cxl/memdev: Add support for the Clear Poison mailbox command

CXL devices optionally support the CLEAR POISON mailbox command. Add
memdev driver support for clearing poison.

Per the CXL Specification (3.0 8.2.9.8.4.3), after receiving a valid
clear poison request, the device removes the address from the device's
Poison List and writes 0 (zero) for 64 bytes starting at address. If
the device cannot clear poison from the address, it returns a permanent
media error and -ENXIO is returned to the user.

Additionally, and per the spec also, it is not an error to clear poison
of an address that is not poisoned.

If the address is not contained in the device's dpa resource, or is
not 64 byte aligned, the driver returns -EINVAL without sending the
command to the device.

Poison clearing is intended for debug only and will be exposed to
userspace through debugfs. Restrict compilation to CONFIG_DEBUG_FS.

Implementation note: Although the CXL specification defines the clear
command to accept 64 bytes of 'write-data', this implementation always
uses zeroes as write-data.
Signed-off-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/8682c30ec24bd9c45af5feccb04b02be51e58c0a.1681874357.git.alison.schofield@intel.comTested-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

drivers/cxl/core/memdev.c

@@ -216,6 +216,49 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa)
 }
 EXPORT_SYMBOL_NS_GPL(cxl_inject_poison, CXL);
 
+int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa)
+{
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	struct cxl_mbox_clear_poison clear;
+	struct cxl_mbox_cmd mbox_cmd;
+	int rc;
+
+	if (!IS_ENABLED(CONFIG_DEBUG_FS))
+		return 0;
+
+	rc = down_read_interruptible(&cxl_dpa_rwsem);
+	if (rc)
+		return rc;
+
+	rc = cxl_validate_poison_dpa(cxlmd, dpa);
+	if (rc)
+		goto out;
+
+	/*
+	 * In CXL 3.0 Spec 8.2.9.8.4.3, the Clear Poison mailbox command
+	 * is defined to accept 64 bytes of write-data, along with the
+	 * address to clear. This driver uses zeroes as write-data.
+	 */
+	clear = (struct cxl_mbox_clear_poison) {
+		.address = cpu_to_le64(dpa)
+	};
+
+	mbox_cmd = (struct cxl_mbox_cmd) {
+		.opcode = CXL_MBOX_OP_CLEAR_POISON,
+		.size_in = sizeof(clear),
+		.payload_in = &clear,
+	};
+
+	rc = cxl_internal_send_cmd(cxlds, &mbox_cmd);
+	if (rc)
+		goto out;
+out:
+	up_read(&cxl_dpa_rwsem);
+
+	return rc;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_clear_poison, CXL);
+
 static struct attribute *cxl_memdev_attributes[] = {
 	&dev_attr_serial.attr,
 	&dev_attr_firmware_version.attr,

drivers/cxl/cxlmem.h

@@ -620,6 +620,12 @@ struct cxl_mbox_inject_poison {
 	__le64 address;
 };
 
+/* Clear Poison  CXL 3.0 Spec 8.2.9.8.4.3 */
+struct cxl_mbox_clear_poison {
+	__le64 address;
+	u8 write_data[CXL_POISON_LEN_MULT];
+} __packed;
+
 /**
  * struct cxl_mem_command - Driver representation of a memory device command
  * @info: Command information as it exists for the UAPI
@@ -695,6 +701,7 @@ int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len,
 		       struct cxl_region *cxlr);
 int cxl_trigger_poison_list(struct cxl_memdev *cxlmd);
 int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa);
+int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa);
 
 #ifdef CONFIG_CXL_SUSPEND
 void cxl_mem_active_inc(void);