13 files changed, 129 insertions, 40 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index 84a1b4bc9bb4..a9ce3b20d371 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -26,6 +26,7 @@
 #include <linux/slab.h>
 #include <linux/power_supply.h>
 #include <linux/pm_runtime.h>
+#include <linux/suspend.h>
 #include <acpi/video.h>
 #include <acpi/actbl.h>
 
@@ -1039,10 +1040,10 @@ void amdgpu_acpi_detect(void)
  */
 bool amdgpu_acpi_is_s0ix_supported(struct amdgpu_device *adev)
 {
-#if defined(CONFIG_AMD_PMC) || defined(CONFIG_AMD_PMC_MODULE)
+#if IS_ENABLED(CONFIG_AMD_PMC) && IS_ENABLED(CONFIG_SUSPEND)
 	if (acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0) {
 		if (adev->flags & AMD_IS_APU)
-			return true;
+			return pm_suspend_target_state == PM_SUSPEND_TO_IDLE;
 	}
 #endif
 	return false;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
index 3b5d13189073..8f53837d4d3e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
@@ -468,6 +468,46 @@ bool amdgpu_atomfirmware_dynamic_boot_config_supported(struct amdgpu_device *ade
 	return (fw_cap & ATOM_FIRMWARE_CAP_DYNAMIC_BOOT_CFG_ENABLE) ? true : false;
 }
 
+/*
+ * Helper function to query RAS EEPROM address
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Return true if vbios supports ras rom address reporting
+ */
+bool amdgpu_atomfirmware_ras_rom_addr(struct amdgpu_device *adev, uint8_t* i2c_address)
+{
+	struct amdgpu_mode_info *mode_info = &adev->mode_info;
+	int index;
+	u16 data_offset, size;
+	union firmware_info *firmware_info;
+	u8 frev, crev;
+
+	if (i2c_address == NULL)
+		return false;
+
+	*i2c_address = 0;
+
+	index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1,
+			firmwareinfo);
+
+	if (amdgpu_atom_parse_data_header(adev->mode_info.atom_context,
+				index, &size, &frev, &crev, &data_offset)) {
+		/* support firmware_info 3.4 + */
+		if ((frev == 3 && crev >=4) || (frev > 3)) {
+			firmware_info = (union firmware_info *)
+				(mode_info->atom_context->bios + data_offset);
+			*i2c_address = firmware_info->v34.ras_rom_i2c_slave_addr;
+		}
+	}
+
+	if (*i2c_address != 0)
+		return true;
+
+	return false;
+}
+
+
 union smu_info {
 	struct atom_smu_info_v3_1 v31;
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h
index 1bbbb195015d..751248b253de 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h
@@ -36,6 +36,7 @@ int amdgpu_atomfirmware_get_clock_info(struct amdgpu_device *adev);
 int amdgpu_atomfirmware_get_gfx_info(struct amdgpu_device *adev);
 bool amdgpu_atomfirmware_mem_ecc_supported(struct amdgpu_device *adev);
 bool amdgpu_atomfirmware_sram_ecc_supported(struct amdgpu_device *adev);
+bool amdgpu_atomfirmware_ras_rom_addr(struct amdgpu_device *adev, uint8_t* i2c_address);
 bool amdgpu_atomfirmware_mem_training_supported(struct amdgpu_device *adev);
 bool amdgpu_atomfirmware_dynamic_boot_config_supported(struct amdgpu_device *adev);
 int amdgpu_atomfirmware_get_fw_reserved_fb_size(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index d303e88e3c23..f944ed858f3e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2777,12 +2777,11 @@ static void amdgpu_device_delay_enable_gfx_off(struct work_struct *work)
 	struct amdgpu_device *adev =
 		container_of(work, struct amdgpu_device, gfx.gfx_off_delay_work.work);
 
-	mutex_lock(&adev->gfx.gfx_off_mutex);
-	if (!adev->gfx.gfx_off_state && !adev->gfx.gfx_off_req_count) {
-		if (!amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, true))
-			adev->gfx.gfx_off_state = true;
-	}
-	mutex_unlock(&adev->gfx.gfx_off_mutex);
+	WARN_ON_ONCE(adev->gfx.gfx_off_state);
+	WARN_ON_ONCE(adev->gfx.gfx_off_req_count);
+
+	if (!amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, true))
+		adev->gfx.gfx_off_state = true;
 }
 
 /**
@@ -3504,13 +3503,13 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	r = amdgpu_device_get_job_timeout_settings(adev);
 	if (r) {
 		dev_err(adev->dev, "invalid lockup_timeout parameter syntax\n");
-		goto failed_unmap;
+		return r;
 	}
 
 	/* early init functions */
 	r = amdgpu_device_ip_early_init(adev);
 	if (r)
-		goto failed_unmap;
+		return r;
 
 	/* doorbell bar mapping and doorbell index init*/
 	amdgpu_device_doorbell_init(adev);
@@ -3736,10 +3735,6 @@ release_ras_con:
 failed:
 	amdgpu_vf_error_trans_all(adev);
 
-failed_unmap:
-	iounmap(adev->rmmio);
-	adev->rmmio = NULL;
-
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index 43e7b61d1c5c..ada7bc19118a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -299,6 +299,9 @@ int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev)
 				  ip->major, ip->minor,
 				  ip->revision);
 
+			if (le16_to_cpu(ip->hw_id) == VCN_HWID)
+				adev->vcn.num_vcn_inst++;
+
 			for (k = 0; k < num_base_address; k++) {
 				/*
 				 * convert the endianness of base addresses in place,
@@ -385,7 +388,7 @@ void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev)
 {
 	struct binary_header *bhdr;
 	struct harvest_table *harvest_info;
-	int i;
+	int i, vcn_harvest_count = 0;
 
 	bhdr = (struct binary_header *)adev->mman.discovery_bin;
 	harvest_info = (struct harvest_table *)(adev->mman.discovery_bin +
@@ -397,8 +400,7 @@ void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev)
 
 		switch (le32_to_cpu(harvest_info->list[i].hw_id)) {
 		case VCN_HWID:
-			adev->harvest_ip_mask |= AMD_HARVEST_IP_VCN_MASK;
-			adev->harvest_ip_mask |= AMD_HARVEST_IP_JPEG_MASK;
+			vcn_harvest_count++;
 			break;
 		case DMU_HWID:
 			adev->harvest_ip_mask |= AMD_HARVEST_IP_DMU_MASK;
@@ -407,6 +409,10 @@ void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev)
 			break;
 		}
 	}
+	if (vcn_harvest_count == adev->vcn.num_vcn_inst) {
+		adev->harvest_ip_mask |= AMD_HARVEST_IP_VCN_MASK;
+		adev->harvest_ip_mask |= AMD_HARVEST_IP_JPEG_MASK;
+	}
 }
 
 int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 361b86b71b56..971c5b8e75dc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1213,6 +1213,13 @@ static const struct pci_device_id pciidlist[] = {
 	{0x1002, 0x740F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ALDEBARAN|AMD_EXP_HW_SUPPORT},
 	{0x1002, 0x7410, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ALDEBARAN|AMD_EXP_HW_SUPPORT},
 
+	/* BEIGE_GOBY */
+	{0x1002, 0x7420, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY},
+	{0x1002, 0x7421, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY},
+	{0x1002, 0x7422, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY},
+	{0x1002, 0x7423, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY},
+	{0x1002, 0x743F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY},
+
 	{0, 0, 0}
 };
 
@@ -1564,6 +1571,8 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev)
 		pci_ignore_hotplug(pdev);
 		pci_set_power_state(pdev, PCI_D3cold);
 		drm_dev->switch_power_state = DRM_SWITCH_POWER_DYNAMIC_OFF;
+	} else if (amdgpu_device_supports_boco(drm_dev)) {
+		/* nothing to do */
 	} else if (amdgpu_device_supports_baco(drm_dev)) {
 		amdgpu_device_baco_enter(drm_dev);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index a0be0772c8b3..b4ced45301be 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -563,24 +563,38 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable)
 
 	mutex_lock(&adev->gfx.gfx_off_mutex);
 
-	if (!enable)
-		adev->gfx.gfx_off_req_count++;
-	else if (adev->gfx.gfx_off_req_count > 0)
+	if (enable) {
+		/* If the count is already 0, it means there's an imbalance bug somewhere.
+		 * Note that the bug may be in a different caller than the one which triggers the
+		 * WARN_ON_ONCE.
+		 */
+		if (WARN_ON_ONCE(adev->gfx.gfx_off_req_count == 0))
+			goto unlock;
+
 		adev->gfx.gfx_off_req_count--;
 
-	if (enable && !adev->gfx.gfx_off_state && !adev->gfx.gfx_off_req_count) {
-		schedule_delayed_work(&adev->gfx.gfx_off_delay_work, GFX_OFF_DELAY_ENABLE);
-	} else if (!enable && adev->gfx.gfx_off_state) {
-		if (!amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, false)) {
-			adev->gfx.gfx_off_state = false;
+		if (adev->gfx.gfx_off_req_count == 0 && !adev->gfx.gfx_off_state)
+			schedule_delayed_work(&adev->gfx.gfx_off_delay_work, GFX_OFF_DELAY_ENABLE);
+	} else {
+		if (adev->gfx.gfx_off_req_count == 0) {
+			cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work);
+
+			if (adev->gfx.gfx_off_state &&
+			    !amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, false)) {
+				adev->gfx.gfx_off_state = false;
 
-			if (adev->gfx.funcs->init_spm_golden) {
-				dev_dbg(adev->dev, "GFXOFF is disabled, re-init SPM golden settings\n");
-				amdgpu_gfx_init_spm_golden(adev);
+				if (adev->gfx.funcs->init_spm_golden) {
+					dev_dbg(adev->dev,
+						"GFXOFF is disabled, re-init SPM golden settings\n");
+					amdgpu_gfx_init_spm_golden(adev);
+				}
 			}
 		}
+
+		adev->gfx.gfx_off_req_count++;
 	}
 
+unlock:
 	mutex_unlock(&adev->gfx.gfx_off_mutex);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
index 83af307e97cd..cd2e18f072fc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
@@ -502,7 +502,7 @@ void amdgpu_irq_dispatch(struct amdgpu_device *adev,
 
 	} else if ((client_id == AMDGPU_IRQ_CLIENTID_LEGACY) &&
 		   adev->irq.virq[src_id]) {
-		generic_handle_irq(irq_find_mapping(adev->irq.domain, src_id));
+		generic_handle_domain_irq(adev->irq.domain, src_id);
 
 	} else if (!adev->irq.client[client_id].sources) {
 		DRM_DEBUG("Unregistered interrupt client_id: %d src_id: %d\n",
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 795fa7445abe..92c8e6e7f346 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -920,11 +920,6 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 			return -EINVAL;
 	}
 
-	/* This assumes only APU display buffers are pinned with (VRAM|GTT).
-	 * See function amdgpu_display_supported_domains()
-	 */
-	domain = amdgpu_bo_get_preferred_pin_domain(adev, domain);
-
 	if (bo->tbo.pin_count) {
 		uint32_t mem_type = bo->tbo.resource->mem_type;
 		uint32_t mem_flags = bo->tbo.resource->placement;
@@ -949,6 +944,11 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 		return 0;
 	}
 
+	/* This assumes only APU display buffers are pinned with (VRAM|GTT).
+	 * See function amdgpu_display_supported_domains()
+	 */
+	domain = amdgpu_bo_get_preferred_pin_domain(adev, domain);
+
 	if (bo->tbo.base.import_attach)
 		dma_buf_pin(bo->tbo.base.import_attach);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index f40c871da0c6..38222de921d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -26,6 +26,7 @@
 #include "amdgpu_ras.h"
 #include <linux/bits.h>
 #include "atom.h"
+#include "amdgpu_atomfirmware.h"
 
 #define EEPROM_I2C_TARGET_ADDR_VEGA20		0xA0
 #define EEPROM_I2C_TARGET_ADDR_ARCTURUS		0xA8
@@ -96,6 +97,9 @@ static bool __get_eeprom_i2c_addr(struct amdgpu_device *adev,
 	if (!i2c_addr)
 		return false;
 
+	if (amdgpu_atomfirmware_ras_rom_addr(adev, (uint8_t*)i2c_addr))
+		return true;
+
 	switch (adev->asic_type) {
 	case CHIP_VEGA20:
 		*i2c_addr = EEPROM_I2C_TARGET_ADDR_VEGA20;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h
index 59e0fefb15aa..acfa207cf970 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h
@@ -54,11 +54,12 @@ static inline void amdgpu_res_first(struct ttm_resource *res,
 {
 	struct drm_mm_node *node;
 
-	if (!res) {
+	if (!res || res->mem_type == TTM_PL_SYSTEM) {
 		cur->start = start;
 		cur->size = size;
 		cur->remaining = size;
 		cur->node = NULL;
+		WARN_ON(res && start + size > res->num_pages << PAGE_SHIFT);
 		return;
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 044076ec1d03..6a23c6826e12 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -1295,6 +1295,16 @@ static bool is_raven_kicker(struct amdgpu_device *adev)
 		return false;
 }
 
+static bool check_if_enlarge_doorbell_range(struct amdgpu_device *adev)
+{
+	if ((adev->asic_type == CHIP_RENOIR) &&
+	    (adev->gfx.me_fw_version >= 0x000000a5) &&
+	    (adev->gfx.me_feature_version >= 52))
+		return true;
+	else
+		return false;
+}
+
 static void gfx_v9_0_check_if_need_gfxoff(struct amdgpu_device *adev)
 {
 	if (gfx_v9_0_should_disable_gfxoff(adev->pdev))
@@ -3675,7 +3685,16 @@ static int gfx_v9_0_kiq_init_register(struct amdgpu_ring *ring)
 	if (ring->use_doorbell) {
 		WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_LOWER,
 					(adev->doorbell_index.kiq * 2) << 2);
-		WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_UPPER,
+		/* If GC has entered CGPG, ringing doorbell > first page
+		 * doesn't wakeup GC. Enlarge CP_MEC_DOORBELL_RANGE_UPPER to
+		 * workaround this issue. And this change has to align with firmware
+		 * update.
+		 */
+		if (check_if_enlarge_doorbell_range(adev))
+			WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_UPPER,
+					(adev->doorbell.size - 4));
+		else
+			WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_UPPER,
 					(adev->doorbell_index.userqueue_end * 2) << 2);
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
index 618e5b6b85d9..536d41f327c1 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
@@ -67,7 +67,7 @@ static int psp_v12_0_init_microcode(struct psp_context *psp)
 
 	err = psp_init_asd_microcode(psp, chip_name);
 	if (err)
-		goto out;
+		return err;
 
 	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ta.bin", chip_name);
 	err = request_firmware(&adev->psp.ta_fw, fw_name, adev->dev);
@@ -80,7 +80,7 @@ static int psp_v12_0_init_microcode(struct psp_context *psp)
 	} else {
 		err = amdgpu_ucode_validate(adev->psp.ta_fw);
 		if (err)
-			goto out2;
+			goto out;
 
 		ta_hdr = (const struct ta_firmware_header_v1_0 *)
 				 adev->psp.ta_fw->data;
@@ -105,10 +105,9 @@ static int psp_v12_0_init_microcode(struct psp_context *psp)
 
 	return 0;
 
-out2:
+out:
 	release_firmware(adev->psp.ta_fw);
 	adev->psp.ta_fw = NULL;
-out:
 	if (err) {
 		dev_err(adev->dev,
 			"psp v12.0: Failed to load firmware \"%s\"\n",