Merge branch 'for-5.1/libnvdimm' into libnvdimm-for-next

Merge miscellaneous libnvdimm sub-system updates for v5.1. Highlights
include:

* Support for the Hyper-V family of device-specific-methods (DSMs)
* Several fixes and workarounds for Hyper-V compatibility.
* Fix for the support to cache the dirty-shutdown-count at init.

MAINTAINERS

@@ -4536,20 +4536,21 @@ S:	Maintained
 F:	drivers/i2c/busses/i2c-diolan-u2c.c
 
 FILESYSTEM DIRECT ACCESS (DAX)
-M:	Matthew Wilcox <[email protected]>
-M:	Ross Zwisler <zwisler@kernel.org>
-M:	Jan Kara <[email protected]>
+M:	Dan Williams <[email protected]>
+R:	Matthew Wilcox <willy@infradead.org>
+R:	Jan Kara <[email protected]>
 L:	[email protected]
+L:	[email protected]
 S:	Supported
 F:	fs/dax.c
 F:	include/linux/dax.h
 F:	include/trace/events/fs_dax.h
 
 DEVICE DIRECT ACCESS (DAX)
 M:	Dan Williams <[email protected]>
-M:	Dave Jiang <[email protected]>
-M:	Ross Zwisler <[email protected]>
 M:	Vishal Verma <[email protected]>
+M:	Keith Busch <[email protected]>
+M:	Dave Jiang <[email protected]>
 L:	[email protected]
 S:	Supported
 F:	drivers/dax/
@@ -8643,7 +8644,6 @@ S:	Maintained
 F:	tools/lib/lockdep/
 
 LIBNVDIMM BLK: MMIO-APERTURE DRIVER
-M:	Ross Zwisler <[email protected]>
 M:	Dan Williams <[email protected]>
 M:	Vishal Verma <[email protected]>
 M:	Dave Jiang <[email protected]>
@@ -8656,15 +8656,13 @@ F:	drivers/nvdimm/region_devs.c
 LIBNVDIMM BTT: BLOCK TRANSLATION TABLE
 M:	Vishal Verma <[email protected]>
 M:	Dan Williams <[email protected]>
-M:	Ross Zwisler <[email protected]>
 M:	Dave Jiang <[email protected]>
 L:	[email protected]
 Q:	https://patchwork.kernel.org/project/linux-nvdimm/list/
 S:	Supported
 F:	drivers/nvdimm/btt*
 
 LIBNVDIMM PMEM: PERSISTENT MEMORY DRIVER
-M:	Ross Zwisler <[email protected]>
 M:	Dan Williams <[email protected]>
 M:	Vishal Verma <[email protected]>
 M:	Dave Jiang <[email protected]>
@@ -8683,9 +8681,10 @@ F:	Documentation/devicetree/bindings/pmem/pmem-region.txt
 
 LIBNVDIMM: NON-VOLATILE MEMORY DEVICE SUBSYSTEM
 M:	Dan Williams <[email protected]>
-M:	Ross Zwisler <[email protected]>
 M:	Vishal Verma <[email protected]>
 M:	Dave Jiang <[email protected]>
+M:	Keith Busch <[email protected]>
+M:	Ira Weiny <[email protected]>
 L:	[email protected]
 Q:	https://patchwork.kernel.org/project/linux-nvdimm/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm.git

drivers/acpi/nfit/core.c

@@ -55,6 +55,10 @@ static bool no_init_ars;
 module_param(no_init_ars, bool, 0644);
 MODULE_PARM_DESC(no_init_ars, "Skip ARS run at nfit init time");
 
+static bool force_labels;
+module_param(force_labels, bool, 0444);
+MODULE_PARM_DESC(force_labels, "Opt-in to labels despite missing methods");
+
 LIST_HEAD(acpi_descs);
 DEFINE_MUTEX(acpi_desc_lock);
 
@@ -556,6 +560,13 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
 		return -EINVAL;
 	}
 
+	if (out_obj->type != ACPI_TYPE_BUFFER) {
+		dev_dbg(dev, "%s unexpected output object type cmd: %s type: %d\n",
+				dimm_name, cmd_name, out_obj->type);
+		rc = -EINVAL;
+		goto out;
+	}
+
 	if (call_pkg) {
 		call_pkg->nd_fw_size = out_obj->buffer.length;
 		memcpy(call_pkg->nd_payload + call_pkg->nd_size_in,
@@ -574,13 +585,6 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
 		return 0;
 	}
 
-	if (out_obj->package.type != ACPI_TYPE_BUFFER) {
-		dev_dbg(dev, "%s unexpected output object type cmd: %s type: %d\n",
-				dimm_name, cmd_name, out_obj->type);
-		rc = -EINVAL;
-		goto out;
-	}
-
 	dev_dbg(dev, "%s cmd: %s output length: %d\n", dimm_name,
 			cmd_name, out_obj->buffer.length);
 	print_hex_dump_debug(cmd_name, DUMP_PREFIX_OFFSET, 4, 4,
@@ -1761,14 +1765,14 @@ static bool acpi_nvdimm_has_method(struct acpi_device *adev, char *method)
 
 __weak void nfit_intel_shutdown_status(struct nfit_mem *nfit_mem)
 {
+	struct device *dev = &nfit_mem->adev->dev;
 	struct nd_intel_smart smart = { 0 };
 	union acpi_object in_buf = {
-		.type = ACPI_TYPE_BUFFER,
-		.buffer.pointer = (char *) &smart,
-		.buffer.length = sizeof(smart),
+		.buffer.type = ACPI_TYPE_BUFFER,
+		.buffer.length = 0,
 	};
 	union acpi_object in_obj = {
-		.type = ACPI_TYPE_PACKAGE,
+		.package.type = ACPI_TYPE_PACKAGE,
 		.package.count = 1,
 		.package.elements = &in_buf,
 	};
@@ -1783,8 +1787,15 @@ __weak void nfit_intel_shutdown_status(struct nfit_mem *nfit_mem)
 		return;
 
 	out_obj = acpi_evaluate_dsm(handle, guid, revid, func, &in_obj);
-	if (!out_obj)
+	if (!out_obj || out_obj->type != ACPI_TYPE_BUFFER
+			|| out_obj->buffer.length < sizeof(smart)) {
+		dev_dbg(dev->parent, "%s: failed to retrieve initial health\n",
+				dev_name(dev));
+		ACPI_FREE(out_obj);
 		return;
+	}
+	memcpy(&smart, out_obj->buffer.pointer, sizeof(smart));
+	ACPI_FREE(out_obj);
 
 	if (smart.flags & ND_INTEL_SMART_SHUTDOWN_VALID) {
 		if (smart.shutdown_state)
@@ -1795,7 +1806,6 @@ __weak void nfit_intel_shutdown_status(struct nfit_mem *nfit_mem)
 		set_bit(NFIT_MEM_DIRTY_COUNT, &nfit_mem->flags);
 		nfit_mem->dirty_shutdown = smart.shutdown_count;
 	}
-	ACPI_FREE(out_obj);
 }
 
 static void populate_shutdown_status(struct nfit_mem *nfit_mem)
@@ -1863,9 +1873,17 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 	dev_set_drvdata(&adev_dimm->dev, nfit_mem);
 
 	/*
-	 * Until standardization materializes we need to consider 4
-	 * different command sets.  Note, that checking for function0 (bit0)
-	 * tells us if any commands are reachable through this GUID.
+	 * There are 4 "legacy" NVDIMM command sets
+	 * (NVDIMM_FAMILY_{INTEL,MSFT,HPE1,HPE2}) that were created before
+	 * an EFI working group was established to constrain this
+	 * proliferation. The nfit driver probes for the supported command
+	 * set by GUID. Note, if you're a platform developer looking to add
+	 * a new command set to this probe, consider using an existing set,
+	 * or otherwise seek approval to publish the command set at
+	 * http://www.uefi.org/RFIC_LIST.
+	 *
+	 * Note, that checking for function0 (bit0) tells us if any commands
+	 * are reachable through this GUID.
 	 */
 	for (i = 0; i <= NVDIMM_FAMILY_MAX; i++)
 		if (acpi_check_dsm(adev_dimm->handle, to_nfit_uuid(i), 1, 1))
@@ -1888,6 +1906,8 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 			dsm_mask &= ~(1 << 8);
 	} else if (nfit_mem->family == NVDIMM_FAMILY_MSFT) {
 		dsm_mask = 0xffffffff;
+	} else if (nfit_mem->family == NVDIMM_FAMILY_HYPERV) {
+		dsm_mask = 0x1f;
 	} else {
 		dev_dbg(dev, "unknown dimm command family\n");
 		nfit_mem->family = -1;
@@ -1917,18 +1937,32 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 		| 1 << ND_CMD_SET_CONFIG_DATA;
 	if (family == NVDIMM_FAMILY_INTEL
 			&& (dsm_mask & label_mask) == label_mask)
-		return 0;
+		/* skip _LS{I,R,W} enabling */;
+	else {
+		if (acpi_nvdimm_has_method(adev_dimm, "_LSI")
+				&& acpi_nvdimm_has_method(adev_dimm, "_LSR")) {
+			dev_dbg(dev, "%s: has _LSR\n", dev_name(&adev_dimm->dev));
+			set_bit(NFIT_MEM_LSR, &nfit_mem->flags);
+		}
 
-	if (acpi_nvdimm_has_method(adev_dimm, "_LSI")
-			&& acpi_nvdimm_has_method(adev_dimm, "_LSR")) {
-		dev_dbg(dev, "%s: has _LSR\n", dev_name(&adev_dimm->dev));
-		set_bit(NFIT_MEM_LSR, &nfit_mem->flags);
-	}
+		if (test_bit(NFIT_MEM_LSR, &nfit_mem->flags)
+				&& acpi_nvdimm_has_method(adev_dimm, "_LSW")) {
+			dev_dbg(dev, "%s: has _LSW\n", dev_name(&adev_dimm->dev));
+			set_bit(NFIT_MEM_LSW, &nfit_mem->flags);
+		}
 
-	if (test_bit(NFIT_MEM_LSR, &nfit_mem->flags)
-			&& acpi_nvdimm_has_method(adev_dimm, "_LSW")) {
-		dev_dbg(dev, "%s: has _LSW\n", dev_name(&adev_dimm->dev));
-		set_bit(NFIT_MEM_LSW, &nfit_mem->flags);
+		/*
+		 * Quirk read-only label configurations to preserve
+		 * access to label-less namespaces by default.
+		 */
+		if (!test_bit(NFIT_MEM_LSW, &nfit_mem->flags)
+				&& !force_labels) {
+			dev_dbg(dev, "%s: No _LSW, disable labels\n",
+					dev_name(&adev_dimm->dev));
+			clear_bit(NFIT_MEM_LSR, &nfit_mem->flags);
+		} else
+			dev_dbg(dev, "%s: Force enable labels\n",
+					dev_name(&adev_dimm->dev));
 	}
 
 	populate_shutdown_status(nfit_mem);
@@ -2029,6 +2063,10 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc)
 			cmd_mask |= nfit_mem->dsm_mask & NVDIMM_STANDARD_CMDMASK;
 		}
 
+		/* Quirk to ignore LOCAL for labels on HYPERV DIMMs */
+		if (nfit_mem->family == NVDIMM_FAMILY_HYPERV)
+			set_bit(NDD_NOBLK, &flags);
+
 		if (test_bit(NFIT_MEM_LSR, &nfit_mem->flags)) {
 			set_bit(ND_CMD_GET_CONFIG_SIZE, &cmd_mask);
 			set_bit(ND_CMD_GET_CONFIG_DATA, &cmd_mask);
@@ -2052,7 +2090,7 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc)
 		if ((mem_flags & ACPI_NFIT_MEM_FAILED_MASK) == 0)
 			continue;
 
-		dev_info(acpi_desc->dev, "%s flags:%s%s%s%s%s\n",
+		dev_err(acpi_desc->dev, "Error found in NVDIMM %s flags:%s%s%s%s%s\n",
 				nvdimm_name(nvdimm),
 		  mem_flags & ACPI_NFIT_MEM_SAVE_FAILED ? " save_fail" : "",
 		  mem_flags & ACPI_NFIT_MEM_RESTORE_FAILED ? " restore_fail":"",
@@ -3731,6 +3769,7 @@ static __init int nfit_init(void)
 	guid_parse(UUID_NFIT_DIMM_N_HPE1, &nfit_uuid[NFIT_DEV_DIMM_N_HPE1]);
 	guid_parse(UUID_NFIT_DIMM_N_HPE2, &nfit_uuid[NFIT_DEV_DIMM_N_HPE2]);
 	guid_parse(UUID_NFIT_DIMM_N_MSFT, &nfit_uuid[NFIT_DEV_DIMM_N_MSFT]);
+	guid_parse(UUID_NFIT_DIMM_N_HYPERV, &nfit_uuid[NFIT_DEV_DIMM_N_HYPERV]);
 
 	nfit_wq = create_singlethread_workqueue("nfit");
 	if (!nfit_wq)

drivers/acpi/nfit/nfit.h

@@ -34,11 +34,14 @@
 /* https://msdn.microsoft.com/library/windows/hardware/mt604741 */
 #define UUID_NFIT_DIMM_N_MSFT "1ee68b36-d4bd-4a1a-9a16-4f8e53d46e05"
 
+/* http://www.uefi.org/RFIC_LIST (see "Virtual NVDIMM 0x1901") */
+#define UUID_NFIT_DIMM_N_HYPERV "5746c5f2-a9a2-4264-ad0e-e4ddc9e09e80"
+
 #define ACPI_NFIT_MEM_FAILED_MASK (ACPI_NFIT_MEM_SAVE_FAILED \
 		| ACPI_NFIT_MEM_RESTORE_FAILED | ACPI_NFIT_MEM_FLUSH_FAILED \
 		| ACPI_NFIT_MEM_NOT_ARMED | ACPI_NFIT_MEM_MAP_FAILED)
 
-#define NVDIMM_FAMILY_MAX NVDIMM_FAMILY_MSFT
+#define NVDIMM_FAMILY_MAX NVDIMM_FAMILY_HYPERV
 
 #define NVDIMM_STANDARD_CMDMASK \
 (1 << ND_CMD_SMART | 1 << ND_CMD_SMART_THRESHOLD | 1 << ND_CMD_DIMM_FLAGS \
@@ -94,6 +97,7 @@ enum nfit_uuids {
 	NFIT_DEV_DIMM_N_HPE1 = NVDIMM_FAMILY_HPE1,
 	NFIT_DEV_DIMM_N_HPE2 = NVDIMM_FAMILY_HPE2,
 	NFIT_DEV_DIMM_N_MSFT = NVDIMM_FAMILY_MSFT,
+	NFIT_DEV_DIMM_N_HYPERV = NVDIMM_FAMILY_HYPERV,
 	NFIT_SPA_VOLATILE,
 	NFIT_SPA_PM,
 	NFIT_SPA_DCR,

drivers/nvdimm/btt.c

@@ -541,51 +541,60 @@ static int arena_clear_freelist_error(struct arena_info *arena, u32 lane)
 
 static int btt_freelist_init(struct arena_info *arena)
 {
-	int old, new, ret;
-	u32 i, map_entry;
-	struct log_entry log_new, log_old;
+	int new, ret;
+	struct log_entry log_new;
+	u32 i, map_entry, log_oldmap, log_newmap;
 
 	arena->freelist = kcalloc(arena->nfree, sizeof(struct free_entry),
 					GFP_KERNEL);
 	if (!arena->freelist)
 		return -ENOMEM;
 
 	for (i = 0; i < arena->nfree; i++) {
-		old = btt_log_read(arena, i, &log_old, LOG_OLD_ENT);
-		if (old < 0)
-			return old;
-
 		new = btt_log_read(arena, i, &log_new, LOG_NEW_ENT);
 		if (new < 0)
 			return new;
 
+		/* old and new map entries with any flags stripped out */
+		log_oldmap = ent_lba(le32_to_cpu(log_new.old_map));
+		log_newmap = ent_lba(le32_to_cpu(log_new.new_map));
+
 		/* sub points to the next one to be overwritten */
 		arena->freelist[i].sub = 1 - new;
 		arena->freelist[i].seq = nd_inc_seq(le32_to_cpu(log_new.seq));
-		arena->freelist[i].block = le32_to_cpu(log_new.old_map);
+		arena->freelist[i].block = log_oldmap;
 
 		/*
 		 * FIXME: if error clearing fails during init, we want to make
 		 * the BTT read-only
 		 */
-		if (ent_e_flag(log_new.old_map)) {
+		if (ent_e_flag(log_new.old_map) &&
+				!ent_normal(log_new.old_map)) {
+			arena->freelist[i].has_err = 1;
 			ret = arena_clear_freelist_error(arena, i);
 			if (ret)
 				dev_err_ratelimited(to_dev(arena),
 					"Unable to clear known errors\n");
 		}
 
 		/* This implies a newly created or untouched flog entry */
-		if (log_new.old_map == log_new.new_map)
+		if (log_oldmap == log_newmap)
 			continue;
 
 		/* Check if map recovery is needed */
 		ret = btt_map_read(arena, le32_to_cpu(log_new.lba), &map_entry,
 				NULL, NULL, 0);
 		if (ret)
 			return ret;
-		if ((le32_to_cpu(log_new.new_map) != map_entry) &&
-				(le32_to_cpu(log_new.old_map) == map_entry)) {
+
+		/*
+		 * The map_entry from btt_read_map is stripped of any flag bits,
+		 * so use the stripped out versions from the log as well for
+		 * testing whether recovery is needed. For restoration, use the
+		 * 'raw' version of the log entries as that captured what we
+		 * were going to write originally.
+		 */
+		if ((log_newmap != map_entry) && (log_oldmap == map_entry)) {
 			/*
 			 * Last transaction wrote the flog, but wasn't able
 			 * to complete the map write. So fix up the map.

drivers/nvdimm/btt.h

@@ -44,6 +44,8 @@
 #define ent_e_flag(ent) (!!(ent & MAP_ERR_MASK))
 #define ent_z_flag(ent) (!!(ent & MAP_TRIM_MASK))
 #define set_e_flag(ent) (ent |= MAP_ERR_MASK)
+/* 'normal' is both e and z flags set */
+#define ent_normal(ent) (ent_e_flag(ent) && ent_z_flag(ent))
 
 enum btt_init_state {
 	INIT_UNCHECKED = 0,

drivers/nvdimm/btt_devs.c

@@ -159,11 +159,19 @@ static ssize_t size_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(size);
 
+static ssize_t log_zero_flags_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "Y\n");
+}
+static DEVICE_ATTR_RO(log_zero_flags);
+
 static struct attribute *nd_btt_attributes[] = {
 	&dev_attr_sector_size.attr,
 	&dev_attr_namespace.attr,
 	&dev_attr_uuid.attr,
 	&dev_attr_size.attr,
+	&dev_attr_log_zero_flags.attr,
 	NULL,
 };