Merge tag 'libnvdimm-for-4.20' of git://git.kernel.org/pub/scm/linux/…

…kernel/git/nvdimm/nvdimm

Pull libnvdimm updates from Dan Williams:

 - Improve the efficiency and performance of reading nvdimm-namespace
   labels. Reduce the amount of label data read at driver load time by a
   few orders of magnitude. Reduce heavyweight call-outs to
   platform-firmware routines.

 - Handle media errors located in the 'struct page' array stored on a
   persistent memory namespace. Let the kernel clear these errors rather
   than an awkward userspace workaround.

 - Fix Address Range Scrub (ARS) completion tracking. Correct occasions
   where the kernel indicates completion of ARS before submission.

 - Fix asynchronous device registration reference counting.

 - Add support for reporting an nvdimm dirty-shutdown-count via sysfs.

 - Fix various small libnvdimm core and uapi issues.

* tag 'libnvdimm-for-4.20' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (21 commits)
  acpi, nfit: Further restrict userspace ARS start requests
  acpi, nfit: Fix Address Range Scrub completion tracking
  UAPI: ndctl: Remove use of PAGE_SIZE
  UAPI: ndctl: Fix g++-unsupported initialisation in headers
  tools/testing/nvdimm: Populate dirty shutdown data
  acpi, nfit: Collect shutdown status
  acpi, nfit: Introduce nfit_mem flags
  libnvdimm, label: Fix sparse warning
  nvdimm: Use namespace index data to reduce number of label reads needed
  nvdimm: Split label init out from the logic for getting config data
  nvdimm: Remove empty if statement
  nvdimm: Clarify comment in sizeof_namespace_index
  nvdimm: Sanity check labeloff
  libnvdimm, dimm: Maximize label transfer size
  libnvdimm, pmem: Fix badblocks population for 'raw' namespaces
  libnvdimm, namespace: Drop the repeat assignment for variable dev->parent
  libnvdimm, region: Fail badblocks listing for inactive regions
  libnvdimm, pfn: during init, clear errors in the metadata area
  libnvdimm: Set device node in nd_device_register
  libnvdimm: Hold reference on parent while scheduling async init
  ...

drivers/acpi/nfit/intel.h

@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright(c) 2018 Intel Corporation. All rights reserved.
+ * Intel specific definitions for NVDIMM Firmware Interface Table - NFIT
+ */
+#ifndef _NFIT_INTEL_H_
+#define _NFIT_INTEL_H_
+
+#define ND_INTEL_SMART 1
+
+#define ND_INTEL_SMART_SHUTDOWN_COUNT_VALID     (1 << 5)
+#define ND_INTEL_SMART_SHUTDOWN_VALID           (1 << 10)
+
+struct nd_intel_smart {
+	u32 status;
+	union {
+		struct {
+			u32 flags;
+			u8 reserved0[4];
+			u8 health;
+			u8 spares;
+			u8 life_used;
+			u8 alarm_flags;
+			u16 media_temperature;
+			u16 ctrl_temperature;
+			u32 shutdown_count;
+			u8 ait_status;
+			u16 pmic_temperature;
+			u8 reserved1[8];
+			u8 shutdown_state;
+			u32 vendor_size;
+			u8 vendor_data[92];
+		} __packed;
+		u8 data[128];
+	};
+} __packed;
+
+#endif

drivers/acpi/nfit/nfit.h

@@ -118,10 +118,8 @@ enum nfit_dimm_notifiers {
 };
 
 enum nfit_ars_state {
-	ARS_REQ,
-	ARS_REQ_REDO,
-	ARS_DONE,
-	ARS_SHORT,
+	ARS_REQ_SHORT,
+	ARS_REQ_LONG,
 	ARS_FAILED,
 };
 
@@ -159,6 +157,13 @@ struct nfit_memdev {
 	struct acpi_nfit_memory_map memdev[0];
 };
 
+enum nfit_mem_flags {
+	NFIT_MEM_LSR,
+	NFIT_MEM_LSW,
+	NFIT_MEM_DIRTY,
+	NFIT_MEM_DIRTY_COUNT,
+};
+
 /* assembled tables for a given dimm/memory-device */
 struct nfit_mem {
 	struct nvdimm *nvdimm;
@@ -178,9 +183,9 @@ struct nfit_mem {
 	struct acpi_nfit_desc *acpi_desc;
 	struct resource *flush_wpq;
 	unsigned long dsm_mask;
+	unsigned long flags;
+	u32 dirty_shutdown;
 	int family;
-	bool has_lsr;
-	bool has_lsw;
 };
 
 struct acpi_nfit_desc {
@@ -198,6 +203,7 @@ struct acpi_nfit_desc {
 	struct device *dev;
 	u8 ars_start_flags;
 	struct nd_cmd_ars_status *ars_status;
+	struct nfit_spa *scrub_spa;
 	struct delayed_work dwork;
 	struct list_head list;
 	struct kernfs_node *scrub_count_state;
@@ -252,7 +258,8 @@ struct nfit_blk {
 
 extern struct list_head acpi_descs;
 extern struct mutex acpi_desc_lock;
-int acpi_nfit_ars_rescan(struct acpi_nfit_desc *acpi_desc, unsigned long flags);
+int acpi_nfit_ars_rescan(struct acpi_nfit_desc *acpi_desc,
+		enum nfit_ars_state req_type);
 
 #ifdef CONFIG_X86_MCE
 void nfit_mce_register(void);

drivers/nvdimm/bus.c

@@ -54,12 +54,6 @@ static int to_nd_device_type(struct device *dev)
 
 static int nvdimm_bus_uevent(struct device *dev, struct kobj_uevent_env *env)
 {
-	/*
-	 * Ensure that region devices always have their numa node set as
-	 * early as possible.
-	 */
-	if (is_nd_region(dev))
-		set_dev_node(dev, to_nd_region(dev)->numa_node);
 	return add_uevent_var(env, "MODALIAS=" ND_DEVICE_MODALIAS_FMT,
 			to_nd_device_type(dev));
 }
@@ -488,6 +482,8 @@ static void nd_async_device_register(void *d, async_cookie_t cookie)
 		put_device(dev);
 	}
 	put_device(dev);
+	if (dev->parent)
+		put_device(dev->parent);
 }
 
 static void nd_async_device_unregister(void *d, async_cookie_t cookie)
@@ -506,7 +502,19 @@ void __nd_device_register(struct device *dev)
 {
 	if (!dev)
 		return;
+
+	/*
+	 * Ensure that region devices always have their NUMA node set as
+	 * early as possible. This way we are able to make certain that
+	 * any memory associated with the creation and the creation
+	 * itself of the region is associated with the correct node.
+	 */
+	if (is_nd_region(dev))
+		set_dev_node(dev, to_nd_region(dev)->numa_node);
+
 	dev->bus = &nvdimm_bus_type;
+	if (dev->parent)
+		get_device(dev->parent);
 	get_device(dev);
 	async_schedule_domain(nd_async_device_register, dev,
 			&nd_async_domain);

drivers/nvdimm/dimm.c

@@ -75,7 +75,7 @@ static int nvdimm_probe(struct device *dev)
 	 * DIMM capacity. We fail the dimm probe to prevent regions from
 	 * attempting to parse the label area.
 	 */
-	rc = nvdimm_init_config_data(ndd);
+	rc = nd_label_data_init(ndd);
 	if (rc == -EACCES)
 		nvdimm_set_locked(dev);
 	if (rc)
@@ -84,10 +84,6 @@ static int nvdimm_probe(struct device *dev)
 	dev_dbg(dev, "config data size: %d\n", ndd->nsarea.config_size);
 
 	nvdimm_bus_lock(dev);
-	ndd->ns_current = nd_label_validate(ndd);
-	ndd->ns_next = nd_label_next_nsindex(ndd->ns_current);
-	nd_label_copy(ndd, to_next_namespace_index(ndd),
-			to_current_namespace_index(ndd));
 	if (ndd->ns_current >= 0) {
 		rc = nd_label_reserve_dpa(ndd);
 		if (rc == 0)

drivers/nvdimm/dimm_devs.c

@@ -85,56 +85,48 @@ int nvdimm_init_nsarea(struct nvdimm_drvdata *ndd)
 	return cmd_rc;
 }
 
-int nvdimm_init_config_data(struct nvdimm_drvdata *ndd)
+int nvdimm_get_config_data(struct nvdimm_drvdata *ndd, void *buf,
+			   size_t offset, size_t len)
 {
 	struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(ndd->dev);
+	struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc;
 	int rc = validate_dimm(ndd), cmd_rc = 0;
 	struct nd_cmd_get_config_data_hdr *cmd;
-	struct nvdimm_bus_descriptor *nd_desc;
-	u32 max_cmd_size, config_size;
-	size_t offset;
+	size_t max_cmd_size, buf_offset;
 
 	if (rc)
 		return rc;
 
-	if (ndd->data)
-		return 0;
-
-	if (ndd->nsarea.status || ndd->nsarea.max_xfer == 0
-			|| ndd->nsarea.config_size < ND_LABEL_MIN_SIZE) {
-		dev_dbg(ndd->dev, "failed to init config data area: (%d:%d)\n",
-				ndd->nsarea.max_xfer, ndd->nsarea.config_size);
+	if (offset + len > ndd->nsarea.config_size)
 		return -ENXIO;
-	}
 
-	ndd->data = kvmalloc(ndd->nsarea.config_size, GFP_KERNEL);
-	if (!ndd->data)
-		return -ENOMEM;
-
-	max_cmd_size = min_t(u32, PAGE_SIZE, ndd->nsarea.max_xfer);
-	cmd = kzalloc(max_cmd_size + sizeof(*cmd), GFP_KERNEL);
+	max_cmd_size = min_t(u32, len, ndd->nsarea.max_xfer);
+	cmd = kvzalloc(max_cmd_size + sizeof(*cmd), GFP_KERNEL);
 	if (!cmd)
 		return -ENOMEM;
 
-	nd_desc = nvdimm_bus->nd_desc;
-	for (config_size = ndd->nsarea.config_size, offset = 0;
-			config_size; config_size -= cmd->in_length,
-			offset += cmd->in_length) {
-		cmd->in_length = min(config_size, max_cmd_size);
-		cmd->in_offset = offset;
+	for (buf_offset = 0; len;
+	     len -= cmd->in_length, buf_offset += cmd->in_length) {
+		size_t cmd_size;
+
+		cmd->in_offset = offset + buf_offset;
+		cmd->in_length = min(max_cmd_size, len);
+
+		cmd_size = sizeof(*cmd) + cmd->in_length;
+
 		rc = nd_desc->ndctl(nd_desc, to_nvdimm(ndd->dev),
-				ND_CMD_GET_CONFIG_DATA, cmd,
-				cmd->in_length + sizeof(*cmd), &cmd_rc);
+				ND_CMD_GET_CONFIG_DATA, cmd, cmd_size, &cmd_rc);
 		if (rc < 0)
 			break;
 		if (cmd_rc < 0) {
 			rc = cmd_rc;
 			break;
 		}
-		memcpy(ndd->data + offset, cmd->out_buf, cmd->in_length);
+
+		/* out_buf should be valid, copy it into our output buffer */
+		memcpy(buf + buf_offset, cmd->out_buf, cmd->in_length);
 	}
-	dev_dbg(ndd->dev, "len: %zu rc: %d\n", offset, rc);
-	kfree(cmd);
+	kvfree(cmd);
 
 	return rc;
 }
@@ -151,15 +143,11 @@ int nvdimm_set_config_data(struct nvdimm_drvdata *ndd, size_t offset,
 	if (rc)
 		return rc;
 
-	if (!ndd->data)
-		return -ENXIO;
-
 	if (offset + len > ndd->nsarea.config_size)
 		return -ENXIO;
 
-	max_cmd_size = min_t(u32, PAGE_SIZE, len);
-	max_cmd_size = min_t(u32, max_cmd_size, ndd->nsarea.max_xfer);
-	cmd = kzalloc(max_cmd_size + sizeof(*cmd) + sizeof(u32), GFP_KERNEL);
+	max_cmd_size = min_t(u32, len, ndd->nsarea.max_xfer);
+	cmd = kvzalloc(max_cmd_size + sizeof(*cmd) + sizeof(u32), GFP_KERNEL);
 	if (!cmd)
 		return -ENOMEM;
 
@@ -183,7 +171,7 @@ int nvdimm_set_config_data(struct nvdimm_drvdata *ndd, size_t offset,
 			break;
 		}
 	}
-	kfree(cmd);
+	kvfree(cmd);
 
 	return rc;
 }