Merge patch series "scsi: mpt3sas: add hwmon support"

Louis Sautier <sautier.louis@gmail.com> says:

Expose the IOC and board temperature sensors of LSI / Broadcom / Avago
SAS HBAs that bind to mpt3sas through the hwmon interface. The data
lives in MPI IO Unit Page 7.

The same fields are exposed by Broadcom's userspace tooling through
the /dev/mpt[23]ctl ioctl path (typically root-only): IOCTemperature
and BoardTemperature in lsiutil; ROC and Controller in storcli.
With this driver, sensors(1) shows them unprivileged:

  $ sensors mpt3sas-pci-0200
  mpt3sas-pci-0200
  Adapter: PCI adapter
  IOC:          +42.0°C

Testing
-------

Build-tested all four SCSI_MPT3SAS x HWMON combinations (=y and =m
each), including the SCSI_MPT3SAS=y with HWMON=m case that requires
IS_REACHABLE().

Validated across three Broadcom SAS chip generations. None of the
cards had a board sensor present, so the testing only covers the
IOC channel:

  * LSI 9500-8i / SAS3816, SAS-3:
    - hwmon device registers as "mpt3sas" with only temp1 (IOC) exposed
    - IOC reading matches `storcli /c0 show temperature` and
      `lsiutil -p1 -a 25,2,0,0`
    - rmmod / modprobe cycle goes through the explicit
      unregister/register paths cleanly

  * LSI 9305-24i / SAS3224, SAS-3: same behaviour.

  * LSI 9211-4i / SAS2004, SAS-2: firmware reports both
    *TemperatureUnits = NOT_PRESENT, no hwmon device registered
    (graceful-skip path).

Not verified (no available hardware):
  * Path with both IOC and board sensors present.
  * Fahrenheit-units conversion.
  * Sub-zero readings (signed-cast path).

Link: https://patch.msgid.link/20260630224922.2543096-1-sautier.louis@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

drivers/scsi/mpt3sas/Makefile

@@ -9,3 +9,5 @@ mpt3sas-y +=  mpt3sas_base.o     \
 		mpt3sas_trigger_diag.o \
 		mpt3sas_warpdrive.o \
 		mpt3sas_debugfs.o \
+
+mpt3sas-$(CONFIG_HWMON) += mpt3sas_hwmon.o

drivers/scsi/mpt3sas/mpt3sas_base.h

@@ -1629,6 +1629,9 @@ struct MPT3SAS_ADAPTER {
 	u8		is_aero_ioc;
 	struct dentry	*debugfs_root;
 	struct dentry	*ioc_dump;
+#if IS_REACHABLE(CONFIG_HWMON)
+	struct mpt3sas_hwmon *hwmon;
+#endif
 	PUT_SMID_IO_FP_HIP put_smid_scsi_io;
 	PUT_SMID_IO_FP_HIP put_smid_fast_path;
 	PUT_SMID_IO_FP_HIP put_smid_hi_priority;
@@ -1904,6 +1907,9 @@ int mpt3sas_config_get_iounit_pg3(struct MPT3SAS_ADAPTER *ioc,
 	Mpi2ConfigReply_t *mpi_reply, Mpi2IOUnitPage3_t *config_page, u16 sz);
 int mpt3sas_config_set_iounit_pg1(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigReply_t
 	*mpi_reply, Mpi2IOUnitPage1_t *config_page);
+int mpt3sas_config_get_iounit_pg7(struct MPT3SAS_ADAPTER *ioc,
+				  Mpi2ConfigReply_t *mpi_reply,
+				  Mpi2IOUnitPage7_t *config_page);
 int mpt3sas_config_get_iounit_pg8(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigReply_t
 	*mpi_reply, Mpi2IOUnitPage8_t *config_page);
 int mpt3sas_config_get_sas_iounit_pg1(struct MPT3SAS_ADAPTER *ioc,
@@ -2047,6 +2053,20 @@ void mpt3sas_destroy_debugfs(struct MPT3SAS_ADAPTER *ioc);
 void mpt3sas_init_debugfs(void);
 void mpt3sas_exit_debugfs(void);
 
+#if IS_REACHABLE(CONFIG_HWMON)
+int mpt3sas_hwmon_register(struct MPT3SAS_ADAPTER *ioc);
+void mpt3sas_hwmon_unregister(struct MPT3SAS_ADAPTER *ioc);
+#else
+static inline int mpt3sas_hwmon_register(struct MPT3SAS_ADAPTER *ioc)
+{
+	return 0;
+}
+
+static inline void mpt3sas_hwmon_unregister(struct MPT3SAS_ADAPTER *ioc)
+{
+}
+#endif
+
 /**
  * _scsih_is_pcie_scsi_device - determines if device is an pcie scsi device
  * @device_info: bitfield providing information about the device.

drivers/scsi/mpt3sas/mpt3sas_config.c

@@ -991,6 +991,42 @@ mpt3sas_config_get_iounit_pg3(struct MPT3SAS_ADAPTER *ioc,
 	return r;
 }
 
+/**
+ * mpt3sas_config_get_iounit_pg7 - obtain iounit page 7
+ * @ioc: per adapter object
+ * @mpi_reply: reply mf payload returned from firmware
+ * @config_page: contents of the config page
+ * Context: sleep.
+ *
+ * Return: 0 for success, non-zero for failure.
+ */
+int mpt3sas_config_get_iounit_pg7(struct MPT3SAS_ADAPTER *ioc,
+				  Mpi2ConfigReply_t *mpi_reply,
+				  Mpi2IOUnitPage7_t *config_page)
+{
+	Mpi2ConfigRequest_t mpi_request;
+	int r;
+
+	memset(&mpi_request, 0, sizeof(Mpi2ConfigRequest_t));
+	mpi_request.Function = MPI2_FUNCTION_CONFIG;
+	mpi_request.Action = MPI2_CONFIG_ACTION_PAGE_HEADER;
+	mpi_request.Header.PageType = MPI2_CONFIG_PAGETYPE_IO_UNIT;
+	mpi_request.Header.PageNumber = 7;
+	mpi_request.Header.PageVersion = MPI2_IOUNITPAGE7_PAGEVERSION;
+	ioc->build_zero_len_sge_mpi(ioc, &mpi_request.PageBufferSGE);
+	r = _config_request(ioc, &mpi_request, mpi_reply,
+			    MPT3_CONFIG_PAGE_DEFAULT_TIMEOUT, NULL, 0);
+	if (r)
+		goto out;
+
+	mpi_request.Action = MPI2_CONFIG_ACTION_PAGE_READ_CURRENT;
+	r = _config_request(ioc, &mpi_request, mpi_reply,
+			    MPT3_CONFIG_PAGE_DEFAULT_TIMEOUT,
+			    config_page, sizeof(*config_page));
+ out:
+	return r;
+}
+
 /**
  * mpt3sas_config_get_iounit_pg8 - obtain iounit page 8
  * @ioc: per adapter object

drivers/scsi/mpt3sas/mpt3sas_hwmon.c

@@ -0,0 +1,191 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Hardware monitoring (hwmon) support for the LSI / Broadcom mpt3sas
+ * SAS HBA driver. Exposes the IOC and board temperature sensors by
+ * reading MPI IO Unit Page 7.
+ */
+
+#include <linux/err.h>
+#include <linux/hwmon.h>
+#include <linux/slab.h>
+
+#include "mpt3sas_base.h"
+
+struct mpt3sas_hwmon {
+	struct MPT3SAS_ADAPTER *ioc;
+	struct device *hwmon_dev;
+	bool ioc_present;
+	bool board_present;
+};
+
+/*
+ * Convert a (raw, units) reading to millidegrees Celsius.
+ * Returns -ENODATA when the sensor reports "not present" or
+ * unknown units. Temperature values are interpreted as signed
+ * two's-complement integers.
+ *
+ * The MPI2_IOUNITPAGE7_IOC_TEMP_* and MPI2_IOUNITPAGE7_BOARD_TEMP_*
+ * defines in mpi2_cnfg.h share the same values; the IOC ones are
+ * used for both channels.
+ */
+static int _hwmon_to_mdegc(s16 raw, u8 units, long *out)
+{
+	switch (units) {
+	case MPI2_IOUNITPAGE7_IOC_TEMP_CELSIUS:
+		*out = (long)raw * 1000;
+		return 0;
+	case MPI2_IOUNITPAGE7_IOC_TEMP_FAHRENHEIT:
+		/* (F - 32) * 5 / 9, expressed in milli-units */
+		*out = ((long)raw - 32) * 5000 / 9;
+		return 0;
+	default:
+		return -ENODATA;
+	}
+}
+
+static umode_t _hwmon_is_visible(const void *drvdata,
+				 enum hwmon_sensor_types type,
+				 u32 attr, int channel)
+{
+	const struct mpt3sas_hwmon *h = drvdata;
+
+	if (type != hwmon_temp)
+		return 0;
+	if (attr != hwmon_temp_input && attr != hwmon_temp_label)
+		return 0;
+	if (channel == 0 && h->ioc_present)
+		return 0444;
+	if (channel == 1 && h->board_present)
+		return 0444;
+	return 0;
+}
+
+static int _hwmon_read(struct device *dev, enum hwmon_sensor_types type,
+		       u32 attr, int channel, long *val)
+{
+	struct mpt3sas_hwmon *h = dev_get_drvdata(dev);
+	Mpi2ConfigReply_t mpi_reply;
+	Mpi2IOUnitPage7_t page;
+	int r;
+
+	if (type != hwmon_temp || attr != hwmon_temp_input)
+		return -EOPNOTSUPP;
+
+	r = mpt3sas_config_get_iounit_pg7(h->ioc, &mpi_reply, &page);
+	if (r)
+		return r;
+
+	if (channel == 0)
+		return _hwmon_to_mdegc((s16)le16_to_cpu(page.IOCTemperature),
+				       page.IOCTemperatureUnits, val);
+	if (channel == 1)
+		return _hwmon_to_mdegc((s16)le16_to_cpu(page.BoardTemperature),
+				       page.BoardTemperatureUnits, val);
+	return -EOPNOTSUPP;
+}
+
+static const char * const mpt3sas_hwmon_temp_labels[] = {
+	"IOC",
+	"Board",
+};
+
+static int _hwmon_read_string(struct device *dev,
+			      enum hwmon_sensor_types type,
+			      u32 attr, int channel, const char **str)
+{
+	if (type != hwmon_temp || attr != hwmon_temp_label)
+		return -EOPNOTSUPP;
+	*str = mpt3sas_hwmon_temp_labels[channel];
+	return 0;
+}
+
+static const struct hwmon_channel_info * const mpt3sas_hwmon_info[] = {
+	HWMON_CHANNEL_INFO(temp,
+			   HWMON_T_INPUT | HWMON_T_LABEL,
+			   HWMON_T_INPUT | HWMON_T_LABEL),
+	NULL,
+};
+
+static const struct hwmon_ops mpt3sas_hwmon_ops = {
+	.is_visible	= _hwmon_is_visible,
+	.read		= _hwmon_read,
+	.read_string	= _hwmon_read_string,
+};
+
+static const struct hwmon_chip_info mpt3sas_hwmon_chip_info = {
+	.ops	= &mpt3sas_hwmon_ops,
+	.info	= mpt3sas_hwmon_info,
+};
+
+/**
+ * mpt3sas_hwmon_register - register an hwmon device for the IOC
+ * @ioc: per adapter object
+ * Context: sleep.
+ *
+ * Succeeds without registering when no temperature sensors are present,
+ * so cards without thermal monitoring do not expose an empty hwmon node.
+ * Paired with mpt3sas_hwmon_unregister() from the driver's remove path.
+ *
+ * Return: 0 for success, non-zero for failure.
+ */
+int mpt3sas_hwmon_register(struct MPT3SAS_ADAPTER *ioc)
+{
+	struct device *parent = &ioc->pdev->dev;
+	struct mpt3sas_hwmon *h;
+	struct device *hwdev;
+	Mpi2ConfigReply_t mpi_reply;
+	Mpi2IOUnitPage7_t page;
+	int r;
+
+	r = mpt3sas_config_get_iounit_pg7(ioc, &mpi_reply, &page);
+	if (r)
+		return r;
+
+	/*
+	 * A page where both *TemperatureUnits are NOT_PRESENT covers
+	 * two cases: cards that genuinely lack sensors, and firmware
+	 * errors that left the page zero-filled (the accessor mirrors
+	 * _config_request() behaviour). Either way: skip registration.
+	 */
+	if (page.IOCTemperatureUnits == MPI2_IOUNITPAGE7_IOC_TEMP_NOT_PRESENT &&
+	    page.BoardTemperatureUnits == MPI2_IOUNITPAGE7_BOARD_TEMP_NOT_PRESENT)
+		return 0;
+
+	h = kzalloc_obj(*h);
+	if (!h)
+		return -ENOMEM;
+
+	h->ioc = ioc;
+	h->ioc_present = page.IOCTemperatureUnits != MPI2_IOUNITPAGE7_IOC_TEMP_NOT_PRESENT;
+	h->board_present = page.BoardTemperatureUnits != MPI2_IOUNITPAGE7_BOARD_TEMP_NOT_PRESENT;
+
+	hwdev = hwmon_device_register_with_info(parent, "mpt3sas", h,
+						&mpt3sas_hwmon_chip_info,
+						NULL);
+	if (IS_ERR(hwdev)) {
+		kfree(h);
+		return PTR_ERR(hwdev);
+	}
+
+	h->hwmon_dev = hwdev;
+	ioc->hwmon = h;
+	return 0;
+}
+
+/**
+ * mpt3sas_hwmon_unregister - tear down the hwmon device, if any
+ * @ioc: per adapter object
+ *
+ * Safe to call when registration was skipped (no sensors) or
+ * failed; in those cases ioc->hwmon is NULL and this is a no-op.
+ */
+void mpt3sas_hwmon_unregister(struct MPT3SAS_ADAPTER *ioc)
+{
+	struct mpt3sas_hwmon *h = ioc->hwmon;
+
+	if (!h)
+		return;
+	hwmon_device_unregister(h->hwmon_dev);
+	kfree(h);
+	ioc->hwmon = NULL;
+}

drivers/scsi/mpt3sas/mpt3sas_scsih.c

@@ -12562,6 +12562,7 @@ static void scsih_remove(struct pci_dev *pdev)
 	/* release all the volumes */
 	_scsih_ir_shutdown(ioc);
 	mpt3sas_destroy_debugfs(ioc);
+	mpt3sas_hwmon_unregister(ioc);
 	sas_remove_host(shost);
 	list_for_each_entry_safe(raid_device, next, &ioc->raid_device_list,
 	    list) {
@@ -13651,6 +13652,11 @@ _scsih_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	}
 
 	scsi_scan_host(shost);
+
+	if (mpt3sas_hwmon_register(ioc))
+		ioc_warn(ioc,
+			 "hwmon registration failed; temperatures not exposed\n");
+
 	mpt3sas_setup_debugfs(ioc);
 	return 0;
 out_add_shost_fail: