Merge tag 'for-5.5/drivers-post-20191122' of git://git.kernel.dk/linux-block

Pull additional block driver updates from Jens Axboe:
 "Here's another block driver update, done to avoid conflicts with the
  zoned changes coming next.

  This contains:

   - Prepare SCSI sd for zone open/close/finish support

   - Small NVMe pull request
        - hwmon support (Akinobu)
        - add new co-maintainer (Christoph)
        - work-around for a discard issue on non-conformant drives
          (Eduard)

   - Small nbd leak fix"

* tag 'for-5.5/drivers-post-20191122' of git://git.kernel.dk/linux-block:
  nbd: prevent memory leak
  nvme: hwmon: add quirk to avoid changing temperature threshold
  nvme: hwmon: provide temperature min and max values for each sensor
  nvmet: add another maintainer
  nvme: Discard workaround for non-conformant devices
  nvme: Add hardware monitoring support
  scsi: sd_zbc: add zone open, close, and finish support

10 files changed, 334 insertions, 20 deletions

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 19e75999bb15..57532465fb83 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -1032,14 +1032,15 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
 		sockfd_put(sock);
 		return -ENOMEM;
 	}
+
+	config->socks = socks;
+
 	nsock = kzalloc(sizeof(struct nbd_sock), GFP_KERNEL);
 	if (!nsock) {
 		sockfd_put(sock);
 		return -ENOMEM;
 	}
 
-	config->socks = socks;
-
 	nsock->fallback_index = -1;
 	nsock->dead = false;
 	mutex_init(&nsock->tx_lock);
diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig
index 2b36f052bfb9..c6439638a419 100644
--- a/drivers/nvme/host/Kconfig
+++ b/drivers/nvme/host/Kconfig
@@ -23,6 +23,16 @@ config NVME_MULTIPATH
 	   /dev/nvmeXnY device will show up for each NVMe namespaces,
 	   even if it is accessible through multiple controllers.
 
+config NVME_HWMON
+	bool "NVMe hardware monitoring"
+	depends on (NVME_CORE=y && HWMON=y) || (NVME_CORE=m && HWMON)
+	help
+	  This provides support for NVMe hardware monitoring. If enabled,
+	  a hardware monitoring device will be created for each NVMe drive
+	  in the system.
+
+	  If unsure, say N.
+
 config NVME_FABRICS
 	tristate
 
diff --git a/drivers/nvme/host/Makefile b/drivers/nvme/host/Makefile
index 8a4b671c5f0c..fc7b26be692d 100644
--- a/drivers/nvme/host/Makefile
+++ b/drivers/nvme/host/Makefile
@@ -14,6 +14,7 @@ nvme-core-$(CONFIG_TRACING)		+= trace.o
 nvme-core-$(CONFIG_NVME_MULTIPATH)	+= multipath.o
 nvme-core-$(CONFIG_NVM)			+= lightnvm.o
 nvme-core-$(CONFIG_FAULT_INJECTION_DEBUG_FS)	+= fault_inject.o
+nvme-core-$(CONFIG_NVME_HWMON)		+= hwmon.o
 
 nvme-y					+= pci.o
 
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index c5e434c9af62..8e8527408db3 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -613,8 +613,14 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
 	struct nvme_dsm_range *range;
 	struct bio *bio;
 
-	range = kmalloc_array(segments, sizeof(*range),
-				GFP_ATOMIC | __GFP_NOWARN);
+	/*
+	 * Some devices do not consider the DSM 'Number of Ranges' field when
+	 * determining how much data to DMA. Always allocate memory for maximum
+	 * number of segments to prevent device reading beyond end of buffer.
+	 */
+	static const size_t alloc_size = sizeof(*range) * NVME_DSM_MAX_RANGES;
+
+	range = kzalloc(alloc_size, GFP_ATOMIC | __GFP_NOWARN);
 	if (!range) {
 		/*
 		 * If we fail allocation our range, fallback to the controller
@@ -654,7 +660,7 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
 
 	req->special_vec.bv_page = virt_to_page(range);
 	req->special_vec.bv_offset = offset_in_page(range);
-	req->special_vec.bv_len = sizeof(*range) * segments;
+	req->special_vec.bv_len = alloc_size;
 	req->rq_flags |= RQF_SPECIAL_PAYLOAD;
 
 	return BLK_STS_OK;
@@ -2798,6 +2804,9 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	ctrl->oncs = le16_to_cpu(id->oncs);
 	ctrl->mtfa = le16_to_cpu(id->mtfa);
 	ctrl->oaes = le32_to_cpu(id->oaes);
+	ctrl->wctemp = le16_to_cpu(id->wctemp);
+	ctrl->cctemp = le16_to_cpu(id->cctemp);
+
 	atomic_set(&ctrl->abort_limit, id->acl + 1);
 	ctrl->vwc = id->vwc;
 	if (id->mdts)
@@ -2897,6 +2906,9 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	if (ret < 0)
 		return ret;
 
+	if (!ctrl->identified)
+		nvme_hwmon_init(ctrl);
+
 	ctrl->identified = true;
 
 	return 0;
diff --git a/drivers/nvme/host/hwmon.c b/drivers/nvme/host/hwmon.c
new file mode 100644
index 000000000000..a5af21f5d370
--- /dev/null
+++ b/drivers/nvme/host/hwmon.c
@@ -0,0 +1,259 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NVM Express hardware monitoring support
+ * Copyright (c) 2019, Guenter Roeck
+ */
+
+#include <linux/hwmon.h>
+#include <asm/unaligned.h>
+
+#include "nvme.h"
+
+/* These macros should be moved to linux/temperature.h */
+#define MILLICELSIUS_TO_KELVIN(t) DIV_ROUND_CLOSEST((t) + 273150, 1000)
+#define KELVIN_TO_MILLICELSIUS(t) ((t) * 1000L - 273150)
+
+struct nvme_hwmon_data {
+	struct nvme_ctrl *ctrl;
+	struct nvme_smart_log log;
+	struct mutex read_lock;
+};
+
+static int nvme_get_temp_thresh(struct nvme_ctrl *ctrl, int sensor, bool under,
+				long *temp)
+{
+	unsigned int threshold = sensor << NVME_TEMP_THRESH_SELECT_SHIFT;
+	u32 status;
+	int ret;
+
+	if (under)
+		threshold |= NVME_TEMP_THRESH_TYPE_UNDER;
+
+	ret = nvme_get_features(ctrl, NVME_FEAT_TEMP_THRESH, threshold, NULL, 0,
+				&status);
+	if (ret > 0)
+		return -EIO;
+	if (ret < 0)
+		return ret;
+	*temp = KELVIN_TO_MILLICELSIUS(status & NVME_TEMP_THRESH_MASK);
+
+	return 0;
+}
+
+static int nvme_set_temp_thresh(struct nvme_ctrl *ctrl, int sensor, bool under,
+				long temp)
+{
+	unsigned int threshold = sensor << NVME_TEMP_THRESH_SELECT_SHIFT;
+	int ret;
+
+	temp = MILLICELSIUS_TO_KELVIN(temp);
+	threshold |= clamp_val(temp, 0, NVME_TEMP_THRESH_MASK);
+
+	if (under)
+		threshold |= NVME_TEMP_THRESH_TYPE_UNDER;
+
+	ret = nvme_set_features(ctrl, NVME_FEAT_TEMP_THRESH, threshold, NULL, 0,
+				NULL);
+	if (ret > 0)
+		return -EIO;
+
+	return ret;
+}
+
+static int nvme_hwmon_get_smart_log(struct nvme_hwmon_data *data)
+{
+	int ret;
+
+	ret = nvme_get_log(data->ctrl, NVME_NSID_ALL, NVME_LOG_SMART, 0,
+			   &data->log, sizeof(data->log), 0);
+
+	return ret <= 0 ? ret : -EIO;
+}
+
+static int nvme_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
+			   u32 attr, int channel, long *val)
+{
+	struct nvme_hwmon_data *data = dev_get_drvdata(dev);
+	struct nvme_smart_log *log = &data->log;
+	int temp;
+	int err;
+
+	/*
+	 * First handle attributes which don't require us to read
+	 * the smart log.
+	 */
+	switch (attr) {
+	case hwmon_temp_max:
+		return nvme_get_temp_thresh(data->ctrl, channel, false, val);
+	case hwmon_temp_min:
+		return nvme_get_temp_thresh(data->ctrl, channel, true, val);
+	case hwmon_temp_crit:
+		*val = KELVIN_TO_MILLICELSIUS(data->ctrl->cctemp);
+		return 0;
+	default:
+		break;
+	}
+
+	mutex_lock(&data->read_lock);
+	err = nvme_hwmon_get_smart_log(data);
+	if (err)
+		goto unlock;
+
+	switch (attr) {
+	case hwmon_temp_input:
+		if (!channel)
+			temp = get_unaligned_le16(log->temperature);
+		else
+			temp = le16_to_cpu(log->temp_sensor[channel - 1]);
+		*val = KELVIN_TO_MILLICELSIUS(temp);
+		break;
+	case hwmon_temp_alarm:
+		*val = !!(log->critical_warning & NVME_SMART_CRIT_TEMPERATURE);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+unlock:
+	mutex_unlock(&data->read_lock);
+	return err;
+}
+
+static int nvme_hwmon_write(struct device *dev, enum hwmon_sensor_types type,
+			    u32 attr, int channel, long val)
+{
+	struct nvme_hwmon_data *data = dev_get_drvdata(dev);
+
+	switch (attr) {
+	case hwmon_temp_max:
+		return nvme_set_temp_thresh(data->ctrl, channel, false, val);
+	case hwmon_temp_min:
+		return nvme_set_temp_thresh(data->ctrl, channel, true, val);
+	default:
+		break;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static const char * const nvme_hwmon_sensor_names[] = {
+	"Composite",
+	"Sensor 1",
+	"Sensor 2",
+	"Sensor 3",
+	"Sensor 4",
+	"Sensor 5",
+	"Sensor 6",
+	"Sensor 7",
+	"Sensor 8",
+};
+
+static int nvme_hwmon_read_string(struct device *dev,
+				  enum hwmon_sensor_types type, u32 attr,
+				  int channel, const char **str)
+{
+	*str = nvme_hwmon_sensor_names[channel];
+	return 0;
+}
+
+static umode_t nvme_hwmon_is_visible(const void *_data,
+				     enum hwmon_sensor_types type,
+				     u32 attr, int channel)
+{
+	const struct nvme_hwmon_data *data = _data;
+
+	switch (attr) {
+	case hwmon_temp_crit:
+		if (!channel && data->ctrl->cctemp)
+			return 0444;
+		break;
+	case hwmon_temp_max:
+	case hwmon_temp_min:
+		if ((!channel && data->ctrl->wctemp) ||
+		    (channel && data->log.temp_sensor[channel - 1])) {
+			if (data->ctrl->quirks &
+			    NVME_QUIRK_NO_TEMP_THRESH_CHANGE)
+				return 0444;
+			return 0644;
+		}
+		break;
+	case hwmon_temp_alarm:
+		if (!channel)
+			return 0444;
+		break;
+	case hwmon_temp_input:
+	case hwmon_temp_label:
+		if (!channel || data->log.temp_sensor[channel - 1])
+			return 0444;
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
+static const struct hwmon_channel_info *nvme_hwmon_info[] = {
+	HWMON_CHANNEL_INFO(chip, HWMON_C_REGISTER_TZ),
+	HWMON_CHANNEL_INFO(temp,
+			   HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN |
+				HWMON_T_CRIT | HWMON_T_LABEL | HWMON_T_ALARM,
+			   HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN |
+				HWMON_T_LABEL,
+			   HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN |
+				HWMON_T_LABEL,
+			   HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN |
+				HWMON_T_LABEL,
+			   HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN |
+				HWMON_T_LABEL,
+			   HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN |
+				HWMON_T_LABEL,
+			   HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN |
+				HWMON_T_LABEL,
+			   HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN |
+				HWMON_T_LABEL,
+			   HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN |
+				HWMON_T_LABEL),
+	NULL
+};
+
+static const struct hwmon_ops nvme_hwmon_ops = {
+	.is_visible	= nvme_hwmon_is_visible,
+	.read		= nvme_hwmon_read,
+	.read_string	= nvme_hwmon_read_string,
+	.write		= nvme_hwmon_write,
+};
+
+static const struct hwmon_chip_info nvme_hwmon_chip_info = {
+	.ops	= &nvme_hwmon_ops,
+	.info	= nvme_hwmon_info,
+};
+
+void nvme_hwmon_init(struct nvme_ctrl *ctrl)
+{
+	struct device *dev = ctrl->dev;
+	struct nvme_hwmon_data *data;
+	struct device *hwmon;
+	int err;
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return;
+
+	data->ctrl = ctrl;
+	mutex_init(&data->read_lock);
+
+	err = nvme_hwmon_get_smart_log(data);
+	if (err) {
+		dev_warn(dev, "Failed to read smart log (error %d)\n", err);
+		devm_kfree(dev, data);
+		return;
+	}
+
+	hwmon = devm_hwmon_device_register_with_info(dev, "nvme", data,
+						     &nvme_hwmon_chip_info,
+						     NULL);
+	if (IS_ERR(hwmon)) {
+		dev_warn(dev, "Failed to instantiate hwmon device\n");
+		devm_kfree(dev, data);
+	}
+}
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index fdda273cd2f6..3b9cbe0668fa 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -115,6 +115,11 @@ enum nvme_quirks {
 	 * Prevent tag overlap between queues
 	 */
 	NVME_QUIRK_SHARED_TAGS                  = (1 << 13),
+
+	/*
+	 * Don't change the value of the temperature threshold feature
+	 */
+	NVME_QUIRK_NO_TEMP_THRESH_CHANGE	= (1 << 14),
 };
 
 /*
@@ -231,6 +236,8 @@ struct nvme_ctrl {
 	u16 kas;
 	u8 npss;
 	u8 apsta;
+	u16 wctemp;
+	u16 cctemp;
 	u32 oaes;
 	u32 aen_result;
 	u32 ctratt;
@@ -668,4 +675,10 @@ static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev)
 	return dev_to_disk(dev)->private_data;
 }
 
+#ifdef CONFIG_NVME_HWMON
+void nvme_hwmon_init(struct nvme_ctrl *ctrl);
+#else
+static inline void nvme_hwmon_init(struct nvme_ctrl *ctrl) { }
+#endif
+
 #endif /* _NVME_H */
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 3aab92bd2263..dcaad5831cee 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -3080,7 +3080,8 @@ static const struct pci_device_id nvme_id_table[] = {
 				NVME_QUIRK_DEALLOCATE_ZEROES, },
 	{ PCI_VDEVICE(INTEL, 0xf1a5),	/* Intel 600P/P3100 */
 		.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
-				NVME_QUIRK_MEDIUM_PRIO_SQ },
+				NVME_QUIRK_MEDIUM_PRIO_SQ |
+				NVME_QUIRK_NO_TEMP_THRESH_CHANGE },
 	{ PCI_VDEVICE(INTEL, 0xf1a6),	/* Intel 760p/Pro 7600p */
 		.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, },
 	{ PCI_VDEVICE(INTEL, 0x5845),	/* Qemu emulated controller */
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index ebb40160539f..470ee6dc3f7e 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1291,9 +1291,17 @@ static blk_status_t sd_init_command(struct scsi_cmnd *cmd)
 	case REQ_OP_WRITE:
 		return sd_setup_read_write_cmnd(cmd);
 	case REQ_OP_ZONE_RESET:
-		return sd_zbc_setup_reset_cmnd(cmd, false);
+		return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_RESET_WRITE_POINTER,
+						   false);
 	case REQ_OP_ZONE_RESET_ALL:
-		return sd_zbc_setup_reset_cmnd(cmd, true);
+		return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_RESET_WRITE_POINTER,
+						   true);
+	case REQ_OP_ZONE_OPEN:
+		return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_OPEN_ZONE, false);
+	case REQ_OP_ZONE_CLOSE:
+		return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_CLOSE_ZONE, false);
+	case REQ_OP_ZONE_FINISH:
+		return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_FINISH_ZONE, false);
 	default:
 		WARN_ON_ONCE(1);
 		return BLK_STS_NOTSUPP;
@@ -1961,6 +1969,9 @@ static int sd_done(struct scsi_cmnd *SCpnt)
 	case REQ_OP_WRITE_SAME:
 	case REQ_OP_ZONE_RESET:
 	case REQ_OP_ZONE_RESET_ALL:
+	case REQ_OP_ZONE_OPEN:
+	case REQ_OP_ZONE_CLOSE:
+	case REQ_OP_ZONE_FINISH:
 		if (!result) {
 			good_bytes = blk_rq_bytes(req);
 			scsi_set_resid(SCpnt, 0);
diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index 1eab779f812b..bf2102a749bc 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -209,7 +209,8 @@ static inline int sd_is_zoned(struct scsi_disk *sdkp)
 
 extern int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buffer);
 extern void sd_zbc_print_zones(struct scsi_disk *sdkp);
-extern blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd, bool all);
+blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd,
+					 unsigned char op, bool all);
 extern void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
 			    struct scsi_sense_hdr *sshdr);
 extern int sd_zbc_report_zones(struct gendisk *disk, sector_t sector,
@@ -225,8 +226,9 @@ static inline int sd_zbc_read_zones(struct scsi_disk *sdkp,
 
 static inline void sd_zbc_print_zones(struct scsi_disk *sdkp) {}
 
-static inline blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd,
-						   bool all)
+static inline blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd,
+						       unsigned char op,
+						       bool all)
 {
 	return BLK_STS_TARGET;
 }
diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
index 1efc69e194f8..39f10ec0dfcf 100644
--- a/drivers/scsi/sd_zbc.c
+++ b/drivers/scsi/sd_zbc.c
@@ -207,13 +207,17 @@ static inline sector_t sd_zbc_zone_sectors(struct scsi_disk *sdkp)
 }
 
 /**
- * sd_zbc_setup_reset_cmnd - Prepare a RESET WRITE POINTER scsi command.
+ * sd_zbc_setup_zone_mgmt_cmnd - Prepare a zone ZBC_OUT command. The operations
+ *			can be RESET WRITE POINTER, OPEN, CLOSE or FINISH.
  * @cmd: the command to setup
- * @all: Reset all zones control.
+ * @op: Operation to be performed
+ * @all: All zones control
  *
- * Called from sd_init_command() for a REQ_OP_ZONE_RESET request.
+ * Called from sd_init_command() for REQ_OP_ZONE_RESET, REQ_OP_ZONE_RESET_ALL,
+ * REQ_OP_ZONE_OPEN, REQ_OP_ZONE_CLOSE or REQ_OP_ZONE_FINISH requests.
  */
-blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd, bool all)
+blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd,
+					 unsigned char op, bool all)
 {
 	struct request *rq = cmd->request;
 	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
@@ -234,7 +238,7 @@ blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd, bool all)
 	cmd->cmd_len = 16;
 	memset(cmd->cmnd, 0, cmd->cmd_len);
 	cmd->cmnd[0] = ZBC_OUT;
-	cmd->cmnd[1] = ZO_RESET_WRITE_POINTER;
+	cmd->cmnd[1] = op;
 	if (all)
 		cmd->cmnd[14] = 0x1;
 	else
@@ -263,14 +267,14 @@ void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
 	int result = cmd->result;
 	struct request *rq = cmd->request;
 
-	if (req_op(rq) == REQ_OP_ZONE_RESET &&
+	if (op_is_zone_mgmt(req_op(rq)) &&
 	    result &&
 	    sshdr->sense_key == ILLEGAL_REQUEST &&
 	    sshdr->asc == 0x24) {
 		/*
-		 * INVALID FIELD IN CDB error: reset of a conventional
-		 * zone was attempted. Nothing to worry about, so be
-		 * quiet about the error.
+		 * INVALID FIELD IN CDB error: a zone management command was
+		 * attempted on a conventional zone. Nothing to worry about,
+		 * so be quiet about the error.
 		 */
 		rq->rq_flags |= RQF_QUIET;
 	}