Commit 7e1c07dd authored by Oded Gabbay's avatar Oded Gabbay
Browse files

habanalabs: unify and improve device cpu init 



Move the code of device CPU initialization from being ASIC-Dependent to
common code. In addition, add support for the new error reporting feature
of the firmware boot code.

Reviewed-by: default avatarOmer Shpigelman <oshpigelman@habana.ai>
Signed-off-by: default avatarOded Gabbay <oded.gabbay@gmail.com>
parent 1fa185c6

drivers/misc/habanalabs/firmware_if.c

+186 −2
Original line number Diff line number Diff line
@@ -6,20 +6,21 @@ 
 */



#include "habanalabs.h"

#include "include/hl_boot_if.h"



#include <linux/firmware.h>

#include <linux/genalloc.h>

#include <linux/io-64-nonatomic-lo-hi.h>



/**

 * hl_fw_push_fw_to_device() - Push FW code to device.

 * hl_fw_load_fw_to_device() - Load F/W code to device's memory.

 * @hdev: pointer to hl_device structure.

 *

 * Copy fw code from firmware file to device memory.

 *

 * Return: 0 on success, non-zero for failure.

 */

int hl_fw_push_fw_to_device(struct hl_device *hdev, const char *fw_name,

int hl_fw_load_fw_to_device(struct hl_device *hdev, const char *fw_name,

				void __iomem *dst)

{

	const struct firmware *fw;
@@ -286,3 +287,186 @@ int hl_fw_get_eeprom_data(struct hl_device *hdev, void *data, size_t max_size) 


	return rc;

}



static void fw_read_errors(struct hl_device *hdev, u32 boot_err0_reg)

{

	u32 err_val;



	/* Some of the firmware status codes are deprecated in newer f/w

	 * versions. In those versions, the errors are reported

	 * in different registers. Therefore, we need to check those

	 * registers and print the exact errors. Moreover, there

	 * may be multiple errors, so we need to report on each error

	 * separately. Some of the error codes might indicate a state

	 * that is not an error per-se, but it is an error in production

	 * environment

	 */

	err_val = RREG32(boot_err0_reg);

	if (!(err_val & CPU_BOOT_ERR0_ENABLED))

		return;



	if (err_val & CPU_BOOT_ERR0_DRAM_INIT_FAIL)

		dev_err(hdev->dev,

			"Device boot error - DRAM initialization failed\n");

	if (err_val & CPU_BOOT_ERR0_FIT_CORRUPTED)

		dev_err(hdev->dev, "Device boot error - FIT image corrupted\n");

	if (err_val & CPU_BOOT_ERR0_TS_INIT_FAIL)

		dev_err(hdev->dev,

			"Device boot error - Thermal Sensor initialization failed\n");

	if (err_val & CPU_BOOT_ERR0_DRAM_SKIPPED)

		dev_warn(hdev->dev,

			"Device boot warning - Skipped DRAM initialization\n");

	if (err_val & CPU_BOOT_ERR0_BMC_WAIT_SKIPPED)

		dev_warn(hdev->dev,

			"Device boot error - Skipped waiting for BMC\n");

	if (err_val & CPU_BOOT_ERR0_NIC_DATA_NOT_RDY)

		dev_err(hdev->dev,

			"Device boot error - Serdes data from BMC not available\n");

	if (err_val & CPU_BOOT_ERR0_NIC_FW_FAIL)

		dev_err(hdev->dev,

			"Device boot error - NIC F/W initialization failed\n");

}



int hl_fw_init_cpu(struct hl_device *hdev, u32 cpu_boot_status_reg,

			u32 msg_to_cpu_reg, u32 boot_err0_reg, bool skip_bmc,

			u32 cpu_timeout)

{

	u32 status;

	int rc;



	dev_info(hdev->dev, "Going to wait for device boot (up to %lds)\n",

		cpu_timeout / USEC_PER_SEC);



	/* Make sure CPU boot-loader is running */

	rc = hl_poll_timeout(

		hdev,

		cpu_boot_status_reg,

		status,

		(status == CPU_BOOT_STATUS_DRAM_RDY) ||

		(status == CPU_BOOT_STATUS_NIC_FW_RDY) ||

		(status == CPU_BOOT_STATUS_READY_TO_BOOT) ||

		(status == CPU_BOOT_STATUS_SRAM_AVAIL),

		10000,

		cpu_timeout);



	/* Read U-Boot, preboot versions now in case we will later fail */

	hdev->asic_funcs->read_device_fw_version(hdev, FW_COMP_UBOOT);

	hdev->asic_funcs->read_device_fw_version(hdev, FW_COMP_PREBOOT);



	/* Some of the status codes below are deprecated in newer f/w

	 * versions but we keep them here for backward compatibility

	 */

	if (rc) {

		switch (status) {

		case CPU_BOOT_STATUS_NA:

			dev_err(hdev->dev,

				"Device boot error - BTL did NOT run\n");

			break;

		case CPU_BOOT_STATUS_IN_WFE:

			dev_err(hdev->dev,

				"Device boot error - Stuck inside WFE loop\n");

			break;

		case CPU_BOOT_STATUS_IN_BTL:

			dev_err(hdev->dev,

				"Device boot error - Stuck in BTL\n");

			break;

		case CPU_BOOT_STATUS_IN_PREBOOT:

			dev_err(hdev->dev,

				"Device boot error - Stuck in Preboot\n");

			break;

		case CPU_BOOT_STATUS_IN_SPL:

			dev_err(hdev->dev,

				"Device boot error - Stuck in SPL\n");

			break;

		case CPU_BOOT_STATUS_IN_UBOOT:

			dev_err(hdev->dev,

				"Device boot error - Stuck in u-boot\n");

			break;

		case CPU_BOOT_STATUS_DRAM_INIT_FAIL:

			dev_err(hdev->dev,

				"Device boot error - DRAM initialization failed\n");

			break;

		case CPU_BOOT_STATUS_UBOOT_NOT_READY:

			dev_err(hdev->dev,

				"Device boot error - u-boot stopped by user\n");

			break;

		case CPU_BOOT_STATUS_TS_INIT_FAIL:

			dev_err(hdev->dev,

				"Device boot error - Thermal Sensor initialization failed\n");

			break;

		default:

			dev_err(hdev->dev,

				"Device boot error - Invalid status code\n");

			break;

		}



		rc = -EIO;

		goto out;

	}



	if (!hdev->fw_loading) {

		dev_info(hdev->dev, "Skip loading FW\n");

		goto out;

	}



	if (status == CPU_BOOT_STATUS_SRAM_AVAIL)

		goto out;



	dev_info(hdev->dev,

		"Loading firmware to device, may take some time...\n");



	rc = hdev->asic_funcs->load_firmware_to_device(hdev);

	if (rc)

		goto out;



	if (skip_bmc) {

		WREG32(msg_to_cpu_reg, KMD_MSG_SKIP_BMC);



		rc = hl_poll_timeout(

			hdev,

			cpu_boot_status_reg,

			status,

			(status == CPU_BOOT_STATUS_BMC_WAITING_SKIPPED),

			10000,

			cpu_timeout);



		if (rc) {

			dev_err(hdev->dev,

				"Failed to get ACK on skipping BMC, %d\n",

				status);

			WREG32(msg_to_cpu_reg, KMD_MSG_NA);

			rc = -EIO;

			goto out;

		}

	}



	WREG32(msg_to_cpu_reg, KMD_MSG_FIT_RDY);



	rc = hl_poll_timeout(

		hdev,

		cpu_boot_status_reg,

		status,

		(status == CPU_BOOT_STATUS_SRAM_AVAIL),

		10000,

		cpu_timeout);



	if (rc) {

		if (status == CPU_BOOT_STATUS_FIT_CORRUPTED)

			dev_err(hdev->dev,

				"Device reports FIT image is corrupted\n");

		else

			dev_err(hdev->dev,

				"Device failed to load, %d\n", status);



		WREG32(msg_to_cpu_reg, KMD_MSG_NA);

		rc = -EIO;

		goto out;

	}



	dev_info(hdev->dev, "Successfully loaded firmware to device\n");



out:

	fw_read_errors(hdev, boot_err0_reg);



	return rc;

}

drivers/misc/habanalabs/goya/goya.c

+12 −104
Original line number Diff line number Diff line
@@ -2223,24 +2223,24 @@ static int goya_push_uboot_to_device(struct hl_device *hdev) 


	dst = hdev->pcie_bar[SRAM_CFG_BAR_ID] + UBOOT_FW_OFFSET;



	return hl_fw_push_fw_to_device(hdev, GOYA_UBOOT_FW_FILE, dst);

	return hl_fw_load_fw_to_device(hdev, GOYA_UBOOT_FW_FILE, dst);

}



/*

 * goya_push_linux_to_device() - Push LINUX FW code to device.

 * goya_load_firmware_to_device() - Load LINUX FW code to device.

 * @hdev: Pointer to hl_device structure.

 *

 * Copy LINUX fw code from firmware file to HBM BAR.

 *

 * Return: 0 on success, non-zero for failure.

 */

static int goya_push_linux_to_device(struct hl_device *hdev)

static int goya_load_firmware_to_device(struct hl_device *hdev)

{

	void __iomem *dst;



	dst = hdev->pcie_bar[DDR_BAR_ID] + LINUX_FW_OFFSET;



	return hl_fw_push_fw_to_device(hdev, GOYA_LINUX_FW_FILE, dst);

	return hl_fw_load_fw_to_device(hdev, GOYA_LINUX_FW_FILE, dst);

}



static int goya_pldm_init_cpu(struct hl_device *hdev)
@@ -2266,7 +2266,7 @@ static int goya_pldm_init_cpu(struct hl_device *hdev) 
	if (rc)

		return rc;



	rc = goya_push_linux_to_device(hdev);

	rc = goya_load_firmware_to_device(hdev);

	if (rc)

		return rc;
@@ -2291,7 +2291,7 @@ static int goya_pldm_init_cpu(struct hl_device *hdev) 
 * The version string should be located by that offset.

 */

static void goya_read_device_fw_version(struct hl_device *hdev,

					enum goya_fw_component fwc)

					enum hl_fw_component fwc)

{

	const char *name;

	u32 ver_off;
@@ -2328,7 +2328,6 @@ static void goya_read_device_fw_version(struct hl_device *hdev, 
static int goya_init_cpu(struct hl_device *hdev, u32 cpu_timeout)

{

	struct goya_device *goya = hdev->asic_specific;

	u32 status;

	int rc;



	if (!hdev->cpu_enable)
@@ -2355,106 +2354,13 @@ static int goya_init_cpu(struct hl_device *hdev, u32 cpu_timeout) 
		goto out;

	}



	/* Make sure CPU boot-loader is running */

	rc = hl_poll_timeout(

		hdev,

		mmPSOC_GLOBAL_CONF_WARM_REBOOT,

		status,

		(status == CPU_BOOT_STATUS_DRAM_RDY) ||

		(status == CPU_BOOT_STATUS_SRAM_AVAIL),

		10000,

		cpu_timeout);



	/* Read U-Boot version now in case we will later fail */

	goya_read_device_fw_version(hdev, FW_COMP_UBOOT);

	goya_read_device_fw_version(hdev, FW_COMP_PREBOOT);



	if (rc) {

		dev_err(hdev->dev, "Error in ARM u-boot!");

		switch (status) {

		case CPU_BOOT_STATUS_NA:

			dev_err(hdev->dev,

				"ARM status %d - BTL did NOT run\n", status);

			break;

		case CPU_BOOT_STATUS_IN_WFE:

			dev_err(hdev->dev,

				"ARM status %d - Inside WFE loop\n", status);

			break;

		case CPU_BOOT_STATUS_IN_BTL:

			dev_err(hdev->dev,

				"ARM status %d - Stuck in BTL\n", status);

			break;

		case CPU_BOOT_STATUS_IN_PREBOOT:

			dev_err(hdev->dev,

				"ARM status %d - Stuck in Preboot\n", status);

			break;

		case CPU_BOOT_STATUS_IN_SPL:

			dev_err(hdev->dev,

				"ARM status %d - Stuck in SPL\n", status);

			break;

		case CPU_BOOT_STATUS_IN_UBOOT:

			dev_err(hdev->dev,

				"ARM status %d - Stuck in u-boot\n", status);

			break;

		case CPU_BOOT_STATUS_DRAM_INIT_FAIL:

			dev_err(hdev->dev,

				"ARM status %d - DDR initialization failed\n",

				status);

			break;

		case CPU_BOOT_STATUS_UBOOT_NOT_READY:

			dev_err(hdev->dev,

				"ARM status %d - u-boot stopped by user\n",

				status);

			break;

		case CPU_BOOT_STATUS_TS_INIT_FAIL:

			dev_err(hdev->dev,

				"ARM status %d - Thermal Sensor initialization failed\n",

				status);

			break;

		default:

			dev_err(hdev->dev,

				"ARM status %d - Invalid status code\n",

				status);

			break;

		}

		return -EIO;

	}



	if (!hdev->fw_loading) {

		dev_info(hdev->dev, "Skip loading FW\n");

		goto out;

	}



	if (status == CPU_BOOT_STATUS_SRAM_AVAIL)

		goto out;

	rc = hl_fw_init_cpu(hdev, mmPSOC_GLOBAL_CONF_CPU_BOOT_STATUS,

			mmPSOC_GLOBAL_CONF_UBOOT_MAGIC, mmCPU_BOOT_ERR0,

			false, cpu_timeout);



	rc = goya_push_linux_to_device(hdev);

	if (rc)

		return rc;



	WREG32(mmPSOC_GLOBAL_CONF_UBOOT_MAGIC, KMD_MSG_FIT_RDY);



	rc = hl_poll_timeout(

		hdev,

		mmPSOC_GLOBAL_CONF_WARM_REBOOT,

		status,

		(status == CPU_BOOT_STATUS_SRAM_AVAIL),

		10000,

		cpu_timeout);



	if (rc) {

		if (status == CPU_BOOT_STATUS_FIT_CORRUPTED)

			dev_err(hdev->dev,

				"ARM u-boot reports FIT image is corrupted\n");

		else

			dev_err(hdev->dev,

				"ARM Linux failed to load, %d\n", status);

		WREG32(mmPSOC_GLOBAL_CONF_UBOOT_MAGIC, KMD_MSG_NA);

		return -EIO;

	}



	dev_info(hdev->dev, "Successfully loaded firmware to device\n");



out:

	goya->hw_cap_initialized |= HW_CAP_CPU;
@@ -5339,7 +5245,9 @@ static const struct hl_asic_funcs goya_funcs = { 
	.wreg = hl_wreg,

	.halt_coresight = goya_halt_coresight,

	.get_clk_rate = goya_get_clk_rate,

	.get_queue_id_for_cq = goya_get_queue_id_for_cq

	.get_queue_id_for_cq = goya_get_queue_id_for_cq,

	.read_device_fw_version = goya_read_device_fw_version,

	.load_firmware_to_device = goya_load_firmware_to_device

};



/*

drivers/misc/habanalabs/goya/goyaP.h

+0 −5
Original line number Diff line number Diff line
@@ -149,11 +149,6 @@ 
#define HW_CAP_GOLDEN		0x00000400

#define HW_CAP_TPC		0x00000800



enum goya_fw_component {

	FW_COMP_UBOOT,

	FW_COMP_PREBOOT

};



struct goya_device {

	/* TODO: remove hw_queues_lock after moving to scheduler code */

	spinlock_t	hw_queues_lock;

drivers/misc/habanalabs/habanalabs.h

+20 −1
Original line number Diff line number Diff line
@@ -75,6 +75,16 @@ struct pgt_info { 
struct hl_device;

struct hl_fpriv;



/**

 * enum hl_fw_component - F/W components to read version through registers.

 * @FW_COMP_UBOOT: u-boot.

 * @FW_COMP_PREBOOT: preboot.

 */

enum hl_fw_component {

	FW_COMP_UBOOT,

	FW_COMP_PREBOOT

};



/**

 * enum hl_queue_type - Supported QUEUE types.

 * @QUEUE_TYPE_NA: queue is not available.
@@ -539,6 +549,9 @@ enum hl_pll_frequency { 
 * @halt_coresight: stop the ETF and ETR traces.

 * @get_clk_rate: Retrieve the ASIC current and maximum clock rate in MHz

 * @get_queue_id_for_cq: Get the H/W queue id related to the given CQ index.

 * @read_device_fw_version: read the device's firmware versions that are

 *                          contained in registers

 * @load_firmware_to_device: load the firmware to the device's memory

 */

struct hl_asic_funcs {

	int (*early_init)(struct hl_device *hdev);
@@ -626,6 +639,9 @@ struct hl_asic_funcs { 
	void (*halt_coresight)(struct hl_device *hdev);

	int (*get_clk_rate)(struct hl_device *hdev, u32 *cur_clk, u32 *max_clk);

	u32 (*get_queue_id_for_cq)(struct hl_device *hdev, u32 cq_idx);

	void (*read_device_fw_version)(struct hl_device *hdev,

					enum hl_fw_component fwc);

	int (*load_firmware_to_device)(struct hl_device *hdev);

};
@@ -1591,7 +1607,7 @@ int hl_mmu_unmap(struct hl_ctx *ctx, u64 virt_addr, u32 page_size, 
void hl_mmu_swap_out(struct hl_ctx *ctx);

void hl_mmu_swap_in(struct hl_ctx *ctx);



int hl_fw_push_fw_to_device(struct hl_device *hdev, const char *fw_name,

int hl_fw_load_fw_to_device(struct hl_device *hdev, const char *fw_name,

				void __iomem *dst);

int hl_fw_send_pci_access_msg(struct hl_device *hdev, u32 opcode);

int hl_fw_send_cpu_message(struct hl_device *hdev, u32 hw_queue_id, u32 *msg,
@@ -1604,6 +1620,9 @@ void hl_fw_cpu_accessible_dma_pool_free(struct hl_device *hdev, size_t size, 
int hl_fw_send_heartbeat(struct hl_device *hdev);

int hl_fw_armcp_info_get(struct hl_device *hdev);

int hl_fw_get_eeprom_data(struct hl_device *hdev, void *data, size_t max_size);

int hl_fw_init_cpu(struct hl_device *hdev, u32 cpu_boot_status_reg,

			u32 msg_to_cpu_reg, u32 boot_err0_reg, bool skip_bmc,

			u32 cpu_timeout);



int hl_pci_bars_map(struct hl_device *hdev, const char * const name[3],

			bool is_wc[3]);

drivers/misc/habanalabs/include/hl_boot_if.h

+2 −1
Original line number Diff line number Diff line
@@ -42,7 +42,8 @@ enum cpu_boot_status { 
enum kmd_msg {

	KMD_MSG_NA = 0,

	KMD_MSG_GOTO_WFE,

	KMD_MSG_FIT_RDY

	KMD_MSG_FIT_RDY,

	KMD_MSG_SKIP_BMC,

};



#endif /* HL_BOOT_IF_H */