nfit, libnvdimm: deprecate the generic SMART ioctl

The kernel's ND_IOCTL_SMART_THRESHOLD command is based on a payload
definition that has become broken / out-of-sync with recent versions of
the NVDIMM_FAMILY_INTEL definition. Deprecate the use of the
ND_IOCTL_SMART_THRESHOLD command in favor of the ND_CMD_CALL approach
taken by NVDIMM_FAMILY_{HPE,MSFT}, where we can manage the per-vendor
variance in userspace.

In a couple years, when the new scheme is widely deployed in userspace
packages, the ND_IOCTL_SMART_THRESHOLD support can be removed. For now
we prevent new binaries from compiling against the kernel header
definitions, but kernel still compatible with old binaries. The
libndctl.h [1] header is now the authoritative interface definition for
NVDIMM SMART.

[1]: https://github.com/pmem/ndctlSigned-off-by: Dan Williams <dan.j.williams@intel.com>

drivers/nvdimm/bus.c

@@ -1142,9 +1142,6 @@ int __init nvdimm_bus_init(void)
 {
 	int rc;
 
-	BUILD_BUG_ON(sizeof(struct nd_smart_payload) != 128);
-	BUILD_BUG_ON(sizeof(struct nd_smart_threshold_payload) != 8);
-
 	rc = bus_register(&nvdimm_bus_type);
 	if (rc)
 		return rc;

include/uapi/linux/ndctl.h

@@ -15,54 +15,6 @@
 
 #include <linux/types.h>
 
-struct nd_cmd_smart {
-	__u32 status;
-	__u8 data[128];
-} __packed;
-
-#define ND_SMART_HEALTH_VALID	(1 << 0)
-#define ND_SMART_SPARES_VALID	(1 << 1)
-#define ND_SMART_USED_VALID	(1 << 2)
-#define ND_SMART_TEMP_VALID 	(1 << 3)
-#define ND_SMART_CTEMP_VALID 	(1 << 4)
-#define ND_SMART_ALARM_VALID	(1 << 9)
-#define ND_SMART_SHUTDOWN_VALID	(1 << 10)
-#define ND_SMART_VENDOR_VALID	(1 << 11)
-#define ND_SMART_SPARE_TRIP	(1 << 0)
-#define ND_SMART_TEMP_TRIP	(1 << 1)
-#define ND_SMART_CTEMP_TRIP	(1 << 2)
-#define ND_SMART_NON_CRITICAL_HEALTH	(1 << 0)
-#define ND_SMART_CRITICAL_HEALTH	(1 << 1)
-#define ND_SMART_FATAL_HEALTH		(1 << 2)
-
-struct nd_smart_payload {
-	__u32 flags;
-	__u8 reserved0[4];
-	__u8 health;
-	__u8 spares;
-	__u8 life_used;
-	__u8 alarm_flags;
-	__u16 temperature;
-	__u16 ctrl_temperature;
-	__u8 reserved1[15];
-	__u8 shutdown_state;
-	__u32 vendor_size;
-	__u8 vendor_data[92];
-} __packed;
-
-struct nd_cmd_smart_threshold {
-	__u32 status;
-	__u8 data[8];
-} __packed;
-
-struct nd_smart_threshold_payload {
-	__u8 alarm_control;
-	__u8 reserved0;
-	__u16 temperature;
-	__u8 spares;
-	__u8 reserved[3];
-} __packed;
-
 struct nd_cmd_dimm_flags {
 	__u32 status;
 	__u32 flags;
@@ -211,12 +163,6 @@ static inline const char *nvdimm_cmd_name(unsigned cmd)
 
 #define ND_IOCTL 'N'
 
-#define ND_IOCTL_SMART			_IOWR(ND_IOCTL, ND_CMD_SMART,\
-					struct nd_cmd_smart)
-
-#define ND_IOCTL_SMART_THRESHOLD	_IOWR(ND_IOCTL, ND_CMD_SMART_THRESHOLD,\
-					struct nd_cmd_smart_threshold)
-
 #define ND_IOCTL_DIMM_FLAGS		_IOWR(ND_IOCTL, ND_CMD_DIMM_FLAGS,\
 					struct nd_cmd_dimm_flags)
 

tools/testing/nvdimm/test/nfit.c

@@ -440,39 +440,50 @@ static int nfit_test_cmd_translate_spa(struct nvdimm_bus *bus,
 	return 0;
 }
 
-static int nfit_test_cmd_smart(struct nd_cmd_smart *smart, unsigned int buf_len)
+static int nfit_test_cmd_smart(struct nd_intel_smart *smart, unsigned int buf_len)
 {
-	static const struct nd_smart_payload smart_data = {
-		.flags = ND_SMART_HEALTH_VALID | ND_SMART_TEMP_VALID
-			| ND_SMART_SPARES_VALID | ND_SMART_ALARM_VALID
-			| ND_SMART_USED_VALID | ND_SMART_SHUTDOWN_VALID,
-		.health = ND_SMART_NON_CRITICAL_HEALTH,
-		.temperature = 23 * 16,
+	static const struct nd_intel_smart smart_data = {
+		.flags = ND_INTEL_SMART_HEALTH_VALID
+			| ND_INTEL_SMART_SPARES_VALID
+			| ND_INTEL_SMART_ALARM_VALID
+			| ND_INTEL_SMART_USED_VALID
+			| ND_INTEL_SMART_SHUTDOWN_VALID
+			| ND_INTEL_SMART_MTEMP_VALID,
+		.health = ND_INTEL_SMART_NON_CRITICAL_HEALTH,
+		.media_temperature = 23 * 16,
+		.ctrl_temperature = 30 * 16,
+		.pmic_temperature = 40 * 16,
 		.spares = 75,
-		.alarm_flags = ND_SMART_SPARE_TRIP | ND_SMART_TEMP_TRIP,
+		.alarm_flags = ND_INTEL_SMART_SPARE_TRIP
+			| ND_INTEL_SMART_TEMP_TRIP,
+		.ait_status = 1,
 		.life_used = 5,
 		.shutdown_state = 0,
 		.vendor_size = 0,
+		.shutdown_count = 100,
 	};
 
 	if (buf_len < sizeof(*smart))
 		return -EINVAL;
-	memcpy(smart->data, &smart_data, sizeof(smart_data));
+	memcpy(smart, &smart_data, sizeof(smart_data));
 	return 0;
 }
 
-static int nfit_test_cmd_smart_threshold(struct nd_cmd_smart_threshold *smart_t,
+static int nfit_test_cmd_smart_threshold(
+		struct nd_intel_smart_threshold *smart_t,
 		unsigned int buf_len)
 {
-	static const struct nd_smart_threshold_payload smart_t_data = {
-		.alarm_control = ND_SMART_SPARE_TRIP | ND_SMART_TEMP_TRIP,
-		.temperature = 40 * 16,
+	static const struct nd_intel_smart_threshold smart_t_data = {
+		.alarm_control = ND_INTEL_SMART_SPARE_TRIP
+			| ND_INTEL_SMART_TEMP_TRIP,
+		.media_temperature = 40 * 16,
+		.ctrl_temperature = 30 * 16,
 		.spares = 5,
 	};
 
 	if (buf_len < sizeof(*smart_t))
 		return -EINVAL;
-	memcpy(smart_t->data, &smart_t_data, sizeof(smart_t_data));
+	memcpy(smart_t, &smart_t_data, sizeof(smart_t_data));
 	return 0;
 }
 

tools/testing/nvdimm/test/nfit_test.h

@@ -84,6 +84,65 @@ struct nd_cmd_ars_err_inj_stat {
 	} __packed record[0];
 } __packed;
 
+#define ND_INTEL_SMART 1
+#define ND_INTEL_SMART_THRESHOLD 2
+
+#define ND_INTEL_SMART_HEALTH_VALID             (1 << 0)
+#define ND_INTEL_SMART_SPARES_VALID             (1 << 1)
+#define ND_INTEL_SMART_USED_VALID               (1 << 2)
+#define ND_INTEL_SMART_MTEMP_VALID              (1 << 3)
+#define ND_INTEL_SMART_CTEMP_VALID              (1 << 4)
+#define ND_INTEL_SMART_SHUTDOWN_COUNT_VALID     (1 << 5)
+#define ND_INTEL_SMART_AIT_STATUS_VALID         (1 << 6)
+#define ND_INTEL_SMART_PTEMP_VALID              (1 << 7)
+#define ND_INTEL_SMART_ALARM_VALID              (1 << 9)
+#define ND_INTEL_SMART_SHUTDOWN_VALID           (1 << 10)
+#define ND_INTEL_SMART_VENDOR_VALID             (1 << 11)
+#define ND_INTEL_SMART_SPARE_TRIP               (1 << 0)
+#define ND_INTEL_SMART_TEMP_TRIP                (1 << 1)
+#define ND_INTEL_SMART_CTEMP_TRIP               (1 << 2)
+#define ND_INTEL_SMART_NON_CRITICAL_HEALTH      (1 << 0)
+#define ND_INTEL_SMART_CRITICAL_HEALTH          (1 << 1)
+#define ND_INTEL_SMART_FATAL_HEALTH             (1 << 2)
+
+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;
+
+struct nd_intel_smart_threshold {
+	__u32 status;
+	union {
+		struct {
+			__u16 alarm_control;
+			__u8 spares;
+			__u16 media_temperature;
+			__u16 ctrl_temperature;
+			__u8 reserved[1];
+		} __packed;
+		__u8 data[8];
+	};
+} __packed;
+
 union acpi_object;
 typedef void *acpi_handle;