Merge tag 'char-misc-5.13-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc

Pull char/misc driver fixes from Greg KH:
 "Here is a big set of char/misc/other driver fixes for 5.13-rc3.

  The majority here is the fallout of the umn.edu re-review of all prior
  submissions. That resulted in a bunch of reverts along with the
  "correct" changes made, such that there is no regression of any of the
  potential fixes that were made by those individuals. I would like to
  thank the over 80 different developers who helped with the review and
  fixes for this mess.

  Other than that, there's a few habanna driver fixes for reported
  issues, and some dyndbg fixes for reported problems.

  All of these have been in linux-next for a while with no reported
  problems"

* tag 'char-misc-5.13-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc: (82 commits)
  misc: eeprom: at24: check suspend status before disable regulator
  uio_hv_generic: Fix another memory leak in error handling paths
  uio_hv_generic: Fix a memory leak in error handling paths
  uio/uio_pci_generic: fix return value changed in refactoring
  Revert "Revert "ALSA: usx2y: Fix potential NULL pointer dereference""
  dyndbg: drop uninformative vpr_info
  dyndbg: avoid calling dyndbg_emit_prefix when it has no work
  binder: Return EFAULT if we fail BINDER_ENABLE_ONEWAY_SPAM_DETECTION
  cdrom: gdrom: initialize global variable at init time
  brcmfmac: properly check for bus register errors
  Revert "brcmfmac: add a check for the status of usb_register"
  video: imsttfb: check for ioremap() failures
  Revert "video: imsttfb: fix potential NULL pointer dereferences"
  net: liquidio: Add missing null pointer checks
  Revert "net: liquidio: fix a NULL pointer dereference"
  media: gspca: properly check for errors in po1030_probe()
  Revert "media: gspca: Check the return value of write_bridge for timeout"
  media: gspca: mt9m111: Check write_bridge for timeout
  Revert "media: gspca: mt9m111: Check write_bridge for timeout"
  media: dvb: Add check on sp8870_readreg return
  ...

drivers/android/binder.c

@@ -4918,7 +4918,7 @@ static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		uint32_t enable;
 
 		if (copy_from_user(&enable, ubuf, sizeof(enable))) {
-			ret = -EINVAL;
+			ret = -EFAULT;
 			goto err;
 		}
 		binder_inner_proc_lock(proc);

drivers/cdrom/gdrom.c

@@ -744,6 +744,13 @@ static const struct blk_mq_ops gdrom_mq_ops = {
 static int probe_gdrom(struct platform_device *devptr)
 {
 	int err;
+
+	/*
+	 * Ensure our "one" device is initialized properly in case of previous
+	 * usages of it
+	 */
+	memset(&gd, 0, sizeof(gd));
+
 	/* Start the device */
 	if (gdrom_execute_diagnostic() != 1) {
 		pr_warn("ATA Probe for GDROM failed\n");
@@ -830,6 +837,8 @@ static int remove_gdrom(struct platform_device *devptr)
 	if (gdrom_major)
 		unregister_blkdev(gdrom_major, GDROM_DEV_NAME);
 	unregister_cdrom(gd.cd_info);
+	kfree(gd.cd_info);
+	kfree(gd.toc);
 
 	return 0;
 }
@@ -845,7 +854,7 @@ static struct platform_driver gdrom_driver = {
 static int __init init_gdrom(void)
 {
 	int rc;
-	gd.toc = NULL;
+
 	rc = platform_driver_register(&gdrom_driver);
 	if (rc)
 		return rc;
@@ -861,8 +870,6 @@ static void __exit exit_gdrom(void)
 {
 	platform_device_unregister(pd);
 	platform_driver_unregister(&gdrom_driver);
-	kfree(gd.toc);
-	kfree(gd.cd_info);
 }
 
 module_init(init_gdrom);

drivers/char/hpet.c

@@ -984,6 +984,8 @@ static acpi_status hpet_resources(struct acpi_resource *res, void *data)
 		hdp->hd_phys_address = fixmem32->address;
 		hdp->hd_address = ioremap(fixmem32->address,
 						HPET_RANGE_SIZE);
+		if (!hdp->hd_address)
+			return AE_ERROR;
 
 		if (hpet_is_known(hdp)) {
 			iounmap(hdp->hd_address);

drivers/crypto/cavium/nitrox/nitrox_main.c

@@ -442,7 +442,6 @@ static int nitrox_probe(struct pci_dev *pdev,
 	err = pci_request_mem_regions(pdev, nitrox_driver_name);
 	if (err) {
 		pci_disable_device(pdev);
-		dev_err(&pdev->dev, "Failed to request mem regions!\n");
 		return err;
 	}
 	pci_set_master(pdev);

drivers/dma/qcom/hidma_mgmt.c

@@ -418,8 +418,23 @@ static int __init hidma_mgmt_init(void)
 		hidma_mgmt_of_populate_channels(child);
 	}
 #endif
-	return platform_driver_register(&hidma_mgmt_driver);
+	/*
+	 * We do not check for return value here, as it is assumed that
+	 * platform_driver_register must not fail. The reason for this is that
+	 * the (potential) hidma_mgmt_of_populate_channels calls above are not
+	 * cleaned up if it does fail, and to do this work is quite
+	 * complicated. In particular, various calls of of_address_to_resource,
+	 * of_irq_to_resource, platform_device_register_full, of_dma_configure,
+	 * and of_msi_configure which then call other functions and so on, must
+	 * be cleaned up - this is not a trivial exercise.
+	 *
+	 * Currently, this module is not intended to be unloaded, and there is
+	 * no module_exit function defined which does the needed cleanup. For
+	 * this reason, we have to assume success here.
+	 */
+	platform_driver_register(&hidma_mgmt_driver);
 
+	return 0;
 }
 module_init(hidma_mgmt_init);
 MODULE_LICENSE("GPL v2");

drivers/hwmon/lm80.c

@@ -596,7 +596,6 @@ static int lm80_probe(struct i2c_client *client)
 	struct device *dev = &client->dev;
 	struct device *hwmon_dev;
 	struct lm80_data *data;
-	int rv;
 
 	data = devm_kzalloc(dev, sizeof(struct lm80_data), GFP_KERNEL);
 	if (!data)
@@ -609,14 +608,8 @@ static int lm80_probe(struct i2c_client *client)
 	lm80_init_client(client);
 
 	/* A few vars need to be filled upon startup */
-	rv = lm80_read_value(client, LM80_REG_FAN_MIN(1));
+	data->fan[f_min][0] = lm80_read_value(client, LM80_REG_FAN_MIN(1));
-	if (rv < 0)
+	data->fan[f_min][1] = lm80_read_value(client, LM80_REG_FAN_MIN(2));
-		return rv;
-	data->fan[f_min][0] = rv;
-	rv = lm80_read_value(client, LM80_REG_FAN_MIN(2));
-	if (rv < 0)
-		return rv;
-	data->fan[f_min][1] = rv;
 
 	hwmon_dev = devm_hwmon_device_register_with_groups(dev, client->name,
 							   data, lm80_groups);

drivers/isdn/hardware/mISDN/hfcsusb.c

@@ -46,7 +46,7 @@ static void hfcsusb_start_endpoint(struct hfcsusb *hw, int channel);
 static void hfcsusb_stop_endpoint(struct hfcsusb *hw, int channel);
 static int  hfcsusb_setup_bch(struct bchannel *bch, int protocol);
 static void deactivate_bchannel(struct bchannel *bch);
-static void hfcsusb_ph_info(struct hfcsusb *hw);
+static int  hfcsusb_ph_info(struct hfcsusb *hw);
 
 /* start next background transfer for control channel */
 static void
@@ -241,7 +241,7 @@ hfcusb_l2l1B(struct mISDNchannel *ch, struct sk_buff *skb)
  * send full D/B channel status information
  * as MPH_INFORMATION_IND
  */
-static void
+static int
 hfcsusb_ph_info(struct hfcsusb *hw)
 {
 	struct ph_info *phi;
@@ -250,7 +250,7 @@ hfcsusb_ph_info(struct hfcsusb *hw)
 
 	phi = kzalloc(struct_size(phi, bch, dch->dev.nrbchan), GFP_ATOMIC);
 	if (!phi)
-		return;
+		return -ENOMEM;
 
 	phi->dch.ch.protocol = hw->protocol;
 	phi->dch.ch.Flags = dch->Flags;
@@ -263,6 +263,8 @@ hfcsusb_ph_info(struct hfcsusb *hw)
 	_queue_data(&dch->dev.D, MPH_INFORMATION_IND, MISDN_ID_ANY,
 		    struct_size(phi, bch, dch->dev.nrbchan), phi, GFP_ATOMIC);
 	kfree(phi);
+
+	return 0;
 }
 
 /*
@@ -347,8 +349,7 @@ hfcusb_l2l1D(struct mISDNchannel *ch, struct sk_buff *skb)
 			ret = l1_event(dch->l1, hh->prim);
 		break;
 	case MPH_INFORMATION_REQ:
-		hfcsusb_ph_info(hw);
+		ret = hfcsusb_ph_info(hw);
-		ret = 0;
 		break;
 	}
 
@@ -403,8 +404,7 @@ hfc_l1callback(struct dchannel *dch, u_int cmd)
 			       hw->name, __func__, cmd);
 		return -1;
 	}
-	hfcsusb_ph_info(hw);
+	return hfcsusb_ph_info(hw);
-	return 0;
 }
 
 static int
@@ -746,8 +746,7 @@ hfcsusb_setup_bch(struct bchannel *bch, int protocol)
 			handle_led(hw, (bch->nr == 1) ? LED_B1_OFF :
 				   LED_B2_OFF);
 	}
-	hfcsusb_ph_info(hw);
+	return hfcsusb_ph_info(hw);
-	return 0;
 }
 
 static void

drivers/isdn/hardware/mISDN/mISDNinfineon.c

@@ -630,17 +630,19 @@ static void
 release_io(struct inf_hw *hw)
 {
 	if (hw->cfg.mode) {
-		if (hw->cfg.p) {
+		if (hw->cfg.mode == AM_MEMIO) {
 			release_mem_region(hw->cfg.start, hw->cfg.size);
-			iounmap(hw->cfg.p);
+			if (hw->cfg.p)
+				iounmap(hw->cfg.p);
 		} else
 			release_region(hw->cfg.start, hw->cfg.size);
 		hw->cfg.mode = AM_NONE;
 	}
 	if (hw->addr.mode) {
-		if (hw->addr.p) {
+		if (hw->addr.mode == AM_MEMIO) {
 			release_mem_region(hw->addr.start, hw->addr.size);
-			iounmap(hw->addr.p);
+			if (hw->addr.p)
+				iounmap(hw->addr.p);
 		} else
 			release_region(hw->addr.start, hw->addr.size);
 		hw->addr.mode = AM_NONE;
@@ -670,9 +672,12 @@ setup_io(struct inf_hw *hw)
 				(ulong)hw->cfg.start, (ulong)hw->cfg.size);
 			return err;
 		}
-		if (hw->ci->cfg_mode == AM_MEMIO)
-			hw->cfg.p = ioremap(hw->cfg.start, hw->cfg.size);
 		hw->cfg.mode = hw->ci->cfg_mode;
+		if (hw->ci->cfg_mode == AM_MEMIO) {
+			hw->cfg.p = ioremap(hw->cfg.start, hw->cfg.size);
+			if (!hw->cfg.p)
+				return -ENOMEM;
+		}
 		if (debug & DEBUG_HW)
 			pr_notice("%s: IO cfg %lx (%lu bytes) mode%d\n",
 				  hw->name, (ulong)hw->cfg.start,
@@ -697,12 +702,12 @@ setup_io(struct inf_hw *hw)
 				(ulong)hw->addr.start, (ulong)hw->addr.size);
 			return err;
 		}
+		hw->addr.mode = hw->ci->addr_mode;
 		if (hw->ci->addr_mode == AM_MEMIO) {
 			hw->addr.p = ioremap(hw->addr.start, hw->addr.size);
-			if (unlikely(!hw->addr.p))
+			if (!hw->addr.p)
 				return -ENOMEM;
 		}
-		hw->addr.mode = hw->ci->addr_mode;
 		if (debug & DEBUG_HW)
 			pr_notice("%s: IO addr %lx (%lu bytes) mode%d\n",
 				  hw->name, (ulong)hw->addr.start,

drivers/leds/leds-lp5523.c

@@ -307,7 +307,7 @@ static int lp5523_init_program_engine(struct lp55xx_chip *chip)
 	usleep_range(3000, 6000);
 	ret = lp55xx_read(chip, LP5523_REG_STATUS, &status);
 	if (ret)
-		return ret;
+		goto out;
 	status &= LP5523_ENG_STATUS_MASK;
 
 	if (status != LP5523_ENG_STATUS_MASK) {

drivers/media/dvb-frontends/sp8870.c

@@ -281,7 +281,7 @@ static int sp8870_set_frontend_parameters(struct dvb_frontend *fe)
 
 	// read status reg in order to clear pending irqs
 	err = sp8870_readreg(state, 0x200);
-	if (err)
+	if (err < 0)
 		return err;
 
 	// system controller start

drivers/media/platform/rcar_drif.c

@@ -915,7 +915,6 @@ static int rcar_drif_g_fmt_sdr_cap(struct file *file, void *priv,
 {
 	struct rcar_drif_sdr *sdr = video_drvdata(file);
 
-	memset(f->fmt.sdr.reserved, 0, sizeof(f->fmt.sdr.reserved));
 	f->fmt.sdr.pixelformat = sdr->fmt->pixelformat;
 	f->fmt.sdr.buffersize = sdr->fmt->buffersize;
 

drivers/media/usb/gspca/cpia1.c

@@ -1424,7 +1424,6 @@ static int sd_config(struct gspca_dev *gspca_dev,
 {
 	struct sd *sd = (struct sd *) gspca_dev;
 	struct cam *cam;
-	int ret;
 
 	sd->mainsFreq = FREQ_DEF == V4L2_CID_POWER_LINE_FREQUENCY_60HZ;
 	reset_camera_params(gspca_dev);
@@ -1436,10 +1435,7 @@ static int sd_config(struct gspca_dev *gspca_dev,
 	cam->cam_mode = mode;
 	cam->nmodes = ARRAY_SIZE(mode);
 
-	ret = goto_low_power(gspca_dev);
+	goto_low_power(gspca_dev);
-	if (ret)
-		gspca_err(gspca_dev, "Cannot go to low power mode: %d\n",
-			  ret);
 	/* Check the firmware version. */
 	sd->params.version.firmwareVersion = 0;
 	get_version_information(gspca_dev);

drivers/media/usb/gspca/m5602/m5602_mt9m111.c

@@ -195,7 +195,7 @@ static const struct v4l2_ctrl_config mt9m111_greenbal_cfg = {
 int mt9m111_probe(struct sd *sd)
 {
 	u8 data[2] = {0x00, 0x00};
-	int i, rc = 0;
+	int i, err;
 	struct gspca_dev *gspca_dev = (struct gspca_dev *)sd;
 
 	if (force_sensor) {
@@ -213,18 +213,18 @@ int mt9m111_probe(struct sd *sd)
 	/* Do the preinit */
 	for (i = 0; i < ARRAY_SIZE(preinit_mt9m111); i++) {
 		if (preinit_mt9m111[i][0] == BRIDGE) {
-			rc |= m5602_write_bridge(sd,
+			err = m5602_write_bridge(sd,
-				preinit_mt9m111[i][1],
+					preinit_mt9m111[i][1],
-				preinit_mt9m111[i][2]);
+					preinit_mt9m111[i][2]);
 		} else {
 			data[0] = preinit_mt9m111[i][2];
 			data[1] = preinit_mt9m111[i][3];
-			rc |= m5602_write_sensor(sd,
+			err = m5602_write_sensor(sd,
-				preinit_mt9m111[i][1], data, 2);
+					preinit_mt9m111[i][1], data, 2);
 		}
+		if (err < 0)
+			return err;
 	}
-	if (rc < 0)
-		return rc;
 
 	if (m5602_read_sensor(sd, MT9M111_SC_CHIPVER, data, 2))
 		return -ENODEV;

drivers/media/usb/gspca/m5602/m5602_po1030.c

@@ -154,8 +154,8 @@ static const struct v4l2_ctrl_config po1030_greenbal_cfg = {
 
 int po1030_probe(struct sd *sd)
 {
-	int rc = 0;
 	u8 dev_id_h = 0, i;
+	int err;
 	struct gspca_dev *gspca_dev = (struct gspca_dev *)sd;
 
 	if (force_sensor) {
@@ -174,14 +174,14 @@ int po1030_probe(struct sd *sd)
 	for (i = 0; i < ARRAY_SIZE(preinit_po1030); i++) {
 		u8 data = preinit_po1030[i][2];
 		if (preinit_po1030[i][0] == SENSOR)
-			rc |= m5602_write_sensor(sd,
+			err = m5602_write_sensor(sd, preinit_po1030[i][1],
-				preinit_po1030[i][1], &data, 1);
+						 &data, 1);
 		else
-			rc |= m5602_write_bridge(sd, preinit_po1030[i][1],
+			err = m5602_write_bridge(sd, preinit_po1030[i][1],
-						data);
+						 data);
+		if (err < 0)
+			return err;
 	}
-	if (rc < 0)
-		return rc;
 
 	if (m5602_read_sensor(sd, PO1030_DEVID_H, &dev_id_h, 1))
 		return -ENODEV;

drivers/misc/eeprom/at24.c

@@ -763,7 +763,8 @@ static int at24_probe(struct i2c_client *client)
 	at24->nvmem = devm_nvmem_register(dev, &nvmem_config);
 	if (IS_ERR(at24->nvmem)) {
 		pm_runtime_disable(dev);
-		regulator_disable(at24->vcc_reg);
+		if (!pm_runtime_status_suspended(dev))
+			regulator_disable(at24->vcc_reg);
 		return PTR_ERR(at24->nvmem);
 	}
 
@@ -774,7 +775,8 @@ static int at24_probe(struct i2c_client *client)
 	err = at24_read(at24, 0, &test_byte, 1);
 	if (err) {
 		pm_runtime_disable(dev);
-		regulator_disable(at24->vcc_reg);
+		if (!pm_runtime_status_suspended(dev))
+			regulator_disable(at24->vcc_reg);
 		return -ENODEV;
 	}
 

drivers/misc/habanalabs/common/command_submission.c

@@ -2017,7 +2017,7 @@ wait_again:
 		if (completion_value >= target_value) {
 			*status = CS_WAIT_STATUS_COMPLETED;
 		} else {
-			timeout -= jiffies_to_usecs(completion_rc);
+			timeout = completion_rc;
 			goto wait_again;
 		}
 	} else {

drivers/misc/habanalabs/common/firmware_if.c

@@ -362,12 +362,9 @@ static int fw_read_errors(struct hl_device *hdev, u32 boot_err0_reg,
 	}
 
 	if (err_val & CPU_BOOT_ERR0_SECURITY_NOT_RDY) {
-		dev_warn(hdev->dev,
+		dev_err(hdev->dev,
 			"Device boot warning - security not ready\n");
-		/* This is a warning so we don't want it to disable the
+		err_exists = true;
-		 * device
-		 */
-		err_val &= ~CPU_BOOT_ERR0_SECURITY_NOT_RDY;
 	}
 
 	if (err_val & CPU_BOOT_ERR0_SECURITY_FAIL) {
@@ -403,7 +400,8 @@ static int fw_read_errors(struct hl_device *hdev, u32 boot_err0_reg,
 		err_exists = true;
 	}
 
-	if (err_exists)
+	if (err_exists && ((err_val & ~CPU_BOOT_ERR0_ENABLED) &
+				lower_32_bits(hdev->boot_error_status_mask)))
 		return -EIO;
 
 	return 0;
@@ -661,18 +659,13 @@ int hl_fw_cpucp_total_energy_get(struct hl_device *hdev, u64 *total_energy)
 	return rc;
 }
 
-int get_used_pll_index(struct hl_device *hdev, enum pll_index input_pll_index,
+int get_used_pll_index(struct hl_device *hdev, u32 input_pll_index,
 						enum pll_index *pll_index)
 {
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
 	u8 pll_byte, pll_bit_off;
 	bool dynamic_pll;
-
+	int fw_pll_idx;
-	if (input_pll_index >= PLL_MAX) {
-		dev_err(hdev->dev, "PLL index %d is out of range\n",
-							input_pll_index);
-		return -EINVAL;
-	}
 
 	dynamic_pll = prop->fw_security_status_valid &&
 		(prop->fw_app_security_map & CPU_BOOT_DEV_STS0_DYN_PLL_EN);
@@ -680,28 +673,39 @@ int get_used_pll_index(struct hl_device *hdev, enum pll_index input_pll_index,
 	if (!dynamic_pll) {
 		/*
 		 * in case we are working with legacy FW (each asic has unique
-		 * PLL numbering) extract the legacy numbering
+		 * PLL numbering) use the driver based index as they are
+		 * aligned with fw legacy numbering
 		 */
-		*pll_index = hdev->legacy_pll_map[input_pll_index];
+		*pll_index = input_pll_index;
 		return 0;
 	}
 
-	/* PLL map is a u8 array */
+	/* retrieve a FW compatible PLL index based on
-	pll_byte = prop->cpucp_info.pll_map[input_pll_index >> 3];
+	 * ASIC specific user request
-	pll_bit_off = input_pll_index & 0x7;
+	 */
-
+	fw_pll_idx = hdev->asic_funcs->map_pll_idx_to_fw_idx(input_pll_index);
-	if (!(pll_byte & BIT(pll_bit_off))) {
+	if (fw_pll_idx < 0) {
-		dev_err(hdev->dev, "PLL index %d is not supported\n",
+		dev_err(hdev->dev, "Invalid PLL index (%u) error %d\n",
-							input_pll_index);
+			input_pll_index, fw_pll_idx);
 		return -EINVAL;
 	}
 
-	*pll_index = input_pll_index;
+	/* PLL map is a u8 array */
+	pll_byte = prop->cpucp_info.pll_map[fw_pll_idx >> 3];
+	pll_bit_off = fw_pll_idx & 0x7;
+
+	if (!(pll_byte & BIT(pll_bit_off))) {
+		dev_err(hdev->dev, "PLL index %d is not supported\n",
+			fw_pll_idx);
+		return -EINVAL;
+	}
+
+	*pll_index = fw_pll_idx;
 
 	return 0;
 }
 
-int hl_fw_cpucp_pll_info_get(struct hl_device *hdev, enum pll_index pll_index,
+int hl_fw_cpucp_pll_info_get(struct hl_device *hdev, u32 pll_index,
 		u16 *pll_freq_arr)
 {
 	struct cpucp_packet pkt;
@@ -844,8 +848,13 @@ int hl_fw_read_preboot_status(struct hl_device *hdev, u32 cpu_boot_status_reg,
 	if (rc) {
 		dev_err(hdev->dev, "Failed to read preboot version\n");
 		detect_cpu_boot_status(hdev, status);
-		fw_read_errors(hdev, boot_err0_reg,
+
-				cpu_security_boot_status_reg);
+		/* If we read all FF, then something is totally wrong, no point
+		 * of reading specific errors
+		 */
+		if (status != -1)
+			fw_read_errors(hdev, boot_err0_reg,
+					cpu_security_boot_status_reg);
 		return -EIO;
 	}
 

drivers/misc/habanalabs/common/habanalabs.h

@@ -930,6 +930,9 @@ enum div_select_defs {
  *                         driver is ready to receive asynchronous events. This
  *                         function should be called during the first init and
  *                         after every hard-reset of the device
+ * @get_msi_info: Retrieve asic-specific MSI ID of the f/w async event
+ * @map_pll_idx_to_fw_idx: convert driver specific per asic PLL index to
+ *                         generic f/w compatible PLL Indexes
  */
 struct hl_asic_funcs {
 	int (*early_init)(struct hl_device *hdev);
@@ -1054,6 +1057,7 @@ struct hl_asic_funcs {
 			u32 block_id, u32 block_size);
 	void (*enable_events_from_fw)(struct hl_device *hdev);
 	void (*get_msi_info)(u32 *table);
+	int (*map_pll_idx_to_fw_idx)(u32 pll_idx);
 };
 
 
@@ -1950,8 +1954,6 @@ struct hl_mmu_funcs {
  * @aggregated_cs_counters: aggregated cs counters among all contexts
  * @mmu_priv: device-specific MMU data.
  * @mmu_func: device-related MMU functions.
- * @legacy_pll_map: map holding map between dynamic (common) PLL indexes and
- *                  static (asic specific) PLL indexes.
  * @dram_used_mem: current DRAM memory consumption.
  * @timeout_jiffies: device CS timeout value.
  * @max_power: the max power of the device, as configured by the sysadmin. This
@@ -1960,6 +1962,12 @@ struct hl_mmu_funcs {
  * @clock_gating_mask: is clock gating enabled. bitmask that represents the
  *                     different engines. See debugfs-driver-habanalabs for
  *                     details.
+ * @boot_error_status_mask: contains a mask of the device boot error status.
+ *                          Each bit represents a different error, according to
+ *                          the defines in hl_boot_if.h. If the bit is cleared,
+ *                          the error will be ignored by the driver during
+ *                          device initialization. Mainly used to debug and
+ *                          workaround firmware bugs
  * @in_reset: is device in reset flow.
  * @curr_pll_profile: current PLL profile.
  * @card_type: Various ASICs have several card types. This indicates the card
@@ -2071,12 +2079,11 @@ struct hl_device {
 	struct hl_mmu_priv		mmu_priv;
 	struct hl_mmu_funcs		mmu_func[MMU_NUM_PGT_LOCATIONS];
 
-	enum pll_index			*legacy_pll_map;
-
 	atomic64_t			dram_used_mem;
 	u64				timeout_jiffies;
 	u64				max_power;
 	u64				clock_gating_mask;
+	u64				boot_error_status_mask;
 	atomic_t			in_reset;
 	enum hl_pll_frequency		curr_pll_profile;
 	enum cpucp_card_types		card_type;
@@ -2387,9 +2394,9 @@ int hl_fw_cpucp_pci_counters_get(struct hl_device *hdev,
 		struct hl_info_pci_counters *counters);
 int hl_fw_cpucp_total_energy_get(struct hl_device *hdev,
 			u64 *total_energy);
-int get_used_pll_index(struct hl_device *hdev, enum pll_index input_pll_index,
+int get_used_pll_index(struct hl_device *hdev, u32 input_pll_index,
 						enum pll_index *pll_index);
-int hl_fw_cpucp_pll_info_get(struct hl_device *hdev, enum pll_index pll_index,
+int hl_fw_cpucp_pll_info_get(struct hl_device *hdev, u32 pll_index,
 		u16 *pll_freq_arr);
 int hl_fw_cpucp_power_get(struct hl_device *hdev, u64 *power);
 int hl_fw_init_cpu(struct hl_device *hdev, u32 cpu_boot_status_reg,
@@ -2411,9 +2418,9 @@ int hl_pci_set_outbound_region(struct hl_device *hdev,
 int hl_pci_init(struct hl_device *hdev);
 void hl_pci_fini(struct hl_device *hdev);
 
-long hl_get_frequency(struct hl_device *hdev, enum pll_index pll_index,
+long hl_get_frequency(struct hl_device *hdev, u32 pll_index,
 								bool curr);
-void hl_set_frequency(struct hl_device *hdev, enum pll_index pll_index,
+void hl_set_frequency(struct hl_device *hdev, u32 pll_index,
 								u64 freq);
 int hl_get_temperature(struct hl_device *hdev,
 		       int sensor_index, u32 attr, long *value);

drivers/misc/habanalabs/common/habanalabs_drv.c

@@ -30,6 +30,7 @@ static DEFINE_MUTEX(hl_devs_idr_lock);
 static int timeout_locked = 30;
 static int reset_on_lockup = 1;
 static int memory_scrub = 1;
+static ulong boot_error_status_mask = ULONG_MAX;
 
 module_param(timeout_locked, int, 0444);
 MODULE_PARM_DESC(timeout_locked,
@@ -43,6 +44,10 @@ module_param(memory_scrub, int, 0444);
 MODULE_PARM_DESC(memory_scrub,
 	"Scrub device memory in various states (0 = no, 1 = yes, default yes)");
 
+module_param(boot_error_status_mask, ulong, 0444);
+MODULE_PARM_DESC(boot_error_status_mask,
+	"Mask of the error status during device CPU boot (If bitX is cleared then error X is masked. Default all 1's)");
+
 #define PCI_VENDOR_ID_HABANALABS	0x1da3
 
 #define PCI_IDS_GOYA			0x0001
@@ -319,6 +324,8 @@ int create_hdev(struct hl_device **dev, struct pci_dev *pdev,
 	hdev->major = hl_major;
 	hdev->reset_on_lockup = reset_on_lockup;
 	hdev->memory_scrub = memory_scrub;
+	hdev->boot_error_status_mask = boot_error_status_mask;
+
 	hdev->pldm = 0;
 
 	set_driver_behavior_per_device(hdev);

drivers/misc/habanalabs/common/sysfs.c

@@ -9,7 +9,7 @@
 
 #include <linux/pci.h>
 
-long hl_get_frequency(struct hl_device *hdev, enum pll_index pll_index,
+long hl_get_frequency(struct hl_device *hdev, u32 pll_index,
 								bool curr)
 {
 	struct cpucp_packet pkt;
@@ -44,7 +44,7 @@ long hl_get_frequency(struct hl_device *hdev, enum pll_index pll_index,
 	return (long) result;
 }
 
-void hl_set_frequency(struct hl_device *hdev, enum pll_index pll_index,
+void hl_set_frequency(struct hl_device *hdev, u32 pll_index,
 								u64 freq)
 {
 	struct cpucp_packet pkt;