habanalabs: Move device CPU code into common file

This patch moves the code that is responsible of the communication
vs. the F/W to a dedicated file. This will allow us to share the code
between different ASICs.
Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>

drivers/misc/habanalabs/Makefile

@@ -6,7 +6,7 @@ obj-m	:= habanalabs.o
 
 habanalabs-y := habanalabs_drv.o device.o context.o asid.o habanalabs_ioctl.o \
 		command_buffer.o hw_queue.o irq.o sysfs.o hwmon.o memory.o \
-		command_submission.o mmu.o
+		command_submission.o mmu.o firmware_if.o
 
 habanalabs-$(CONFIG_DEBUG_FS) += debugfs.o
 

drivers/misc/habanalabs/firmware_if.c

+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2016-2019 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ */
+
+#include "habanalabs.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.
+ * @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,
+				void __iomem *dst)
+{
+	const struct firmware *fw;
+	const u64 *fw_data;
+	size_t fw_size, i;
+	int rc;
+
+	rc = request_firmware(&fw, fw_name, hdev->dev);
+	if (rc) {
+		dev_err(hdev->dev, "Failed to request %s\n", fw_name);
+		goto out;
+	}
+
+	fw_size = fw->size;
+	if ((fw_size % 4) != 0) {
+		dev_err(hdev->dev, "illegal %s firmware size %zu\n",
+			fw_name, fw_size);
+		rc = -EINVAL;
+		goto out;
+	}
+
+	dev_dbg(hdev->dev, "%s firmware size == %zu\n", fw_name, fw_size);
+
+	fw_data = (const u64 *) fw->data;
+
+	if ((fw->size % 8) != 0)
+		fw_size -= 8;
+
+	for (i = 0 ; i < fw_size ; i += 8, fw_data++, dst += 8) {
+		if (!(i & (0x80000 - 1))) {
+			dev_dbg(hdev->dev,
+				"copied so far %zu out of %zu for %s firmware",
+				i, fw_size, fw_name);
+			usleep_range(20, 100);
+		}
+
+		writeq(*fw_data, dst);
+	}
+
+	if ((fw->size % 8) != 0)
+		writel(*(const u32 *) fw_data, dst);
+
+out:
+	release_firmware(fw);
+	return rc;
+}
+
+int hl_fw_send_pci_access_msg(struct hl_device *hdev, u32 opcode)
+{
+	struct armcp_packet pkt = {};
+
+	pkt.ctl = cpu_to_le32(opcode << ARMCP_PKT_CTL_OPCODE_SHIFT);
+
+	return hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt,
+				sizeof(pkt), HL_DEVICE_TIMEOUT_USEC, NULL);
+}
+
+int hl_fw_send_cpu_message(struct hl_device *hdev, u32 hw_queue_id, u32 *msg,
+				u16 len, u32 timeout, long *result)
+{
+	struct armcp_packet *pkt;
+	dma_addr_t pkt_dma_addr;
+	u32 tmp;
+	int rc = 0;
+
+	if (len > HL_CPU_CB_SIZE) {
+		dev_err(hdev->dev, "Invalid CPU message size of %d bytes\n",
+			len);
+		return -ENOMEM;
+	}
+
+	pkt = hdev->asic_funcs->cpu_accessible_dma_pool_alloc(hdev, len,
+								&pkt_dma_addr);
+	if (!pkt) {
+		dev_err(hdev->dev,
+			"Failed to allocate DMA memory for packet to CPU\n");
+		return -ENOMEM;
+	}
+
+	memcpy(pkt, msg, len);
+
+	mutex_lock(&hdev->send_cpu_message_lock);
+
+	if (hdev->disabled)
+		goto out;
+
+	if (hdev->device_cpu_disabled) {
+		rc = -EIO;
+		goto out;
+	}
+
+	rc = hl_hw_queue_send_cb_no_cmpl(hdev, hw_queue_id, len, pkt_dma_addr);
+	if (rc) {
+		dev_err(hdev->dev, "Failed to send CB on CPU PQ (%d)\n", rc);
+		goto out;
+	}
+
+	rc = hl_poll_timeout_memory(hdev, (u64) (uintptr_t) &pkt->fence,
+					timeout, &tmp);
+
+	hl_hw_queue_inc_ci_kernel(hdev, hw_queue_id);
+
+	if (rc == -ETIMEDOUT) {
+		dev_err(hdev->dev, "Timeout while waiting for device CPU\n");
+		hdev->device_cpu_disabled = true;
+		goto out;
+	}
+
+	if (tmp == ARMCP_PACKET_FENCE_VAL) {
+		u32 ctl = le32_to_cpu(pkt->ctl);
+
+		rc = (ctl & ARMCP_PKT_CTL_RC_MASK) >> ARMCP_PKT_CTL_RC_SHIFT;
+		if (rc) {
+			dev_err(hdev->dev,
+				"F/W ERROR %d for CPU packet %d\n",
+				rc, (ctl & ARMCP_PKT_CTL_OPCODE_MASK)
+						>> ARMCP_PKT_CTL_OPCODE_SHIFT);
+			rc = -EINVAL;
+		} else if (result) {
+			*result = (long) le64_to_cpu(pkt->result);
+		}
+	} else {
+		dev_err(hdev->dev, "CPU packet wrong fence value\n");
+		rc = -EINVAL;
+	}
+
+out:
+	mutex_unlock(&hdev->send_cpu_message_lock);
+
+	hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev, len, pkt);
+
+	return rc;
+}
+
+int hl_fw_test_cpu_queue(struct hl_device *hdev)
+{
+	struct armcp_packet test_pkt = {};
+	long result;
+	int rc;
+
+	test_pkt.ctl = cpu_to_le32(ARMCP_PACKET_TEST <<
+					ARMCP_PKT_CTL_OPCODE_SHIFT);
+	test_pkt.value = cpu_to_le64(ARMCP_PACKET_FENCE_VAL);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &test_pkt,
+			sizeof(test_pkt), HL_DEVICE_TIMEOUT_USEC, &result);
+
+	if (!rc) {
+		if (result == ARMCP_PACKET_FENCE_VAL)
+			dev_info(hdev->dev,
+				"queue test on CPU queue succeeded\n");
+		else
+			dev_err(hdev->dev,
+				"CPU queue test failed (0x%08lX)\n", result);
+	} else {
+		dev_err(hdev->dev, "CPU queue test failed, error %d\n", rc);
+	}
+
+	return rc;
+}
+
+void *hl_fw_cpu_accessible_dma_pool_alloc(struct hl_device *hdev, size_t size,
+						dma_addr_t *dma_handle)
+{
+	u64 kernel_addr;
+
+	/* roundup to HL_CPU_PKT_SIZE */
+	size = (size + (HL_CPU_PKT_SIZE - 1)) & HL_CPU_PKT_MASK;
+
+	kernel_addr = gen_pool_alloc(hdev->cpu_accessible_dma_pool, size);
+
+	*dma_handle = hdev->cpu_accessible_dma_address +
+		(kernel_addr - (u64) (uintptr_t) hdev->cpu_accessible_dma_mem);
+
+	return (void *) (uintptr_t) kernel_addr;
+}
+
+void hl_fw_cpu_accessible_dma_pool_free(struct hl_device *hdev, size_t size,
+					void *vaddr)
+{
+	/* roundup to HL_CPU_PKT_SIZE */
+	size = (size + (HL_CPU_PKT_SIZE - 1)) & HL_CPU_PKT_MASK;
+
+	gen_pool_free(hdev->cpu_accessible_dma_pool, (u64) (uintptr_t) vaddr,
+			size);
+}
+
+int hl_fw_send_heartbeat(struct hl_device *hdev)
+{
+	struct armcp_packet hb_pkt = {};
+	long result;
+	int rc;
+
+	hb_pkt.ctl = cpu_to_le32(ARMCP_PACKET_TEST <<
+					ARMCP_PKT_CTL_OPCODE_SHIFT);
+	hb_pkt.value = cpu_to_le64(ARMCP_PACKET_FENCE_VAL);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &hb_pkt,
+			sizeof(hb_pkt), HL_DEVICE_TIMEOUT_USEC, &result);
+
+	if ((rc) || (result != ARMCP_PACKET_FENCE_VAL))
+		rc = -EIO;
+
+	return rc;
+}
+
+int hl_fw_armcp_info_get(struct hl_device *hdev)
+{
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	struct armcp_packet pkt = {};
+	void *armcp_info_cpu_addr;
+	dma_addr_t armcp_info_dma_addr;
+	long result;
+	int rc;
+
+	armcp_info_cpu_addr =
+			hdev->asic_funcs->cpu_accessible_dma_pool_alloc(hdev,
+					sizeof(struct armcp_info),
+					&armcp_info_dma_addr);
+	if (!armcp_info_cpu_addr) {
+		dev_err(hdev->dev,
+			"Failed to allocate DMA memory for ArmCP info packet\n");
+		return -ENOMEM;
+	}
+
+	memset(armcp_info_cpu_addr, 0, sizeof(struct armcp_info));
+
+	pkt.ctl = cpu_to_le32(ARMCP_PACKET_INFO_GET <<
+				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.addr = cpu_to_le64(armcp_info_dma_addr +
+				prop->host_phys_base_address);
+	pkt.data_max_size = cpu_to_le32(sizeof(struct armcp_info));
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
+					HL_ARMCP_INFO_TIMEOUT_USEC, &result);
+	if (rc) {
+		dev_err(hdev->dev,
+			"Failed to send armcp info pkt, error %d\n", rc);
+		goto out;
+	}
+
+	memcpy(&prop->armcp_info, armcp_info_cpu_addr,
+			sizeof(prop->armcp_info));
+
+	rc = hl_build_hwmon_channel_info(hdev, prop->armcp_info.sensors);
+	if (rc) {
+		dev_err(hdev->dev,
+			"Failed to build hwmon channel info, error %d\n", rc);
+		rc = -EFAULT;
+		goto out;
+	}
+
+out:
+	hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev,
+			sizeof(struct armcp_info), armcp_info_cpu_addr);
+
+	return rc;
+}
+
+int hl_fw_get_eeprom_data(struct hl_device *hdev, void *data, size_t max_size)
+{
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	struct armcp_packet pkt = {};
+	void *eeprom_info_cpu_addr;
+	dma_addr_t eeprom_info_dma_addr;
+	long result;
+	int rc;
+
+	eeprom_info_cpu_addr =
+			hdev->asic_funcs->cpu_accessible_dma_pool_alloc(hdev,
+					max_size, &eeprom_info_dma_addr);
+	if (!eeprom_info_cpu_addr) {
+		dev_err(hdev->dev,
+			"Failed to allocate DMA memory for EEPROM info packet\n");
+		return -ENOMEM;
+	}
+
+	memset(eeprom_info_cpu_addr, 0, max_size);
+
+	pkt.ctl = cpu_to_le32(ARMCP_PACKET_EEPROM_DATA_GET <<
+				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.addr = cpu_to_le64(eeprom_info_dma_addr +
+				prop->host_phys_base_address);
+	pkt.data_max_size = cpu_to_le32(max_size);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
+			HL_ARMCP_EEPROM_TIMEOUT_USEC, &result);
+
+	if (rc) {
+		dev_err(hdev->dev,
+			"Failed to send armcp EEPROM pkt, error %d\n", rc);
+		goto out;
+	}
+
+	/* result contains the actual size */
+	memcpy(data, eeprom_info_cpu_addr, min((size_t)result, max_size));
+
+out:
+	hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev, max_size,
+			eeprom_info_cpu_addr);
+
+	return rc;
+}

drivers/misc/habanalabs/goya/goyaP.h

@@ -49,9 +49,6 @@
 
 #define MAX_POWER_DEFAULT		200000		/* 200W */
 
-#define GOYA_ARMCP_INFO_TIMEOUT		10000000	/* 10s */
-#define GOYA_ARMCP_EEPROM_TIMEOUT	10000000	/* 10s */
-
 #define DRAM_PHYS_DEFAULT_SIZE		0x100000000ull	/* 4GB */
 
 /* DRAM Memory Map */
@@ -142,13 +139,6 @@
 #define HW_CAP_GOLDEN		0x00000400
 #define HW_CAP_TPC		0x00000800
 
-#define CPU_PKT_SHIFT		5
-#define CPU_PKT_SIZE		(1 << CPU_PKT_SHIFT)
-#define CPU_PKT_MASK		(~((1 << CPU_PKT_SHIFT) - 1))
-#define CPU_MAX_PKTS_IN_CB	32
-#define CPU_CB_SIZE		(CPU_PKT_SIZE * CPU_MAX_PKTS_IN_CB)
-#define CPU_ACCESSIBLE_MEM_SIZE	(HL_QUEUE_LENGTH * CPU_CB_SIZE)
-
 enum goya_fw_component {
 	FW_COMP_UBOOT,
 	FW_COMP_PREBOOT
@@ -192,7 +182,6 @@ void goya_init_security(struct hl_device *hdev);
 u64 goya_get_max_power(struct hl_device *hdev);
 void goya_set_max_power(struct hl_device *hdev, u64 value);
 
-int goya_send_pci_access_msg(struct hl_device *hdev, u32 opcode);
 void goya_late_fini(struct hl_device *hdev);
 int goya_suspend(struct hl_device *hdev);
 int goya_resume(struct hl_device *hdev);

drivers/misc/habanalabs/habanalabs.h

@@ -33,6 +33,9 @@
 
 #define HL_PLL_LOW_JOB_FREQ_USEC	5000000 /* 5 s */
 
+#define HL_ARMCP_INFO_TIMEOUT_USEC	10000000 /* 10s */
+#define HL_ARMCP_EEPROM_TIMEOUT_USEC	10000000 /* 10s */
+
 #define HL_MAX_QUEUES			128
 
 #define HL_MAX_JOBS_PER_CS		64
@@ -1351,6 +1354,20 @@ 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,
+				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,
+				u16 len, u32 timeout, long *result);
+int hl_fw_test_cpu_queue(struct hl_device *hdev);
+void *hl_fw_cpu_accessible_dma_pool_alloc(struct hl_device *hdev, size_t size,
+						dma_addr_t *dma_handle);
+void hl_fw_cpu_accessible_dma_pool_free(struct hl_device *hdev, size_t size,
+					void *vaddr);
+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);
+
 long hl_get_frequency(struct hl_device *hdev, u32 pll_index, bool curr);
 void hl_set_frequency(struct hl_device *hdev, u32 pll_index, u64 freq);
 long hl_get_temperature(struct hl_device *hdev, int sensor_index, u32 attr);

drivers/misc/habanalabs/include/armcp_if.h

@@ -302,6 +302,14 @@ enum armcp_pwm_attributes {
 	armcp_pwm_enable
 };
 
+#define HL_CPU_PKT_SHIFT		5
+#define HL_CPU_PKT_SIZE			(1 << HL_CPU_PKT_SHIFT)
+#define HL_CPU_PKT_MASK			(~((1 << HL_CPU_PKT_SHIFT) - 1))
+#define HL_CPU_MAX_PKTS_IN_CB		32
+#define HL_CPU_CB_SIZE			(HL_CPU_PKT_SIZE * \
+					 HL_CPU_MAX_PKTS_IN_CB)
+#define HL_CPU_ACCESSIBLE_MEM_SIZE	(HL_QUEUE_LENGTH * HL_CPU_CB_SIZE)
+
 /* Event Queue Packets */
 
 struct eq_generic_event {