PASS_SET))
+		return sysfs_emit(buf, "disabled\n");
+	if (state & CXL_PMEM_SEC_STATE_FROZEN ||
+	    state & CXL_PMEM_SEC_STATE_MASTER_PLIMIT ||
+	    state & CXL_PMEM_SEC_STATE_USER_PLIMIT)
+		return sysfs_emit(buf, "frozen\n");
+	if (state & CXL_PMEM_SEC_STATE_LOCKED)
+		return sysfs_emit(buf, "locked\n");
+	else
+		return sysfs_emit(buf, "unlocked\n");
+}
+static struct device_attribute dev_attr_security_state =
+	__ATTR(state, 0444, security_state_show, NULL);
+
+static ssize_t security_sanitize_store(struct device *dev,
+				       struct device_attribute *attr,
+				       const char *buf, size_t len)
+{
+	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	struct cxl_port *port = dev_get_drvdata(&cxlmd->dev);
+	ssize_t rc;
+	bool sanitize;
+
+	if (kstrtobool(buf, &sanitize) || !sanitize)
+		return -EINVAL;
+
+	if (!port || !is_cxl_endpoint(port))
+		return -EINVAL;
+
+	/* ensure no regions are mapped to this memdev */
+	if (port->commit_end != -1)
+		return -EBUSY;
+
+	rc = cxl_mem_sanitize(cxlds, CXL_MBOX_OP_SANITIZE);
+
+	return rc ? rc : len;
+}
+static struct device_attribute dev_attr_security_sanitize =
+	__ATTR(sanitize, 0200, NULL, security_sanitize_store);
+
+static ssize_t security_erase_store(struct device *dev,
+				    struct device_attribute *attr,
+				    const char *buf, size_t len)
+{
+	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	struct cxl_port *port = dev_get_drvdata(&cxlmd->dev);
+	ssize_t rc;
+	bool erase;
+
+	if (kstrtobool(buf, &erase) || !erase)
+		return -EINVAL;
+
+	if (!port || !is_cxl_endpoint(port))
+		return -EINVAL;
+
+	/* ensure no regions are mapped to this memdev */
+	if (port->commit_end != -1)
+		return -EBUSY;
+
+	rc = cxl_mem_sanitize(cxlds, CXL_MBOX_OP_SECURE_ERASE);
+
+	return rc ? rc : len;
+}
+static struct device_attribute dev_attr_security_erase =
+	__ATTR(erase, 0200, NULL, security_erase_store);
+
 static int cxl_get_poison_by_memdev(struct cxl_memdev *cxlmd)
 {
 	struct cxl_dev_state *cxlds = cxlmd->cxlds;
@@ -352,6 +435,13 @@ static struct attribute *cxl_memdev_ram_attributes[] = {
 	NULL,
 };
 
+static struct attribute *cxl_memdev_security_attributes[] = {
+	&dev_attr_security_state.attr,
+	&dev_attr_security_sanitize.attr,
+	&dev_attr_security_erase.attr,
+	NULL,
+};
+
 static umode_t cxl_memdev_visible(struct kobject *kobj, struct attribute *a,
 				  int n)
 {
@@ -375,10 +465,16 @@ static struct attribute_group cxl_memdev_pmem_attribute_group = {
 	.attrs = cxl_memdev_pmem_attributes,
 };
 
+static struct attribute_group cxl_memdev_security_attribute_group = {
+	.name = "security",
+	.attrs = cxl_memdev_security_attributes,
+};
+
 static const struct attribute_group *cxl_memdev_attribute_groups[] = {
 	&cxl_memdev_attribute_group,
 	&cxl_memdev_ram_attribute_group,
 	&cxl_memdev_pmem_attribute_group,
+	&cxl_memdev_security_attribute_group,
 	NULL,
 };
 
@@ -427,11 +523,21 @@ void clear_exclusive_cxl_commands(struct cxl_dev_state *cxlds, unsigned long *cm
 }
 EXPORT_SYMBOL_NS_GPL(clear_exclusive_cxl_commands, CXL);
 
+static void cxl_memdev_security_shutdown(struct device *dev)
+{
+	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+
+	if (cxlds->security.poll)
+		cancel_delayed_work_sync(&cxlds->security.poll_dwork);
+}
+
 static void cxl_memdev_shutdown(struct device *dev)
 {
 	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
 
 	down_write(&cxl_memdev_rwsem);
+	cxl_memdev_security_shutdown(dev);
 	cxlmd->cxlds = NULL;
 	up_write(&cxl_memdev_rwsem);
 }
@@ -551,6 +657,34 @@ static const struct file_operations cxl_memdev_fops = {
 	.llseek = noop_llseek,
 };
 
+static void put_sanitize(void *data)
+{
+	struct cxl_dev_state *cxlds = data;
+
+	sysfs_put(cxlds->security.sanitize_node);
+}
+
+static int cxl_memdev_security_init(struct cxl_memdev *cxlmd)
+{
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	struct device *dev = &cxlmd->dev;
+	struct kernfs_node *sec;
+
+	sec = sysfs_get_dirent(dev->kobj.sd, "security");
+	if (!sec) {
+		dev_err(dev, "sysfs_get_dirent 'security' failed\n");
+		return -ENODEV;
+	}
+	cxlds->security.sanitize_node = sysfs_get_dirent(sec, "state");
+	sysfs_put(sec);
+	if (!cxlds->security.sanitize_node) {
+		dev_err(dev, "sysfs_get_dirent 'state' failed\n");
+		return -ENODEV;
+	}
+
+	return devm_add_action_or_reset(cxlds->dev, put_sanitize, cxlds);
+ }
+
 struct cxl_memdev *devm_cxl_add_memdev(struct cxl_dev_state *cxlds)
 {
 	struct cxl_memdev *cxlmd;
@@ -579,6 +713,10 @@ struct cxl_memdev *devm_cxl_add_memdev(struct cxl_dev_state *cxlds)
 	if (rc)
 		goto err;
 
+	rc = cxl_memdev_security_init(cxlmd);
+	if (rc)
+		goto err;
+
 	rc = devm_add_action_or_reset(cxlds->dev, cxl_memdev_unregister, cxlmd);
 	if (rc)
 		return ERR_PTR(rc);

drivers/cxl/cxl.h

@@ -176,14 +176,22 @@ static inline int ways_to_eiw(unsigned int ways, u8 *eiw)
 /* CXL 2.0 8.2.8.4 Mailbox Registers */
 #define CXLDEV_MBOX_CAPS_OFFSET 0x00
 #define   CXLDEV_MBOX_CAP_PAYLOAD_SIZE_MASK GENMASK(4, 0)
+#define   CXLDEV_MBOX_CAP_BG_CMD_IRQ BIT(6)
+#define   CXLDEV_MBOX_CAP_IRQ_MSGNUM_MASK GENMASK(10, 7)
 #define CXLDEV_MBOX_CTRL_OFFSET 0x04
 #define   CXLDEV_MBOX_CTRL_DOORBELL BIT(0)
+#define   CXLDEV_MBOX_CTRL_BG_CMD_IRQ BIT(2)
 #define CXLDEV_MBOX_CMD_OFFSET 0x08
 #define   CXLDEV_MBOX_CMD_COMMAND_OPCODE_MASK GENMASK_ULL(15, 0)
 #define   CXLDEV_MBOX_CMD_PAYLOAD_LENGTH_MASK GENMASK_ULL(36, 16)
 #define CXLDEV_MBOX_STATUS_OFFSET 0x10
+#define   CXLDEV_MBOX_STATUS_BG_CMD BIT(0)
 #define   CXLDEV_MBOX_STATUS_RET_CODE_MASK GENMASK_ULL(47, 32)
 #define CXLDEV_MBOX_BG_CMD_STATUS_OFFSET 0x18
+#define   CXLDEV_MBOX_BG_CMD_COMMAND_OPCODE_MASK GENMASK_ULL(15, 0)
+#define   CXLDEV_MBOX_BG_CMD_COMMAND_PCT_MASK GENMASK_ULL(22, 16)
+#define   CXLDEV_MBOX_BG_CMD_COMMAND_RC_MASK GENMASK_ULL(47, 32)
+#define   CXLDEV_MBOX_BG_CMD_COMMAND_VENDOR_MASK GENMASK_ULL(63, 48)
 #define CXLDEV_MBOX_PAYLOAD_OFFSET 0x20
 
 /*

drivers/cxl/cxlmem.h

@@ -5,6 +5,7 @@
 #include <uapi/linux/cxl_mem.h>
 #include <linux/cdev.h>
 #include <linux/uuid.h>
+#include <linux/rcuwait.h>
 #include "cxl.h"
 
 /* CXL 2.0 8.2.8.5.1.1 Memory Device Status Register */
@@ -108,6 +109,9 @@ static inline struct cxl_ep *cxl_ep_load(struct cxl_port *port,
  *            variable sized output commands, it tells the exact number of bytes
  *            written.
  * @min_out: (input) internal command output payload size validation
+ * @poll_count: (input) Number of timeouts to attempt.
+ * @poll_interval_ms: (input) Time between mailbox background command polling
+ *                    interval timeouts.
  * @return_code: (output) Error code returned from hardware.
  *
  * This is the primary mechanism used to send commands to the hardware.
@@ -123,6 +127,8 @@ struct cxl_mbox_cmd {
 	size_t size_in;
 	size_t size_out;
 	size_t min_out;
+	int poll_count;
+	int poll_interval_ms;
 	u16 return_code;
 };
 
@@ -254,6 +260,23 @@ struct cxl_poison_state {
 	struct mutex lock;  /* Protect reads of poison list */
 };
 
+/**
+ * struct cxl_security_state - Device security state
+ *
+ * @state: state of last security operation
+ * @poll: polling for sanitization is enabled, device has no mbox irq support
+ * @poll_tmo_secs: polling timeout
+ * @poll_dwork: polling work item
+ * @sanitize_node: sanitation sysfs file to notify
+ */
+struct cxl_security_state {
+	unsigned long state;
+	bool poll;
+	int poll_tmo_secs;
+	struct delayed_work poll_dwork;
+	struct kernfs_node *sanitize_node;
+};
+
 /**
  * struct cxl_dev_state - The driver device state
  *
@@ -330,7 +353,9 @@ struct cxl_dev_state {
 
 	struct cxl_event_state event;
 	struct cxl_poison_state poison;
+	struct cxl_security_state security;
 
+	struct rcuwait mbox_wait;
 	int (*mbox_send)(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *cmd);
 };
 
@@ -362,6 +387,8 @@ enum cxl_opcode {
 	CXL_MBOX_OP_GET_SCAN_MEDIA_CAPS	= 0x4303,
 	CXL_MBOX_OP_SCAN_MEDIA		= 0x4304,
 	CXL_MBOX_OP_GET_SCAN_MEDIA	= 0x4305,
+	CXL_MBOX_OP_SANITIZE		= 0x4400,
+	CXL_MBOX_OP_SECURE_ERASE	= 0x4401,
 	CXL_MBOX_OP_GET_SECURITY_STATE	= 0x4500,
 	CXL_MBOX_OP_SET_PASSPHRASE	= 0x4501,
 	CXL_MBOX_OP_DISABLE_PASSPHRASE	= 0x4502,
@@ -722,6 +749,8 @@ static inline void cxl_mem_active_dec(void)
 }
 #endif
 
+int cxl_mem_sanitize(struct cxl_dev_state *cxlds, u16 cmd);
+
 struct cxl_hdm {
 	struct cxl_component_regs regs;
 	unsigned int decoder_count;

drivers/cxl/pci.c

@@ -84,6 +84,89 @@ static int cxl_pci_mbox_wait_for_doorbell(struct cxl_dev_state *cxlds)
 			    status & CXLMDEV_DEV_FATAL ? " fatal" : "",        \
 			    status & CXLMDEV_FW_HALT ? " firmware-halt" : "")
 
+struct cxl_dev_id {
+	struct cxl_dev_state *cxlds;
+};
+
+static int cxl_request_irq(struct cxl_dev_state *cxlds, int irq,
+			   irq_handler_t handler, irq_handler_t thread_fn)
+{
+	struct device *dev = cxlds->dev;
+	struct cxl_dev_id *dev_id;
+
+	/* dev_id must be globally unique and must contain the cxlds */
+	dev_id = devm_kzalloc(dev, sizeof(*dev_id), GFP_KERNEL);
+	if (!dev_id)
+		return -ENOMEM;
+	dev_id->cxlds = cxlds;
+
+	return devm_request_threaded_irq(dev, irq, handler, thread_fn,
+					 IRQF_SHARED | IRQF_ONESHOT,
+					 NULL, dev_id);
+}
+
+static bool cxl_mbox_background_complete(struct cxl_dev_state *cxlds)
+{
+	u64 reg;
+
+	reg = readq(cxlds->regs.mbox + CXLDEV_MBOX_BG_CMD_STATUS_OFFSET);
+	return FIELD_GET(CXLDEV_MBOX_BG_CMD_COMMAND_PCT_MASK, reg) == 100;
+}
+
+static irqreturn_t cxl_pci_mbox_irq(int irq, void *id)
+{
+	u64 reg;
+	u16 opcode;
+	struct cxl_dev_id *dev_id = id;
+	struct cxl_dev_state *cxlds = dev_id->cxlds;
+
+	if (!cxl_mbox_background_complete(cxlds))
+		return IRQ_NONE;
+
+	reg = readq(cxlds->regs.mbox + CXLDEV_MBOX_BG_CMD_STATUS_OFFSET);
+	opcode = FIELD_GET(CXLDEV_MBOX_BG_CMD_COMMAND_OPCODE_MASK, reg);
+	if (opcode == CXL_MBOX_OP_SANITIZE) {
+		if (cxlds->security.sanitize_node)
+			sysfs_notify_dirent(cxlds->security.sanitize_node);
+
+		dev_dbg(cxlds->dev, "Sanitization operation ended\n");
+	} else {
+		/* short-circuit the wait in __cxl_pci_mbox_send_cmd() */
+		rcuwait_wake_up(&cxlds->mbox_wait);
+	}
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * Sanitization operation polling mode.
+ */
+static void cxl_mbox_sanitize_work(struct work_struct *work)
+{
+	struct cxl_dev_state *cxlds;
+
+	cxlds = container_of(work,
+			     struct cxl_dev_state, security.poll_dwork.work);
+
+	mutex_lock(&cxlds->mbox_mutex);
+	if (cxl_mbox_background_complete(cxlds)) {
+		cxlds->security.poll_tmo_secs = 0;
+		put_device(cxlds->dev);
+
+		if (cxlds->security.sanitize_node)
+			sysfs_notify_dirent(cxlds->security.sanitize_node);
+
+		dev_dbg(cxlds->dev, "Sanitization operation ended\n");
+	} else {
+		int timeout = cxlds->security.poll_tmo_secs + 10;
+
+		cxlds->security.poll_tmo_secs = min(15 * 60, timeout);
+		queue_delayed_work(system_wq, &cxlds->security.poll_dwork,
+				   timeout * HZ);
+	}
+	mutex_unlock(&cxlds->mbox_mutex);
+}
+
 /**
  * __cxl_pci_mbox_send_cmd() - Execute a mailbox command
  * @cxlds: The device state to communicate with.
@@ -144,6 +227,16 @@ static int __cxl_pci_mbox_send_cmd(struct cxl_dev_state *cxlds,
 		return -EBUSY;
 	}
 
+	/*
+	 * With sanitize polling, hardware might be done and the poller still
+	 * not be in sync. Ensure no new command comes in until so. Keep the
+	 * hardware semantics and only allow device health status.
+	 */
+	if (cxlds->security.poll_tmo_secs > 0) {
+		if (mbox_cmd->opcode != CXL_MBOX_OP_GET_HEALTH_INFO)
+			return -EBUSY;
+	}
+
 	cmd_reg = FIELD_PREP(CXLDEV_MBOX_CMD_COMMAND_OPCODE_MASK,
 			     mbox_cmd->opcode);
 	if (mbox_cmd->size_in) {
@@ -177,12 +270,80 @@ static int __cxl_pci_mbox_send_cmd(struct cxl_dev_state *cxlds,
 	mbox_cmd->return_code =
 		FIELD_GET(CXLDEV_MBOX_STATUS_RET_CODE_MASK, status_reg);
 
+	/*
+	 * Handle the background command in a synchronous manner.
+	 *
+	 * All other mailbox commands will serialize/queue on the mbox_mutex,
+	 * which we currently hold. Furthermore this also guarantees that
+	 * cxl_mbox_background_complete() checks are safe amongst each other,
+	 * in that no new bg operation can occur in between.
+	 *
+	 * Background operations are timesliced in accordance with the nature
+	 * of the command. In the event of timeout, the mailbox state is
+	 * indeterminate until the next successful command submission and the
+	 * driver can get back in sync with the hardware state.
+	 */
+	if (mbox_cmd->return_code == CXL_MBOX_CMD_RC_BACKGROUND) {
+		u64 bg_status_reg;
+		int i, timeout;
+
+		/*
+		 * Sanitization is a special case which monopolizes the device
+		 * and cannot be timesliced. Handle asynchronously instead,
+		 * and allow userspace to poll(2) for completion.
+		 */
+		if (mbox_cmd->opcode == CXL_MBOX_OP_SANITIZE) {
+			if (cxlds->security.poll_tmo_secs != -1) {
+				/* hold the device throughout */
+				get_device(cxlds->dev);
+
+				/* give first timeout a second */
+				timeout = 1;
+				cxlds->security.poll_tmo_secs = timeout;
+				queue_delayed_work(system_wq,
+						   &cxlds->security.poll_dwork,
+						   timeout * HZ);
+			}
+
+			dev_dbg(dev, "Sanitization operation started\n");
+			goto success;
+		}
+
+		dev_dbg(dev, "Mailbox background operation (0x%04x) started\n",
+			mbox_cmd->opcode);
+
+		timeout = mbox_cmd->poll_interval_ms;
+		for (i = 0; i < mbox_cmd->poll_count; i++) {
+			if (rcuwait_wait_event_timeout(&cxlds->mbox_wait,
+				       cxl_mbox_background_complete(cxlds),
+				       TASK_UNINTERRUPTIBLE,
+				       msecs_to_jiffies(timeout)) > 0)
+				break;
+		}
+
+		if (!cxl_mbox_background_complete(cxlds)) {
+			dev_err(dev, "timeout waiting for background (%d ms)\n",
+				timeout * mbox_cmd->poll_count);
+			return -ETIMEDOUT;
+		}
+
+		bg_status_reg = readq(cxlds->regs.mbox +
+				      CXLDEV_MBOX_BG_CMD_STATUS_OFFSET);
+		mbox_cmd->return_code =
+			FIELD_GET(CXLDEV_MBOX_BG_CMD_COMMAND_RC_MASK,
+				  bg_status_reg);
+		dev_dbg(dev,
+			"Mailbox background operation (0x%04x) completed\n",
+			mbox_cmd->opcode);
+	}
+
 	if (mbox_cmd->return_code != CXL_MBOX_CMD_RC_SUCCESS) {
 		dev_dbg(dev, "Mailbox operation had an error: %s\n",
 			cxl_mbox_cmd_rc2str(mbox_cmd));
 		return 0; /* completed but caller must check return_code */
 	}
 
+success:
 	/* #7 */
 	cmd_reg = readq(cxlds->regs.mbox + CXLDEV_MBOX_CMD_OFFSET);
 	out_len = FIELD_GET(CXLDEV_MBOX_CMD_PAYLOAD_LENGTH_MASK, cmd_reg);
@@ -271,6 +432,34 @@ static int cxl_pci_setup_mailbox(struct cxl_dev_state *cxlds)
 	dev_dbg(cxlds->dev, "Mailbox payload sized %zu",
 		cxlds->payload_size);
 
+	rcuwait_init(&cxlds->mbox_wait);
+
+	if (cap & CXLDEV_MBOX_CAP_BG_CMD_IRQ) {
+		u32 ctrl;
+		int irq, msgnum;
+		struct pci_dev *pdev = to_pci_dev(cxlds->dev);
+
+		msgnum = FIELD_GET(CXLDEV_MBOX_CAP_IRQ_MSGNUM_MASK, cap);
+		irq = pci_irq_vector(pdev, msgnum);
+		if (irq < 0)
+			goto mbox_poll;
+
+		if (cxl_request_irq(cxlds, irq, cxl_pci_mbox_irq, NULL))
+			goto mbox_poll;
+
+		/* enable background command mbox irq support */
+		ctrl = readl(cxlds->regs.mbox + CXLDEV_MBOX_CTRL_OFFSET);
+		ctrl |= CXLDEV_MBOX_CTRL_BG_CMD_IRQ;
+		writel(ctrl, cxlds->regs.mbox + CXLDEV_MBOX_CTRL_OFFSET);
+
+		return 0;
+	}
+
+mbox_poll:
+	cxlds->security.poll = true;
+	INIT_DELAYED_WORK(&cxlds->security.poll_dwork, cxl_mbox_sanitize_work);
+
+	dev_dbg(cxlds->dev, "Mailbox interrupts are unsupported");
 	return 0;
 }
 
@@ -469,10 +658,6 @@ static int cxl_alloc_irq_vectors(struct pci_dev *pdev)
 	return 0;
 }
 
-struct cxl_dev_id {
-	struct cxl_dev_state *cxlds;
-};
-
 static irqreturn_t cxl_event_thread(int irq, void *id)
 {
 	struct cxl_dev_id *dev_id = id;
@@ -498,28 +683,18 @@ static irqreturn_t cxl_event_thread(int irq, void *id)
 
 static int cxl_event_req_irq(struct cxl_dev_state *cxlds, u8 setting)
 {
-	struct device *dev = cxlds->dev;
-	struct pci_dev *pdev = to_pci_dev(dev);
-	struct cxl_dev_id *dev_id;
+	struct pci_dev *pdev = to_pci_dev(cxlds->dev);
 	int irq;
 
 	if (FIELD_GET(CXLDEV_EVENT_INT_MODE_MASK, setting) != CXL_INT_MSI_MSIX)
 		return -ENXIO;
 
-	/* dev_id must be globally unique and must contain the cxlds */
-	dev_id = devm_kzalloc(dev, sizeof(*dev_id), GFP_KERNEL);
-	if (!dev_id)
-		return -ENOMEM;
-	dev_id->cxlds = cxlds;
-
 	irq =  pci_irq_vector(pdev,
 			      FIELD_GET(CXLDEV_EVENT_INT_MSGNUM_MASK, setting));
 	if (irq < 0)
 		return irq;
 
-	return devm_request_threaded_irq(dev, irq, NULL, cxl_event_thread,
-					 IRQF_SHARED | IRQF_ONESHOT, NULL,
-					 dev_id);
+	return cxl_request_irq(cxlds, irq, NULL, cxl_event_thread);
 }
 
 static int cxl_event_get_int_policy(struct cxl_dev_state *cxlds,
@@ -714,6 +889,10 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	else
 		dev_warn(&pdev->dev, "Media not active (%d)\n", rc);
 
+	rc = cxl_alloc_irq_vectors(pdev);
+	if (rc)
+		return rc;
+
 	rc = cxl_pci_setup_mailbox(cxlds);
 	if (rc)
 		return rc;
@@ -738,10 +917,6 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (rc)
 		return rc;
 
-	rc = cxl_alloc_irq_vectors(pdev);
-	if (rc)
-		return rc;
-
 	cxlmd = devm_cxl_add_memdev(cxlds);
 	if (IS_ERR(cxlmd))
 		return PTR_ERR(cxlmd);

drivers/cxl/security.c

@@ -34,6 +34,9 @@ static unsigned long cxl_pmem_get_security_flags(struct nvdimm *nvdimm,
 		return 0;
 
 	sec_out = le32_to_cpu(out.flags);
+	/* cache security state */
+	cxlds->security.state = sec_out;
+
 	if (ptype == NVDIMM_MASTER) {
 		if (sec_out & CXL_PMEM_SEC_STATE_MASTER_PASS_SET)
 			set_bit(NVDIMM_SECURITY_UNLOCKED, &security_flags);

include/linux/rcuwait.h

@@ -49,9 +49,9 @@ static inline void prepare_to_rcuwait(struct rcuwait *w)
 
 extern void finish_rcuwait(struct rcuwait *w);
 
-#define rcuwait_wait_event(w, condition, state)				\
+#define ___rcuwait_wait_event(w, condition, state, ret, cmd)		\
 ({									\
-	int __ret = 0;							\
+	long __ret = ret;						\
 	prepare_to_rcuwait(w);						\
 	for (;;) {							\
 		/*							\
@@ -67,10 +67,27 @@ extern void finish_rcuwait(struct rcuwait *w);
 			break;						\
 		}							\
 									\
-		schedule();						\
+		cmd;							\
 	}								\
 	finish_rcuwait(w);						\
 	__ret;								\
 })
 
+#define rcuwait_wait_event(w, condition, state)				\
+	___rcuwait_wait_event(w, condition, state, 0, schedule())
+
+#define __rcuwait_wait_event_timeout(w, condition, state, timeout)	\
+	___rcuwait_wait_event(w, ___wait_cond_timeout(condition),	\
+			      state, timeout,				\
+			      __ret = schedule_timeout(__ret))
+
+#define rcuwait_wait_event_timeout(w, condition, state, timeout)	\
+({									\
+	long __ret = timeout;						\
+	if (!___wait_cond_timeout(condition))				\
+		__ret = __rcuwait_wait_event_timeout(w, condition,	\
+						     state, timeout);	\
+	__ret;								\
+})
+
 #endif /* _LINUX_RCUWAIT_H_ */

tools/testing/cxl/test/mem.c

@@ -535,6 +535,52 @@ static int mock_partition_info(struct cxl_dev_state *cxlds,
 	return 0;
 }
 
+static int mock_sanitize(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *cmd)
+{
+	struct cxl_mockmem_data *mdata = dev_get_drvdata(cxlds->dev);
+
+	if (cmd->size_in != 0)
+		return -EINVAL;
+
+	if (cmd->size_out != 0)
+		return -EINVAL;
+
+	if (mdata->security_state & CXL_PMEM_SEC_STATE_USER_PASS_SET) {
+		cmd->return_code = CXL_MBOX_CMD_RC_SECURITY;
+		return -ENXIO;
+	}
+	if (mdata->security_state & CXL_PMEM_SEC_STATE_LOCKED) {
+		cmd->return_code = CXL_MBOX_CMD_RC_SECURITY;
+		return -ENXIO;
+	}
+
+	return 0; /* assume less than 2 secs, no bg */
+}
+
+static int mock_secure_erase(struct cxl_dev_state *cxlds,
+			     struct cxl_mbox_cmd *cmd)
+{
+	struct cxl_mockmem_data *mdata = dev_get_drvdata(cxlds->dev);
+
+	if (cmd->size_in != 0)
+		return -EINVAL;
+
+	if (cmd->size_out != 0)
+		return -EINVAL;
+
+	if (mdata->security_state & CXL_PMEM_SEC_STATE_USER_PASS_SET) {
+		cmd->return_code = CXL_MBOX_CMD_RC_SECURITY;
+		return -ENXIO;
+	}
+
+	if (mdata->security_state & CXL_PMEM_SEC_STATE_LOCKED) {
+		cmd->return_code = CXL_MBOX_CMD_RC_SECURITY;
+		return -ENXIO;
+	}
+
+	return 0;
+}
+
 static int mock_get_security_state(struct cxl_dev_state *cxlds,
 				   struct cxl_mbox_cmd *cmd)
 {
@@ -1153,6 +1199,12 @@ static int cxl_mock_mbox_send(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *
 	case CXL_MBOX_OP_GET_HEALTH_INFO:
 		rc = mock_health_info(cxlds, cmd);
 		break;
+	case CXL_MBOX_OP_SANITIZE:
+		rc = mock_sanitize(cxlds, cmd);
+		break;
+	case CXL_MBOX_OP_SECURE_ERASE:
+		rc = mock_secure_erase(cxlds, cmd);
+		break;
 	case CXL_MBOX_OP_GET_SECURITY_STATE:
 		rc = mock_get_security_state(cxlds, cmd);
 		break;