diff options
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu')
131 files changed, 3090 insertions, 2174 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/Kconfig b/drivers/gpu/drm/amd/amdgpu/Kconfig index 5fcd510f1abb..a82d36ea88e2 100644 --- a/drivers/gpu/drm/amd/amdgpu/Kconfig +++ b/drivers/gpu/drm/amd/amdgpu/Kconfig @@ -6,6 +6,7 @@ config DRM_AMDGPU select FW_LOADER select DRM_DISPLAY_DP_HELPER select DRM_DISPLAY_HDMI_HELPER + select DRM_DISPLAY_HDCP_HELPER select DRM_DISPLAY_HELPER select DRM_KMS_HELPER select DRM_SCHED @@ -13,6 +14,8 @@ config DRM_AMDGPU select DRM_TTM_HELPER select POWER_SUPPLY select HWMON + select I2C + select I2C_ALGOBIT select BACKLIGHT_CLASS_DEVICE select INTERVAL_TREE select DRM_BUDDY diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile index 798d0e9a60b7..1d72cbc85348 100644 --- a/drivers/gpu/drm/amd/amdgpu/Makefile +++ b/drivers/gpu/drm/amd/amdgpu/Makefile @@ -34,6 +34,7 @@ ccflags-y := -I$(FULL_AMD_PATH)/include/asic_reg \ -I$(FULL_AMD_PATH)/acp/include \ -I$(FULL_AMD_DISPLAY_PATH) \ -I$(FULL_AMD_DISPLAY_PATH)/include \ + -I$(FULL_AMD_DISPLAY_PATH)/modules/inc \ -I$(FULL_AMD_DISPLAY_PATH)/dc \ -I$(FULL_AMD_DISPLAY_PATH)/amdgpu_dm \ -I$(FULL_AMD_PATH)/amdkfd @@ -76,12 +77,13 @@ amdgpu-y += \ vi.o mxgpu_vi.o nbio_v6_1.o soc15.o emu_soc.o mxgpu_ai.o nbio_v7_0.o vega10_reg_init.o \ vega20_reg_init.o nbio_v7_4.o nbio_v2_3.o nv.o arct_reg_init.o mxgpu_nv.o \ nbio_v7_2.o hdp_v4_0.o hdp_v5_0.o aldebaran_reg_init.o aldebaran.o soc21.o \ - sienna_cichlid.o nbio_v4_3.o hdp_v6_0.o nbio_v7_7.o hdp_v5_2.o lsdma_v6_0.o + sienna_cichlid.o smu_v13_0_10.o nbio_v4_3.o hdp_v6_0.o nbio_v7_7.o hdp_v5_2.o lsdma_v6_0.o # add DF block amdgpu-y += \ df_v1_7.o \ - df_v3_6.o + df_v3_6.o \ + df_v4_3.o # add GMC block amdgpu-y += \ @@ -136,6 +138,7 @@ amdgpu-y += \ gfx_v10_0.o \ imu_v11_0.o \ gfx_v11_0.o \ + gfx_v11_0_3.o \ imu_v11_0_3.o # add async DMA block diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index e3e2e6e3b485..164141bc8b4a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -52,8 +52,7 @@ #include <linux/pci.h> #include <linux/aer.h> -#include <drm/ttm/ttm_bo_api.h> -#include <drm/ttm/ttm_bo_driver.h> +#include <drm/ttm/ttm_bo.h> #include <drm/ttm/ttm_placement.h> #include <drm/ttm/ttm_execbuf_util.h> @@ -150,7 +149,7 @@ struct amdgpu_watchdog_timer * Modules parameters. */ extern int amdgpu_modeset; -extern int amdgpu_vram_limit; +extern unsigned int amdgpu_vram_limit; extern int amdgpu_vis_vram_limit; extern int amdgpu_gart_size; extern int amdgpu_gtt_size; @@ -243,6 +242,7 @@ extern int amdgpu_num_kcq; #define AMDGPU_VCNFW_LOG_SIZE (32 * 1024) extern int amdgpu_vcnfw_log; +extern int amdgpu_sg_display; #define AMDGPU_VM_MAX_NUM_CTX 4096 #define AMDGPU_SG_THRESHOLD (256*1024*1024) @@ -609,7 +609,7 @@ int amdgpu_cs_wait_fences_ioctl(struct drm_device *dev, void *data, struct drm_file *filp); /* VRAM scratch page for HDP bug, default vram page */ -struct amdgpu_vram_scratch { +struct amdgpu_mem_scratch { struct amdgpu_bo *robj; volatile uint32_t *ptr; u64 gpu_addr; @@ -756,6 +756,11 @@ struct amdgpu_mqd { #define AMDGPU_PRODUCT_NAME_LEN 64 struct amdgpu_reset_domain; +/* + * Non-zero (true) if the GPU has VRAM. Zero (false) otherwise. + */ +#define AMDGPU_HAS_VRAM(_adev) ((_adev)->gmc.real_vram_size) + struct amdgpu_device { struct device *dev; struct pci_dev *pdev; @@ -849,7 +854,7 @@ struct amdgpu_device { /* memory management */ struct amdgpu_mman mman; - struct amdgpu_vram_scratch vram_scratch; + struct amdgpu_mem_scratch mem_scratch; struct amdgpu_wb wb; atomic64_t num_bytes_moved; atomic64_t num_evictions; @@ -871,7 +876,7 @@ struct amdgpu_device { struct amdgpu_vkms_output *amdgpu_vkms_output; struct amdgpu_mode_info mode_info; /* For pre-DCE11. DCE11 and later are in "struct amdgpu_device->dm" */ - struct work_struct hotplug_work; + struct delayed_work hotplug_work; struct amdgpu_irq_src crtc_irq; struct amdgpu_irq_src vline0_irq; struct amdgpu_irq_src vupdate_irq; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c index 57b5e11446c6..d4196fcb85a0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c @@ -24,6 +24,7 @@ #include <linux/pci.h> #include <linux/acpi.h> +#include <linux/backlight.h> #include <linux/slab.h> #include <linux/power_supply.h> #include <linux/pm_runtime.h> @@ -31,7 +32,6 @@ #include <acpi/video.h> #include <acpi/actbl.h> -#include <drm/drm_crtc_helper.h> #include "amdgpu.h" #include "amdgpu_pm.h" #include "amdgpu_display.h" @@ -1073,26 +1073,25 @@ bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev) (pm_suspend_target_state != PM_SUSPEND_TO_IDLE)) return false; + if (adev->asic_type < CHIP_RAVEN) + return false; + /* * If ACPI_FADT_LOW_POWER_S0 is not set in the FADT, it is generally * risky to do any special firmware-related preparations for entering * S0ix even though the system is suspending to idle, so return false * in that case. */ - if (!(acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0)) { + if (!(acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0)) dev_warn_once(adev->dev, "Power consumption will be higher as BIOS has not been configured for suspend-to-idle.\n" "To use suspend-to-idle change the sleep mode in BIOS setup.\n"); - return false; - } #if !IS_ENABLED(CONFIG_AMD_PMC) dev_warn_once(adev->dev, "Power consumption will be higher as the kernel has not been compiled with CONFIG_AMD_PMC.\n"); - return false; -#else - return true; #endif /* CONFIG_AMD_PMC */ + return true; } #endif /* CONFIG_SUSPEND */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index 0040deaf8a83..333780491867 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -97,7 +97,7 @@ struct amdgpu_amdkfd_fence { struct amdgpu_kfd_dev { struct kfd_dev *dev; - uint64_t vram_used; + int64_t vram_used; uint64_t vram_used_aligned; bool init_complete; struct work_struct reset_work; @@ -271,9 +271,9 @@ int amdgpu_amdkfd_get_pcie_bandwidth_mbytes(struct amdgpu_device *adev, bool is_ ((struct drm_file *)(drm_priv))->driver_priv)->vm) int amdgpu_amdkfd_gpuvm_set_vm_pasid(struct amdgpu_device *adev, - struct file *filp, u32 pasid); + struct amdgpu_vm *avm, u32 pasid); int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct amdgpu_device *adev, - struct file *filp, + struct amdgpu_vm *avm, void **process_info, struct dma_fence **ef); void amdgpu_amdkfd_gpuvm_release_process_vm(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 3b5c53712d31..d6320c836251 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -25,6 +25,7 @@ #include <linux/pagemap.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> +#include <drm/ttm/ttm_tt.h> #include "amdgpu_object.h" #include "amdgpu_gem.h" @@ -1430,18 +1431,11 @@ static void amdgpu_amdkfd_gpuvm_unpin_bo(struct amdgpu_bo *bo) } int amdgpu_amdkfd_gpuvm_set_vm_pasid(struct amdgpu_device *adev, - struct file *filp, u32 pasid) + struct amdgpu_vm *avm, u32 pasid) { - struct amdgpu_fpriv *drv_priv; - struct amdgpu_vm *avm; int ret; - ret = amdgpu_file_to_fpriv(filp, &drv_priv); - if (ret) - return ret; - avm = &drv_priv->vm; - /* Free the original amdgpu allocated pasid, * will be replaced with kfd allocated pasid. */ @@ -1458,19 +1452,12 @@ int amdgpu_amdkfd_gpuvm_set_vm_pasid(struct amdgpu_device *adev, } int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct amdgpu_device *adev, - struct file *filp, + struct amdgpu_vm *avm, void **process_info, struct dma_fence **ef) { - struct amdgpu_fpriv *drv_priv; - struct amdgpu_vm *avm; int ret; - ret = amdgpu_file_to_fpriv(filp, &drv_priv); - if (ret) - return ret; - avm = &drv_priv->vm; - /* Already a compute VM? */ if (avm->process_info) return -EINVAL; @@ -1612,6 +1599,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( struct amdgpu_bo *bo; struct drm_gem_object *gobj = NULL; u32 domain, alloc_domain; + uint64_t aligned_size; u64 alloc_flags; int ret; @@ -1667,22 +1655,23 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( * the memory. */ if ((*mem)->aql_queue) - size = size >> 1; + size >>= 1; + aligned_size = PAGE_ALIGN(size); (*mem)->alloc_flags = flags; amdgpu_sync_create(&(*mem)->sync); - ret = amdgpu_amdkfd_reserve_mem_limit(adev, size, flags); + ret = amdgpu_amdkfd_reserve_mem_limit(adev, aligned_size, flags); if (ret) { pr_debug("Insufficient memory\n"); goto err_reserve_limit; } pr_debug("\tcreate BO VA 0x%llx size 0x%llx domain %s\n", - va, size, domain_string(alloc_domain)); + va, (*mem)->aql_queue ? size << 1 : size, domain_string(alloc_domain)); - ret = amdgpu_gem_object_create(adev, size, 1, alloc_domain, alloc_flags, + ret = amdgpu_gem_object_create(adev, aligned_size, 1, alloc_domain, alloc_flags, bo_type, NULL, &gobj); if (ret) { pr_debug("Failed to create BO on domain %s. ret %d\n", @@ -1739,7 +1728,7 @@ err_node_allow: /* Don't unreserve system mem limit twice */ goto err_reserve_limit; err_bo_create: - amdgpu_amdkfd_unreserve_mem_limit(adev, size, flags); + amdgpu_amdkfd_unreserve_mem_limit(adev, aligned_size, flags); err_reserve_limit: mutex_destroy(&(*mem)->lock); if (gobj) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h index e4d78491bcc7..ededdc01ca28 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h @@ -28,6 +28,8 @@ struct hmm_range; +struct drm_file; + struct amdgpu_device; struct amdgpu_bo; struct amdgpu_bo_va; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c index f1a050379190..456e385333b6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c @@ -411,17 +411,10 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device, return -EINVAL; } - err = request_firmware(&adev->pm.fw, fw_name, adev->dev); - if (err) { - DRM_ERROR("Failed to request firmware\n"); - return err; - } - - err = amdgpu_ucode_validate(adev->pm.fw); + err = amdgpu_ucode_request(adev, &adev->pm.fw, fw_name); if (err) { DRM_ERROR("Failed to load firmware \"%s\"", fw_name); - release_firmware(adev->pm.fw); - adev->pm.fw = NULL; + amdgpu_ucode_release(&adev->pm.fw); return err; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c index 2ebbc6382a06..6be30dcb029d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c @@ -25,7 +25,9 @@ */ #include <drm/display/drm_dp_helper.h> +#include <drm/drm_crtc_helper.h> #include <drm/drm_edid.h> +#include <drm/drm_modeset_helper_vtables.h> #include <drm/drm_probe_helper.h> #include <drm/amdgpu_drm.h> #include "amdgpu.h" @@ -996,13 +998,33 @@ amdgpu_connector_dvi_detect(struct drm_connector *connector, bool force) } } + if (amdgpu_connector->detected_hpd_without_ddc) { + force = true; + amdgpu_connector->detected_hpd_without_ddc = false; + } + if (!force && amdgpu_connector_check_hpd_status_unchanged(connector)) { ret = connector->status; goto exit; } - if (amdgpu_connector->ddc_bus) + if (amdgpu_connector->ddc_bus) { dret = amdgpu_display_ddc_probe(amdgpu_connector, false); + + /* Sometimes the pins required for the DDC probe on DVI + * connectors don't make contact at the same time that the ones + * for HPD do. If the DDC probe fails even though we had an HPD + * signal, try again later + */ + if (!dret && !force && + amdgpu_display_hpd_sense(adev, amdgpu_connector->hpd.hpd)) { + DRM_DEBUG_KMS("hpd detected without ddc, retrying in 1 second\n"); + amdgpu_connector->detected_hpd_without_ddc = true; + schedule_delayed_work(&adev->hotplug_work, + msecs_to_jiffies(1000)); + goto exit; + } + } if (dret) { amdgpu_connector->detected_by_load = false; amdgpu_connector_free_edid(connector); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 7b5ce00f0602..08eced097bd8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -32,6 +32,8 @@ #include <drm/amdgpu_drm.h> #include <drm/drm_syncobj.h> +#include <drm/ttm/ttm_tt.h> + #include "amdgpu_cs.h" #include "amdgpu.h" #include "amdgpu_trace.h" @@ -1220,10 +1222,13 @@ static int amdgpu_cs_sync_rings(struct amdgpu_cs_parser *p) * next job actually sees the results from the previous one * before we start executing on the same scheduler ring. */ - if (!s_fence || s_fence->sched != sched) + if (!s_fence || s_fence->sched != sched) { + dma_fence_put(fence); continue; + } r = amdgpu_sync_fence(&p->gang_leader->explicit_sync, fence); + dma_fence_put(fence); if (r) return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.h index 113f39510a72..fb3e3d56d427 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.h @@ -23,6 +23,8 @@ #ifndef __AMDGPU_CS_H__ #define __AMDGPU_CS_H__ +#include <linux/ww_mutex.h> + #include "amdgpu_job.h" #include "amdgpu_bo_list.h" #include "amdgpu_ring.h" diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c index 0f16d3c09309..f60753f97ac5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c @@ -1717,7 +1717,7 @@ no_preempt: static int amdgpu_debugfs_ib_preempt(void *data, u64 val) { - int r, resched, length; + int r, length; struct amdgpu_ring *ring; struct dma_fence **fences = NULL; struct amdgpu_device *adev = (struct amdgpu_device *)data; @@ -1747,8 +1747,6 @@ static int amdgpu_debugfs_ib_preempt(void *data, u64 val) /* stop the scheduler */ kthread_park(ring->sched.thread); - resched = ttm_bo_lock_delayed_workqueue(&adev->mman.bdev); - /* preempt the IB */ r = amdgpu_ring_preempt_ib(ring); if (r) { @@ -1785,8 +1783,6 @@ failure: up_read(&adev->reset_domain->sem); - ttm_bo_unlock_delayed_workqueue(&adev->mman.bdev, resched); - pro_end: kfree(fences); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 2f28a8c02f64..da5b0258a237 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -38,6 +38,7 @@ #include <drm/drm_aperture.h> #include <drm/drm_atomic_helper.h> +#include <drm/drm_crtc_helper.h> #include <drm/drm_fb_helper.h> #include <drm/drm_probe_helper.h> #include <drm/amdgpu_drm.h> @@ -163,7 +164,7 @@ static void amdgpu_device_get_pcie_info(struct amdgpu_device *adev); * * The amdgpu driver provides a sysfs API for reporting the product name * for the device - * The file serial_number is used for this and returns the product name + * The file product_name is used for this and returns the product name * as returned from the FRU. * NOTE: This is only available for certain server cards */ @@ -185,7 +186,7 @@ static DEVICE_ATTR(product_name, S_IRUGO, * * The amdgpu driver provides a sysfs API for reporting the part number * for the device - * The file serial_number is used for this and returns the part number + * The file product_number is used for this and returns the part number * as returned from the FRU. * NOTE: This is only available for certain server cards */ @@ -927,32 +928,33 @@ static int amdgpu_device_asic_init(struct amdgpu_device *adev) } /** - * amdgpu_device_vram_scratch_init - allocate the VRAM scratch page + * amdgpu_device_mem_scratch_init - allocate the VRAM scratch page * * @adev: amdgpu_device pointer * * Allocates a scratch page of VRAM for use by various things in the * driver. */ -static int amdgpu_device_vram_scratch_init(struct amdgpu_device *adev) +static int amdgpu_device_mem_scratch_init(struct amdgpu_device *adev) { - return amdgpu_bo_create_kernel(adev, AMDGPU_GPU_PAGE_SIZE, - PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM, - &adev->vram_scratch.robj, - &adev->vram_scratch.gpu_addr, - (void **)&adev->vram_scratch.ptr); + return amdgpu_bo_create_kernel(adev, AMDGPU_GPU_PAGE_SIZE, PAGE_SIZE, + AMDGPU_GEM_DOMAIN_VRAM | + AMDGPU_GEM_DOMAIN_GTT, + &adev->mem_scratch.robj, + &adev->mem_scratch.gpu_addr, + (void **)&adev->mem_scratch.ptr); } /** - * amdgpu_device_vram_scratch_fini - Free the VRAM scratch page + * amdgpu_device_mem_scratch_fini - Free the VRAM scratch page * * @adev: amdgpu_device pointer * * Frees the VRAM scratch page. */ -static void amdgpu_device_vram_scratch_fini(struct amdgpu_device *adev) +static void amdgpu_device_mem_scratch_fini(struct amdgpu_device *adev) { - amdgpu_bo_free_kernel(&adev->vram_scratch.robj, NULL, NULL); + amdgpu_bo_free_kernel(&adev->mem_scratch.robj, NULL, NULL); } /** @@ -1984,17 +1986,10 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev) } snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_gpu_info.bin", chip_name); - err = request_firmware(&adev->firmware.gpu_info_fw, fw_name, adev->dev); + err = amdgpu_ucode_request(adev, &adev->firmware.gpu_info_fw, fw_name); if (err) { dev_err(adev->dev, - "Failed to load gpu_info firmware \"%s\"\n", - fw_name); - goto out; - } - err = amdgpu_ucode_validate(adev->firmware.gpu_info_fw); - if (err) { - dev_err(adev->dev, - "Failed to validate gpu_info firmware \"%s\"\n", + "Failed to get gpu_info firmware \"%s\"\n", fw_name); goto out; } @@ -2081,6 +2076,7 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev) struct drm_device *dev = adev_to_drm(adev); struct pci_dev *parent; int i, r; + bool total; amdgpu_device_enable_virtual_display(adev); @@ -2164,6 +2160,7 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev) if (amdgpu_sriov_vf(adev) && adev->asic_type == CHIP_SIENNA_CICHLID) adev->pm.pp_feature &= ~PP_OVERDRIVE_MASK; + total = true; for (i = 0; i < adev->num_ip_blocks; i++) { if ((amdgpu_ip_block_mask & (1 << i)) == 0) { DRM_ERROR("disabled ip block: %d <%s>\n", @@ -2177,7 +2174,7 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev) } else if (r) { DRM_ERROR("early_init of IP block <%s> failed %d\n", adev->ip_blocks[i].version->funcs->name, r); - return r; + total = false; } else { adev->ip_blocks[i].status.valid = true; } @@ -2208,6 +2205,8 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev) } } + if (!total) + return -ENODEV; adev->cg_flags &= amdgpu_cg_mask; adev->pg_flags &= amdgpu_pg_mask; @@ -2393,9 +2392,9 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev) if (amdgpu_sriov_vf(adev)) amdgpu_virt_exchange_data(adev); - r = amdgpu_device_vram_scratch_init(adev); + r = amdgpu_device_mem_scratch_init(adev); if (r) { - DRM_ERROR("amdgpu_vram_scratch_init failed %d\n", r); + DRM_ERROR("amdgpu_mem_scratch_init failed %d\n", r); goto init_failed; } r = adev->ip_blocks[i].version->funcs->hw_init((void *)adev); @@ -2413,8 +2412,9 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev) /* right after GMC hw init, we create CSA */ if (amdgpu_mcbp) { r = amdgpu_allocate_static_csa(adev, &adev->virt.csa_obj, - AMDGPU_GEM_DOMAIN_VRAM, - AMDGPU_CSA_SIZE); + AMDGPU_GEM_DOMAIN_VRAM | + AMDGPU_GEM_DOMAIN_GTT, + AMDGPU_CSA_SIZE); if (r) { DRM_ERROR("allocate CSA failed %d\n", r); goto init_failed; @@ -2584,9 +2584,10 @@ int amdgpu_device_set_cg_state(struct amdgpu_device *adev, i = state == AMD_CG_STATE_GATE ? j : adev->num_ip_blocks - j - 1; if (!adev->ip_blocks[i].status.late_initialized) continue; - /* skip CG for GFX on S0ix */ + /* skip CG for GFX, SDMA on S0ix */ if (adev->in_s0ix && - adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX) + (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX || + adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_SDMA)) continue; /* skip CG for VCE/UVD, it's handled specially */ if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD && @@ -2620,9 +2621,10 @@ int amdgpu_device_set_pg_state(struct amdgpu_device *adev, i = state == AMD_PG_STATE_GATE ? j : adev->num_ip_blocks - j - 1; if (!adev->ip_blocks[i].status.late_initialized) continue; - /* skip PG for GFX on S0ix */ + /* skip PG for GFX, SDMA on S0ix */ if (adev->in_s0ix && - adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX) + (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX || + adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_SDMA)) continue; /* skip CG for VCE/UVD, it's handled specially */ if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD && @@ -2874,7 +2876,7 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev) amdgpu_ucode_free_bo(adev); amdgpu_free_static_csa(&adev->virt.csa_obj); amdgpu_device_wb_fini(adev); - amdgpu_device_vram_scratch_fini(adev); + amdgpu_device_mem_scratch_fini(adev); amdgpu_ib_pool_fini(adev); } @@ -3030,6 +3032,24 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev) adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_MES)) continue; + /* SDMA 5.x+ is part of GFX power domain so it's covered by GFXOFF */ + if (adev->in_s0ix && + (adev->ip_versions[SDMA0_HWIP][0] >= IP_VERSION(5, 0, 0)) && + (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_SDMA)) + continue; + + /* Once swPSP provides the IMU, RLC FW binaries to TOS during cold-boot. + * These are in TMR, hence are expected to be reused by PSP-TOS to reload + * from this location and RLC Autoload automatically also gets loaded + * from here based on PMFW -> PSP message during re-init sequence. + * Therefore, the psp suspend & resume should be skipped to avoid destroy + * the TMR and reload FWs again for IMU enabled APU ASICs. + */ + if (amdgpu_in_reset(adev) && + (adev->flags & AMD_IS_APU) && adev->gfx.imu.funcs && + adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_PSP) + continue; + /* XXX handle errors */ r = adev->ip_blocks[i].version->funcs->suspend(adev); /* XXX handle errors */ @@ -3230,15 +3250,6 @@ static int amdgpu_device_ip_resume_phase2(struct amdgpu_device *adev) return r; } adev->ip_blocks[i].status.hw = true; - - if (adev->in_s0ix && adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_SMC) { - /* disable gfxoff for IP resume. The gfxoff will be re-enabled in - * amdgpu_device_resume() after IP resume. - */ - amdgpu_gfx_off_ctrl(adev, false); - DRM_DEBUG("will disable gfxoff for re-initializing other blocks\n"); - } - } return 0; @@ -3997,10 +4008,8 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev) } amdgpu_fence_driver_hw_fini(adev); - if (adev->mman.initialized) { - flush_delayed_work(&adev->mman.bdev.wq); - ttm_bo_lock_delayed_workqueue(&adev->mman.bdev); - } + if (adev->mman.initialized) + drain_workqueue(adev->mman.bdev.wq); if (adev->pm_sysfs_en) amdgpu_pm_sysfs_fini(adev); @@ -4022,7 +4031,8 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev) amdgpu_gart_dummy_page_fini(adev); - amdgpu_device_unmap_mmio(adev); + if (drm_dev_is_unplugged(adev_to_drm(adev))) + amdgpu_device_unmap_mmio(adev); } @@ -4032,8 +4042,7 @@ void amdgpu_device_fini_sw(struct amdgpu_device *adev) amdgpu_fence_driver_sw_fini(adev); amdgpu_device_ip_fini(adev); - release_firmware(adev->firmware.gpu_info_fw); - adev->firmware.gpu_info_fw = NULL; + amdgpu_ucode_release(&adev->firmware.gpu_info_fw); adev->accel_working = false; dma_fence_put(rcu_dereference_protected(adev->gang_submit, true)); @@ -4136,8 +4145,6 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) if (amdgpu_acpi_smart_shift_update(dev, AMDGPU_SS_DEV_D3)) DRM_WARN("smart shift update failed\n"); - drm_kms_helper_poll_disable(dev); - if (fbcon) drm_fb_helper_set_suspend_unlocked(adev_to_drm(adev)->fb_helper, true); @@ -4231,18 +4238,9 @@ exit: /* Make sure IB tests flushed */ flush_delayed_work(&adev->delayed_init_work); - if (adev->in_s0ix) { - /* re-enable gfxoff after IP resume. This re-enables gfxoff after - * it was disabled for IP resume in amdgpu_device_ip_resume_phase2(). - */ - amdgpu_gfx_off_ctrl(adev, true); - DRM_DEBUG("will enable gfxoff for the mission mode\n"); - } if (fbcon) drm_fb_helper_set_suspend_unlocked(adev_to_drm(adev)->fb_helper, false); - drm_kms_helper_poll_enable(dev); - amdgpu_ras_resume(adev); if (adev->mode_info.num_crtc) { @@ -4268,6 +4266,9 @@ exit: } adev->in_suspend = false; + if (adev->enable_mes) + amdgpu_mes_self_test(adev); + if (amdgpu_acpi_smart_shift_update(dev, AMDGPU_SS_DEV_D0)) DRM_WARN("smart shift update failed\n"); @@ -4618,11 +4619,6 @@ bool amdgpu_device_should_recover_gpu(struct amdgpu_device *adev) if (!amdgpu_ras_is_poison_mode_supported(adev)) return true; - if (!amdgpu_device_ip_check_soft_reset(adev)) { - dev_info(adev->dev,"Timeout, but no hardware hang detected.\n"); - return false; - } - if (amdgpu_sriov_vf(adev)) return true; @@ -4747,7 +4743,8 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev, if (!need_full_reset) need_full_reset = amdgpu_device_ip_need_full_reset(adev); - if (!need_full_reset && amdgpu_gpu_recovery) { + if (!need_full_reset && amdgpu_gpu_recovery && + amdgpu_device_ip_check_soft_reset(adev)) { amdgpu_device_ip_pre_soft_reset(adev); r = amdgpu_device_ip_soft_reset(adev); amdgpu_device_ip_post_soft_reset(adev); @@ -5873,8 +5870,8 @@ void amdgpu_device_invalidate_hdp(struct amdgpu_device *adev, int amdgpu_in_reset(struct amdgpu_device *adev) { return atomic_read(&adev->reset_domain->in_gpu_reset); - } - +} + /** * amdgpu_device_halt() - bring hardware to some kind of halt state * diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index 1bbd56029a4f..1a3cb53d2e0d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -33,6 +33,7 @@ #include "gmc_v9_0.h" #include "df_v1_7.h" #include "df_v3_6.h" +#include "df_v4_3.h" #include "nbio_v6_1.h" #include "nbio_v7_0.h" #include "nbio_v7_4.h" @@ -542,6 +543,7 @@ static void amdgpu_discovery_read_from_harvest_table(struct amdgpu_device *adev, struct harvest_table *harvest_info; u16 offset; int i; + uint32_t umc_harvest_config = 0; bhdr = (struct binary_header *)adev->mman.discovery_bin; offset = le16_to_cpu(bhdr->table_list[HARVEST_INFO].offset); @@ -569,12 +571,17 @@ static void amdgpu_discovery_read_from_harvest_table(struct amdgpu_device *adev, adev->harvest_ip_mask |= AMD_HARVEST_IP_DMU_MASK; break; case UMC_HWID: + umc_harvest_config |= + 1 << (le16_to_cpu(harvest_info->list[i].number_instance)); (*umc_harvest_count)++; break; default: break; } } + + adev->umc.active_mask = ((1 << adev->umc.node_inst_num) - 1) & + ~umc_harvest_config; } /* ================================================== */ @@ -1155,8 +1162,10 @@ static int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev) AMDGPU_MAX_SDMA_INSTANCES); } - if (le16_to_cpu(ip->hw_id) == UMC_HWID) + if (le16_to_cpu(ip->hw_id) == UMC_HWID) { adev->gmc.num_umc++; + adev->umc.node_inst_num++; + } for (k = 0; k < num_base_address; k++) { /* @@ -2329,6 +2338,9 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(3, 5, 2): adev->df.funcs = &df_v1_7_funcs; break; + case IP_VERSION(4, 3, 0): + adev->df.funcs = &df_v4_3_funcs; + break; default: break; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index b22471b3bd63..d60fe7eb5579 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -42,6 +42,7 @@ #include <drm/drm_fb_helper.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_fourcc.h> +#include <drm/drm_modeset_helper.h> #include <drm/drm_vblank.h> /** @@ -63,7 +64,7 @@ void amdgpu_display_hotplug_work_func(struct work_struct *work) { struct amdgpu_device *adev = container_of(work, struct amdgpu_device, - hotplug_work); + hotplug_work.work); struct drm_device *dev = adev_to_drm(adev); struct drm_mode_config *mode_config = &dev->mode_config; struct drm_connector *connector; @@ -1617,6 +1618,8 @@ int amdgpu_display_suspend_helper(struct amdgpu_device *adev) struct drm_connector_list_iter iter; int r; + drm_kms_helper_poll_disable(dev); + /* turn off display hw */ drm_modeset_lock_all(dev); drm_connector_list_iter_begin(dev, &iter); @@ -1693,6 +1696,8 @@ int amdgpu_display_resume_helper(struct amdgpu_device *adev) drm_modeset_unlock_all(dev); + drm_kms_helper_poll_enable(dev); + return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index 271e30e34d93..0c001bb8fc2b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -37,6 +37,7 @@ #include "amdgpu_dma_buf.h" #include "amdgpu_xgmi.h" #include <drm/amdgpu_drm.h> +#include <drm/ttm/ttm_tt.h> #include <linux/dma-buf.h> #include <linux/dma-fence-array.h> #include <linux/pci-p2pdma.h> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index cd4caaa29528..f5ffca24def4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -38,7 +38,6 @@ #include <linux/mmu_notifier.h> #include <linux/suspend.h> #include <linux/cc_platform.h> -#include <linux/fb.h> #include <linux/dynamic_debug.h> #include "amdgpu.h" @@ -104,13 +103,19 @@ * - 3.46.0 - To enable hot plug amdgpu tests in libdrm * - 3.47.0 - Add AMDGPU_GEM_CREATE_DISCARDABLE and AMDGPU_VM_NOALLOC flags * - 3.48.0 - Add IP discovery version info to HW INFO - * 3.49.0 - Add gang submit into CS IOCTL + * - 3.49.0 - Add gang submit into CS IOCTL + * - 3.50.0 - Update AMDGPU_INFO_DEV_INFO IOCTL for minimum engine and memory clock + * Update AMDGPU_INFO_SENSOR IOCTL for PEAK_PSTATE engine and memory clock + * 3.51.0 - Return the PCIe gen and lanes from the INFO ioctl + * 3.52.0 - Add AMDGPU_IDS_FLAGS_CONFORMANT_TRUNC_COORD, add device_info fields: + * tcp_cache_size, num_sqc_per_wgp, sqc_data_cache_size, sqc_inst_cache_size, + * gl1c_cache_size, gl2c_cache_size, mall_size, enabled_rb_pipes_mask_hi */ #define KMS_DRIVER_MAJOR 3 -#define KMS_DRIVER_MINOR 49 +#define KMS_DRIVER_MINOR 52 #define KMS_DRIVER_PATCHLEVEL 0 -int amdgpu_vram_limit; +unsigned int amdgpu_vram_limit = UINT_MAX; int amdgpu_vis_vram_limit; int amdgpu_gart_size = -1; /* auto */ int amdgpu_gtt_size = -1; /* auto */ @@ -186,6 +191,7 @@ int amdgpu_num_kcq = -1; int amdgpu_smartshift_bias; int amdgpu_use_xgmi_p2p = 1; int amdgpu_vcnfw_log; +int amdgpu_sg_display = -1; /* auto */ static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work); @@ -918,7 +924,7 @@ module_param_named(reset_method, amdgpu_reset_method, int, 0444); * result in the GPU entering bad status when the number of total * faulty pages by ECC exceeds the threshold value. */ -MODULE_PARM_DESC(bad_page_threshold, "Bad page threshold(-1 = auto(default value), 0 = disable bad page retirement, -2 = ignore bad page threshold)"); +MODULE_PARM_DESC(bad_page_threshold, "Bad page threshold(-1 = ignore threshold (default value), 0 = disable bad page retirement, -2 = driver sets threshold)"); module_param_named(bad_page_threshold, amdgpu_bad_page_threshold, int, 0444); MODULE_PARM_DESC(num_kcq, "number of kernel compute queue user want to setup (8 if set to greater than 8 or less than 0, only affect gfx 8+)"); @@ -932,6 +938,16 @@ MODULE_PARM_DESC(vcnfw_log, "Enable vcnfw log(0 = disable (default value), 1 = e module_param_named(vcnfw_log, amdgpu_vcnfw_log, int, 0444); /** + * DOC: sg_display (int) + * Disable S/G (scatter/gather) display (i.e., display from system memory). + * This option is only relevant on APUs. Set this option to 0 to disable + * S/G display if you experience flickering or other issues under memory + * pressure and report the issue. + */ +MODULE_PARM_DESC(sg_display, "S/G Display (-1 = auto (default), 0 = disable)"); +module_param_named(sg_display, amdgpu_sg_display, int, 0444); + +/** * DOC: smu_pptable_id (int) * Used to override pptable id. id = 0 use VBIOS pptable. * id > 0 use the soft pptable with specicfied id. @@ -2225,6 +2241,8 @@ amdgpu_pci_remove(struct pci_dev *pdev) struct drm_device *dev = pci_get_drvdata(pdev); struct amdgpu_device *adev = drm_to_adev(dev); + drm_dev_unplug(dev); + if (adev->pm.rpm_mode != AMDGPU_RUNPM_NONE) { pm_runtime_get_sync(dev->dev); pm_runtime_forbid(dev->dev); @@ -2264,8 +2282,6 @@ amdgpu_pci_remove(struct pci_dev *pdev) amdgpu_driver_unload_kms(dev); - drm_dev_unplug(dev); - /* * Flush any in flight DMA operations from device. * Clear the Bus Master Enable bit and then wait on the PCIe Device @@ -2401,8 +2417,10 @@ static int amdgpu_pmops_suspend(struct device *dev) if (amdgpu_acpi_is_s0ix_active(adev)) adev->in_s0ix = true; - else + else if (amdgpu_acpi_is_s3_active(adev)) adev->in_s3 = true; + if (!adev->in_s0ix && !adev->in_s3) + return 0; return amdgpu_device_suspend(drm_dev, true); } @@ -2423,6 +2441,9 @@ static int amdgpu_pmops_resume(struct device *dev) struct amdgpu_device *adev = drm_to_adev(drm_dev); int r; + if (!adev->in_s0ix && !adev->in_s3) + return 0; + /* Avoids registers access if device is physically gone */ if (!pci_device_is_present(adev->pdev)) adev->no_hw_access = true; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_encoders.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_encoders.c index c96e458ed088..27a782a9dc72 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_encoders.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_encoders.c @@ -24,7 +24,6 @@ * Alex Deucher */ -#include <drm/drm_crtc_helper.h> #include <drm/amdgpu_drm.h> #include "amdgpu.h" #include "amdgpu_connectors.h" diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.h index 41a4c7056729..e86834bfea1d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.h @@ -30,7 +30,6 @@ #include <linux/rbtree.h> #include <drm/gpu_scheduler.h> #include <drm/drm_file.h> -#include <drm/ttm/ttm_bo_driver.h> #include <linux/sched/mm.h> #include "amdgpu_sync.h" diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index 00444203220d..faff4a3f96e6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -618,7 +618,13 @@ void amdgpu_fence_driver_sw_fini(struct amdgpu_device *adev) if (!ring || !ring->fence_drv.initialized) continue; - if (!ring->no_scheduler) + /* + * Notice we check for sched.ops since there's some + * override on the meaning of sched.ready by amdgpu. + * The natural check would be sched.ready, which is + * set as drm_sched_init() finishes... + */ + if (ring->sched.ops) drm_sched_fini(&ring->sched); for (j = 0; j <= ring->fence_drv.num_fences_mask; ++j) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index bb7350ea1d75..d8e683688daa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -34,6 +34,7 @@ #include <drm/amdgpu_drm.h> #include <drm/drm_drv.h> #include <drm/drm_gem_ttm_helper.h> +#include <drm/ttm/ttm_tt.h> #include "amdgpu.h" #include "amdgpu_display.h" @@ -61,10 +62,10 @@ static vm_fault_t amdgpu_gem_fault(struct vm_fault *vmf) goto unlock; } - ret = ttm_bo_vm_fault_reserved(vmf, vmf->vma->vm_page_prot, - TTM_BO_VM_NUM_PREFAULT); + ret = ttm_bo_vm_fault_reserved(vmf, vmf->vma->vm_page_prot, + TTM_BO_VM_NUM_PREFAULT); - drm_dev_exit(idx); + drm_dev_exit(idx); } else { ret = ttm_bo_vm_dummy_page(vmf, vmf->vma->vm_page_prot); } @@ -257,7 +258,7 @@ static int amdgpu_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_str */ if (is_cow_mapping(vma->vm_flags) && !(vma->vm_flags & VM_ACCESS_FLAGS)) - vma->vm_flags &= ~VM_MAYWRITE; + vm_flags_clear(vma, VM_MAYWRITE); return drm_gem_ttm_mmap(obj, vma); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index 3380daf42da8..35ed46b9249c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -375,8 +375,11 @@ int amdgpu_gfx_mqd_sw_init(struct amdgpu_device *adev, * KIQ MQD no matter SRIOV or Bare-metal */ r = amdgpu_bo_create_kernel(adev, mqd_size, PAGE_SIZE, - AMDGPU_GEM_DOMAIN_VRAM, &ring->mqd_obj, - &ring->mqd_gpu_addr, &ring->mqd_ptr); + AMDGPU_GEM_DOMAIN_VRAM | + AMDGPU_GEM_DOMAIN_GTT, + &ring->mqd_obj, + &ring->mqd_gpu_addr, + &ring->mqd_ptr); if (r) { dev_warn(adev->dev, "failed to create ring mqd ob (%d)", r); return r; @@ -696,6 +699,50 @@ late_fini: return r; } +int amdgpu_gfx_ras_sw_init(struct amdgpu_device *adev) +{ + int err = 0; + struct amdgpu_gfx_ras *ras = NULL; + + /* adev->gfx.ras is NULL, which means gfx does not + * support ras function, then do nothing here. + */ + if (!adev->gfx.ras) + return 0; + + ras = adev->gfx.ras; + + err = amdgpu_ras_register_ras_block(adev, &ras->ras_block); + if (err) { + dev_err(adev->dev, "Failed to register gfx ras block!\n"); + return err; + } + + strcpy(ras->ras_block.ras_comm.name, "gfx"); + ras->ras_block.ras_comm.block = AMDGPU_RAS_BLOCK__GFX; + ras->ras_block.ras_comm.type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE; + adev->gfx.ras_if = &ras->ras_block.ras_comm; + + /* If not define special ras_late_init function, use gfx default ras_late_init */ + if (!ras->ras_block.ras_late_init) + ras->ras_block.ras_late_init = amdgpu_ras_block_late_init; + + /* If not defined special ras_cb function, use default ras_cb */ + if (!ras->ras_block.ras_cb) + ras->ras_block.ras_cb = amdgpu_gfx_process_ras_data_cb; + + return 0; +} + +int amdgpu_gfx_poison_consumption_handler(struct amdgpu_device *adev, + struct amdgpu_iv_entry *entry) +{ + if (adev->gfx.ras && adev->gfx.ras->poison_consumption_handler) + return adev->gfx.ras->poison_consumption_handler(adev, entry); + + return 0; +} + int amdgpu_gfx_process_ras_data_cb(struct amdgpu_device *adev, void *err_data, struct amdgpu_iv_entry *entry) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h index b3df4787877e..de9e7a00bb15 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h @@ -178,6 +178,8 @@ struct amdgpu_gfx_config { uint32_t num_sc_per_sh; uint32_t num_packer_per_sc; uint32_t pa_sc_tile_steering_override; + /* Whether texture coordinate truncation is conformant. */ + bool ta_cntl2_truncate_coord_mode; uint64_t tcc_disabled_mask; uint32_t gc_num_tcp_per_sa; uint32_t gc_num_sdp_interface; @@ -210,6 +212,11 @@ struct amdgpu_gfx_ras { struct amdgpu_ras_block_object ras_block; void (*enable_watchdog_timer)(struct amdgpu_device *adev); bool (*query_utcl2_poison_status)(struct amdgpu_device *adev); + int (*rlc_gc_fed_irq)(struct amdgpu_device *adev, + struct amdgpu_irq_src *source, + struct amdgpu_iv_entry *entry); + int (*poison_consumption_handler)(struct amdgpu_device *adev, + struct amdgpu_iv_entry *entry); }; struct amdgpu_gfx_funcs { @@ -323,6 +330,7 @@ struct amdgpu_gfx { struct amdgpu_irq_src priv_inst_irq; struct amdgpu_irq_src cp_ecc_error_irq; struct amdgpu_irq_src sq_irq; + struct amdgpu_irq_src rlc_gc_fed_irq; struct sq_work sq_work; /* gfx status */ @@ -432,4 +440,7 @@ void amdgpu_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v); int amdgpu_gfx_get_num_kcq(struct amdgpu_device *adev); void amdgpu_gfx_cp_init_microcode(struct amdgpu_device *adev, uint32_t ucode_id); +int amdgpu_gfx_ras_sw_init(struct amdgpu_device *adev); +int amdgpu_gfx_poison_consumption_handler(struct amdgpu_device *adev, + struct amdgpu_iv_entry *entry); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index 02a4c93673ce..12a6826caef4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -35,6 +35,7 @@ #include "amdgpu_xgmi.h" #include <drm/drm_drv.h> +#include <drm/ttm/ttm_tt.h> /** * amdgpu_gmc_pdb0_alloc - allocate vram for pdb0 @@ -201,13 +202,20 @@ uint64_t amdgpu_gmc_agp_addr(struct ttm_buffer_object *bo) void amdgpu_gmc_vram_location(struct amdgpu_device *adev, struct amdgpu_gmc *mc, u64 base) { + uint64_t vis_limit = (uint64_t)amdgpu_vis_vram_limit << 20; uint64_t limit = (uint64_t)amdgpu_vram_limit << 20; mc->vram_start = base; mc->vram_end = mc->vram_start + mc->mc_vram_size - 1; - if (limit && limit < mc->real_vram_size) + if (limit < mc->real_vram_size) mc->real_vram_size = limit; + if (vis_limit && vis_limit < mc->visible_vram_size) + mc->visible_vram_size = vis_limit; + + if (mc->real_vram_size < mc->visible_vram_size) + mc->visible_vram_size = mc->real_vram_size; + if (mc->xgmi.num_physical_nodes == 0) { mc->fb_start = mc->vram_start; mc->fb_end = mc->vram_end; @@ -544,6 +552,7 @@ void amdgpu_gmc_tmz_set(struct amdgpu_device *adev) case IP_VERSION(10, 3, 2): case IP_VERSION(10, 3, 4): case IP_VERSION(10, 3, 5): + case IP_VERSION(10, 3, 6): /* VANGOGH */ case IP_VERSION(10, 3, 1): /* YELLOW_CARP*/ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c index a6aef488a822..d0a1cc88832c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c @@ -45,7 +45,6 @@ #include <linux/irq.h> #include <linux/pci.h> -#include <drm/drm_crtc_helper.h> #include <drm/drm_vblank.h> #include <drm/amdgpu_drm.h> #include <drm/drm_drv.h> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 7aa7e52ca784..0efb38539d70 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -43,6 +43,7 @@ #include "amdgpu_gem.h" #include "amdgpu_display.h" #include "amdgpu_ras.h" +#include "amd_pcie.h" void amdgpu_unregister_gpu_instance(struct amdgpu_device *adev) { @@ -767,6 +768,7 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) case AMDGPU_INFO_DEV_INFO: { struct drm_amdgpu_info_device *dev_info; uint64_t vm_size; + uint32_t pcie_gen_mask; int ret; dev_info = kzalloc(sizeof(*dev_info), GFP_KERNEL); @@ -785,15 +787,20 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) if (adev->pm.dpm_enabled) { dev_info->max_engine_clock = amdgpu_dpm_get_sclk(adev, false) * 10; dev_info->max_memory_clock = amdgpu_dpm_get_mclk(adev, false) * 10; + dev_info->min_engine_clock = amdgpu_dpm_get_sclk(adev, true) * 10; + dev_info->min_memory_clock = amdgpu_dpm_get_mclk(adev, true) * 10; } else { - dev_info->max_engine_clock = adev->clock.default_sclk * 10; - dev_info->max_memory_clock = adev->clock.default_mclk * 10; + dev_info->max_engine_clock = + dev_info->min_engine_clock = + adev->clock.default_sclk * 10; + dev_info->max_memory_clock = + dev_info->min_memory_clock = + adev->clock.default_mclk * 10; } dev_info->enabled_rb_pipes_mask = adev->gfx.config.backend_enable_mask; dev_info->num_rb_pipes = adev->gfx.config.max_backends_per_se * adev->gfx.config.max_shader_engines; dev_info->num_hw_gfx_contexts = adev->gfx.config.max_hw_contexts; - dev_info->_pad = 0; dev_info->ids_flags = 0; if (adev->flags & AMD_IS_APU) dev_info->ids_flags |= AMDGPU_IDS_FLAGS_FUSION; @@ -801,6 +808,8 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) dev_info->ids_flags |= AMDGPU_IDS_FLAGS_PREEMPTION; if (amdgpu_is_tmz(adev)) dev_info->ids_flags |= AMDGPU_IDS_FLAGS_TMZ; + if (adev->gfx.config.ta_cntl2_truncate_coord_mode) + dev_info->ids_flags |= AMDGPU_IDS_FLAGS_CONFORMANT_TRUNC_COORD; vm_size = adev->vm_manager.max_pfn * AMDGPU_GPU_PAGE_SIZE; vm_size -= AMDGPU_VA_RESERVED_SIZE; @@ -847,6 +856,26 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) dev_info->tcc_disabled_mask = adev->gfx.config.tcc_disabled_mask; + /* Combine the chip gen mask with the platform (CPU/mobo) mask. */ + pcie_gen_mask = adev->pm.pcie_gen_mask & (adev->pm.pcie_gen_mask >> 16); + dev_info->pcie_gen = fls(pcie_gen_mask); + dev_info->pcie_num_lanes = + adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X32 ? 32 : + adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 ? 16 : + adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 ? 12 : + adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 ? 8 : + adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 ? 4 : + adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 ? 2 : 1; + + dev_info->tcp_cache_size = adev->gfx.config.gc_tcp_l1_size; + dev_info->num_sqc_per_wgp = adev->gfx.config.gc_num_sqc_per_wgp; + dev_info->sqc_data_cache_size = adev->gfx.config.gc_l1_data_cache_size_per_sqc; + dev_info->sqc_inst_cache_size = adev->gfx.config.gc_l1_instruction_cache_size_per_sqc; + dev_info->gl1c_cache_size = adev->gfx.config.gc_gl1c_size_per_instance * + adev->gfx.config.gc_gl1c_per_sa; + dev_info->gl2c_cache_size = adev->gfx.config.gc_gl2c_per_gpu; + dev_info->mall_size = adev->gmc.mall_size; + ret = copy_to_user(out, dev_info, min((size_t)size, sizeof(*dev_info))) ? -EFAULT : 0; kfree(dev_info); @@ -1014,6 +1043,24 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) } ui32 /= 100; break; + case AMDGPU_INFO_SENSOR_PEAK_PSTATE_GFX_SCLK: + /* get peak pstate sclk in Mhz */ + if (amdgpu_dpm_read_sensor(adev, + AMDGPU_PP_SENSOR_PEAK_PSTATE_SCLK, + (void *)&ui32, &ui32_size)) { + return -EINVAL; + } + ui32 /= 100; + break; + case AMDGPU_INFO_SENSOR_PEAK_PSTATE_GFX_MCLK: + /* get peak pstate mclk in Mhz */ + if (amdgpu_dpm_read_sensor(adev, + AMDGPU_PP_SENSOR_PEAK_PSTATE_MCLK, + (void *)&ui32, &ui32_size)) { + return -EINVAL; + } + ui32 /= 100; + break; default: DRM_DEBUG_KMS("Invalid request %d\n", info->sensor_info.type); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c index 0c546245793b..82e27bd4f038 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c @@ -21,6 +21,8 @@ * */ +#include <linux/firmware.h> + #include "amdgpu_mes.h" #include "amdgpu.h" #include "soc15_common.h" @@ -1423,3 +1425,60 @@ error_pasid: kfree(vm); return 0; } + +int amdgpu_mes_init_microcode(struct amdgpu_device *adev, int pipe) +{ + const struct mes_firmware_header_v1_0 *mes_hdr; + struct amdgpu_firmware_info *info; + char ucode_prefix[30]; + char fw_name[40]; + int r; + + amdgpu_ucode_ip_version_decode(adev, GC_HWIP, ucode_prefix, sizeof(ucode_prefix)); + snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mes%s.bin", + ucode_prefix, + pipe == AMDGPU_MES_SCHED_PIPE ? "" : "1"); + r = amdgpu_ucode_request(adev, &adev->mes.fw[pipe], fw_name); + if (r) + goto out; + + mes_hdr = (const struct mes_firmware_header_v1_0 *) + adev->mes.fw[pipe]->data; + adev->mes.uc_start_addr[pipe] = + le32_to_cpu(mes_hdr->mes_uc_start_addr_lo) | + ((uint64_t)(le32_to_cpu(mes_hdr->mes_uc_start_addr_hi)) << 32); + adev->mes.data_start_addr[pipe] = + le32_to_cpu(mes_hdr->mes_data_start_addr_lo) | + ((uint64_t)(le32_to_cpu(mes_hdr->mes_data_start_addr_hi)) << 32); + + if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { + int ucode, ucode_data; + + if (pipe == AMDGPU_MES_SCHED_PIPE) { + ucode = AMDGPU_UCODE_ID_CP_MES; + ucode_data = AMDGPU_UCODE_ID_CP_MES_DATA; + } else { + ucode = AMDGPU_UCODE_ID_CP_MES1; + ucode_data = AMDGPU_UCODE_ID_CP_MES1_DATA; + } + + info = &adev->firmware.ucode[ucode]; + info->ucode_id = ucode; + info->fw = adev->mes.fw[pipe]; + adev->firmware.fw_size += + ALIGN(le32_to_cpu(mes_hdr->mes_ucode_size_bytes), + PAGE_SIZE); + + info = &adev->firmware.ucode[ucode_data]; + info->ucode_id = ucode_data; + info->fw = adev->mes.fw[pipe]; + adev->firmware.fw_size += + ALIGN(le32_to_cpu(mes_hdr->mes_ucode_data_size_bytes), + PAGE_SIZE); + } + + return 0; +out: + amdgpu_ucode_release(&adev->mes.fw[pipe]); + return r; +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h index 97c05d08a551..547ec35691fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h @@ -306,6 +306,7 @@ struct amdgpu_mes_funcs { int amdgpu_mes_ctx_get_offs(struct amdgpu_ring *ring, unsigned int id_offs); +int amdgpu_mes_init_microcode(struct amdgpu_device *adev, int pipe); int amdgpu_mes_init(struct amdgpu_device *adev); void amdgpu_mes_fini(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h index 8a39300b1a84..32fe05c810c6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h @@ -35,7 +35,6 @@ #include <drm/drm_edid.h> #include <drm/drm_encoder.h> #include <drm/drm_fixed.h> -#include <drm/drm_crtc_helper.h> #include <drm/drm_framebuffer.h> #include <drm/drm_probe_helper.h> #include <linux/i2c.h> @@ -534,6 +533,7 @@ struct amdgpu_connector { void *con_priv; bool dac_load_detect; bool detected_by_load; /* if the connection status was determined by load */ + bool detected_hpd_without_ddc; /* if an HPD signal was detected on DVI, but ddc probing failed */ uint16_t connector_object_id; struct amdgpu_hpd hpd; struct amdgpu_router router; @@ -549,8 +549,8 @@ struct amdgpu_mst_connector { struct drm_dp_mst_topology_mgr mst_mgr; struct amdgpu_dm_dp_aux dm_dp_aux; - struct drm_dp_mst_port *port; - struct amdgpu_connector *mst_port; + struct drm_dp_mst_port *mst_output_port; + struct amdgpu_connector *mst_root; bool is_mst_connector; struct amdgpu_encoder *mst_encoder; }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 25a68d8888e0..6c7d672412b2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -139,7 +139,7 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain) if (flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) places[c].lpfn = visible_pfn; - else + else if (adev->gmc.real_vram_size != adev->gmc.visible_vram_size) places[c].flags |= TTM_PL_FLAG_TOPDOWN; if (flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS) @@ -1315,7 +1315,7 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo) if (!bo->resource || bo->resource->mem_type != TTM_PL_VRAM || !(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE) || - adev->in_suspend || adev->shutdown) + adev->in_suspend || drm_dev_is_unplugged(adev_to_drm(adev))) return; if (WARN_ON_ONCE(!dma_resv_trylock(bo->base.resv))) @@ -1574,9 +1574,9 @@ u64 amdgpu_bo_print_info(int id, struct amdgpu_bo *bo, struct seq_file *m) attachment = READ_ONCE(bo->tbo.base.import_attach); if (attachment) - seq_printf(m, " imported from %p", dma_buf); + seq_printf(m, " imported from ino:%lu", file_inode(dma_buf->file)->i_ino); else if (dma_buf) - seq_printf(m, " exported as %p", dma_buf); + seq_printf(m, " exported as ino:%lu", file_inode(dma_buf->file)->i_ino); amdgpu_bo_print_flag(m, bo, CPU_ACCESS_REQUIRED); amdgpu_bo_print_flag(m, bo, NO_CPU_ACCESS); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 7a2fc920739b..3f5d13035aff 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -66,7 +66,8 @@ static int psp_ring_init(struct psp_context *psp, /* allocate 4k Page of Local Frame Buffer memory for ring */ ring->ring_size = 0x1000; ret = amdgpu_bo_create_kernel(adev, ring->ring_size, PAGE_SIZE, - AMDGPU_GEM_DOMAIN_VRAM, + AMDGPU_GEM_DOMAIN_VRAM | + AMDGPU_GEM_DOMAIN_GTT, &adev->firmware.rbuf, &ring->ring_mem_mc_addr, (void **)&ring->ring_mem); @@ -122,6 +123,38 @@ static void psp_check_pmfw_centralized_cstate_management(struct psp_context *psp } } +static int psp_init_sriov_microcode(struct psp_context *psp) +{ + struct amdgpu_device *adev = psp->adev; + char ucode_prefix[30]; + int ret = 0; + + amdgpu_ucode_ip_version_decode(adev, MP0_HWIP, ucode_prefix, sizeof(ucode_prefix)); + + switch (adev->ip_versions[MP0_HWIP][0]) { + case IP_VERSION(9, 0, 0): + case IP_VERSION(11, 0, 7): + case IP_VERSION(11, 0, 9): + adev->virt.autoload_ucode_id = AMDGPU_UCODE_ID_CP_MEC2; + ret = psp_init_cap_microcode(psp, ucode_prefix); + break; + case IP_VERSION(13, 0, 2): + adev->virt.autoload_ucode_id = AMDGPU_UCODE_ID_CP_MEC2; + ret = psp_init_cap_microcode(psp, ucode_prefix); + ret &= psp_init_ta_microcode(psp, ucode_prefix); + break; + case IP_VERSION(13, 0, 0): + adev->virt.autoload_ucode_id = 0; + break; + case IP_VERSION(13, 0, 10): + adev->virt.autoload_ucode_id = AMDGPU_UCODE_ID_CP_MES1_DATA; + break; + default: + return -EINVAL; + } + return ret; +} + static int psp_early_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; @@ -192,7 +225,10 @@ static int psp_early_init(void *handle) psp_check_pmfw_centralized_cstate_management(psp); - return 0; + if (amdgpu_sriov_vf(adev)) + return psp_init_sriov_microcode(psp); + else + return psp_init_microcode(psp); } void psp_ta_free_shared_buf(struct ta_mem_context *mem_ctx) @@ -300,7 +336,7 @@ static bool psp_get_runtime_db_entry(struct amdgpu_device *adev, if (db_header.cookie != PSP_RUNTIME_DB_COOKIE_ID) { /* runtime db doesn't exist, exit */ - dev_warn(adev->dev, "PSP runtime database doesn't exist\n"); + dev_dbg(adev->dev, "PSP runtime database doesn't exist\n"); return false; } @@ -350,42 +386,6 @@ static bool psp_get_runtime_db_entry(struct amdgpu_device *adev, return ret; } -static int psp_init_sriov_microcode(struct psp_context *psp) -{ - struct amdgpu_device *adev = psp->adev; - int ret = 0; - - switch (adev->ip_versions[MP0_HWIP][0]) { - case IP_VERSION(9, 0, 0): - adev->virt.autoload_ucode_id = AMDGPU_UCODE_ID_CP_MEC2; - ret = psp_init_cap_microcode(psp, "vega10"); - break; - case IP_VERSION(11, 0, 9): - adev->virt.autoload_ucode_id = AMDGPU_UCODE_ID_CP_MEC2; - ret = psp_init_cap_microcode(psp, "navi12"); - break; - case IP_VERSION(11, 0, 7): - adev->virt.autoload_ucode_id = AMDGPU_UCODE_ID_CP_MEC2; - ret = psp_init_cap_microcode(psp, "sienna_cichlid"); - break; - case IP_VERSION(13, 0, 2): - adev->virt.autoload_ucode_id = AMDGPU_UCODE_ID_CP_MEC2; - ret = psp_init_cap_microcode(psp, "aldebaran"); - ret &= psp_init_ta_microcode(psp, "aldebaran"); - break; - case IP_VERSION(13, 0, 0): - adev->virt.autoload_ucode_id = 0; - break; - case IP_VERSION(13, 0, 10): - adev->virt.autoload_ucode_id = AMDGPU_UCODE_ID_CP_MES1_DATA; - break; - default: - BUG(); - break; - } - return ret; -} - static int psp_sw_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; @@ -401,15 +401,6 @@ static int psp_sw_init(void *handle) ret = -ENOMEM; } - if (amdgpu_sriov_vf(adev)) - ret = psp_init_sriov_microcode(psp); - else - ret = psp_init_microcode(psp); - if (ret) { - DRM_ERROR("Failed to load psp firmware!\n"); - return ret; - } - adev->psp.xgmi_context.supports_extended_data = !adev->gmc.xgmi.connected_to_cpu && adev->ip_versions[MP0_HWIP][0] == IP_VERSION(13, 0, 2); @@ -514,20 +505,11 @@ static int psp_sw_fini(void *handle) psp_memory_training_fini(psp); - release_firmware(psp->sos_fw); - psp->sos_fw = NULL; - - release_firmware(psp->asd_fw); - psp->asd_fw = NULL; - - release_firmware(psp->ta_fw); - psp->ta_fw = NULL; - - release_firmware(psp->cap_fw); - psp->cap_fw = NULL; - - release_firmware(psp->toc_fw); - psp->toc_fw = NULL; + amdgpu_ucode_release(&psp->sos_fw); + amdgpu_ucode_release(&psp->asd_fw); + amdgpu_ucode_release(&psp->ta_fw); + amdgpu_ucode_release(&psp->cap_fw); + amdgpu_ucode_release(&psp->toc_fw); if (adev->ip_versions[MP0_HWIP][0] == IP_VERSION(11, 0, 0) || adev->ip_versions[MP0_HWIP][0] == IP_VERSION(11, 0, 7)) @@ -620,7 +602,7 @@ psp_cmd_submit_buf(struct psp_context *psp, struct psp_gfx_cmd_resp *cmd, uint64_t fence_mc_addr) { int ret; - int index, idx; + int index; int timeout = 20000; bool ras_intr = false; bool skip_unsupport = false; @@ -628,9 +610,6 @@ psp_cmd_submit_buf(struct psp_context *psp, if (psp->adev->no_hw_access) return 0; - if (!drm_dev_enter(adev_to_drm(psp->adev), &idx)) - return 0; - memset(psp->cmd_buf_mem, 0, PSP_CMD_BUFFER_SIZE); memcpy(psp->cmd_buf_mem, cmd, sizeof(struct psp_gfx_cmd_resp)); @@ -694,7 +673,6 @@ psp_cmd_submit_buf(struct psp_context *psp, } exit: - drm_dev_exit(idx); return ret; } @@ -797,9 +775,13 @@ static int psp_tmr_init(struct psp_context *psp) if (!psp->tmr_bo) { pptr = amdgpu_sriov_vf(psp->adev) ? &tmr_buf : NULL; - ret = amdgpu_bo_create_kernel(psp->adev, tmr_size, PSP_TMR_ALIGNMENT, - AMDGPU_GEM_DOMAIN_VRAM, - &psp->tmr_bo, &psp->tmr_mc_addr, pptr); + ret = amdgpu_bo_create_kernel(psp->adev, tmr_size, + PSP_TMR_ALIGNMENT, + AMDGPU_HAS_VRAM(psp->adev) ? + AMDGPU_GEM_DOMAIN_VRAM : + AMDGPU_GEM_DOMAIN_GTT, + &psp->tmr_bo, &psp->tmr_mc_addr, + pptr); } return ret; @@ -1092,7 +1074,8 @@ int psp_ta_init_shared_buf(struct psp_context *psp, * physical) for ta to host memory */ return amdgpu_bo_create_kernel(psp->adev, mem_ctx->shared_mem_size, - PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM, + PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM | + AMDGPU_GEM_DOMAIN_GTT, &mem_ctx->shared_bo, &mem_ctx->shared_mc_addr, &mem_ctx->shared_buf); @@ -1685,7 +1668,7 @@ static int psp_hdcp_initialize(struct psp_context *psp) psp->hdcp_context.context.mem_context.shared_mem_size = PSP_HDCP_SHARED_MEM_SIZE; psp->hdcp_context.context.ta_load_type = GFX_CMD_ID_LOAD_TA; - if (!psp->hdcp_context.context.initialized) { + if (!psp->hdcp_context.context.mem_context.shared_buf) { ret = psp_ta_init_shared_buf(psp, &psp->hdcp_context.context.mem_context); if (ret) return ret; @@ -1752,7 +1735,7 @@ static int psp_dtm_initialize(struct psp_context *psp) psp->dtm_context.context.mem_context.shared_mem_size = PSP_DTM_SHARED_MEM_SIZE; psp->dtm_context.context.ta_load_type = GFX_CMD_ID_LOAD_TA; - if (!psp->dtm_context.context.initialized) { + if (!psp->dtm_context.context.mem_context.shared_buf) { ret = psp_ta_init_shared_buf(psp, &psp->dtm_context.context.mem_context); if (ret) return ret; @@ -1820,7 +1803,7 @@ static int psp_rap_initialize(struct psp_context *psp) psp->rap_context.context.mem_context.shared_mem_size = PSP_RAP_SHARED_MEM_SIZE; psp->rap_context.context.ta_load_type = GFX_CMD_ID_LOAD_TA; - if (!psp->rap_context.context.initialized) { + if (!psp->rap_context.context.mem_context.shared_buf) { ret = psp_ta_init_shared_buf(psp, &psp->rap_context.context.mem_context); if (ret) return ret; @@ -1901,7 +1884,7 @@ out_unlock: static int psp_securedisplay_initialize(struct psp_context *psp) { int ret; - struct securedisplay_cmd *securedisplay_cmd; + struct ta_securedisplay_cmd *securedisplay_cmd; /* * TODO: bypass the initialize in sriov for now @@ -2908,25 +2891,15 @@ int psp_ring_cmd_submit(struct psp_context *psp, return 0; } -int psp_init_asd_microcode(struct psp_context *psp, - const char *chip_name) +int psp_init_asd_microcode(struct psp_context *psp, const char *chip_name) { struct amdgpu_device *adev = psp->adev; char fw_name[PSP_FW_NAME_LEN]; const struct psp_firmware_header_v1_0 *asd_hdr; int err = 0; - if (!chip_name) { - dev_err(adev->dev, "invalid chip name for asd microcode\n"); - return -EINVAL; - } - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_asd.bin", chip_name); - err = request_firmware(&adev->psp.asd_fw, fw_name, adev->dev); - if (err) - goto out; - - err = amdgpu_ucode_validate(adev->psp.asd_fw); + err = amdgpu_ucode_request(adev, &adev->psp.asd_fw, fw_name); if (err) goto out; @@ -2938,31 +2911,19 @@ int psp_init_asd_microcode(struct psp_context *psp, le32_to_cpu(asd_hdr->header.ucode_array_offset_bytes); return 0; out: - dev_err(adev->dev, "fail to initialize asd microcode\n"); - release_firmware(adev->psp.asd_fw); - adev->psp.asd_fw = NULL; + amdgpu_ucode_release(&adev->psp.asd_fw); return err; } -int psp_init_toc_microcode(struct psp_context *psp, - const char *chip_name) +int psp_init_toc_microcode(struct psp_context *psp, const char *chip_name) { struct amdgpu_device *adev = psp->adev; char fw_name[PSP_FW_NAME_LEN]; const struct psp_firmware_header_v1_0 *toc_hdr; int err = 0; - if (!chip_name) { - dev_err(adev->dev, "invalid chip name for toc microcode\n"); - return -EINVAL; - } - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_toc.bin", chip_name); - err = request_firmware(&adev->psp.toc_fw, fw_name, adev->dev); - if (err) - goto out; - - err = amdgpu_ucode_validate(adev->psp.toc_fw); + err = amdgpu_ucode_request(adev, &adev->psp.toc_fw, fw_name); if (err) goto out; @@ -2974,9 +2935,7 @@ int psp_init_toc_microcode(struct psp_context *psp, le32_to_cpu(toc_hdr->header.ucode_array_offset_bytes); return 0; out: - dev_err(adev->dev, "fail to request/validate toc microcode\n"); - release_firmware(adev->psp.toc_fw); - adev->psp.toc_fw = NULL; + amdgpu_ucode_release(&adev->psp.toc_fw); return err; } @@ -3107,8 +3066,7 @@ static int psp_init_sos_base_fw(struct amdgpu_device *adev) return 0; } -int psp_init_sos_microcode(struct psp_context *psp, - const char *chip_name) +int psp_init_sos_microcode(struct psp_context *psp, const char *chip_name) { struct amdgpu_device *adev = psp->adev; char fw_name[PSP_FW_NAME_LEN]; @@ -3121,17 +3079,8 @@ int psp_init_sos_microcode(struct psp_context *psp, uint8_t *ucode_array_start_addr; int fw_index = 0; - if (!chip_name) { - dev_err(adev->dev, "invalid chip name for sos microcode\n"); - return -EINVAL; - } - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sos.bin", chip_name); - err = request_firmware(&adev->psp.sos_fw, fw_name, adev->dev); - if (err) - goto out; - - err = amdgpu_ucode_validate(adev->psp.sos_fw); + err = amdgpu_ucode_request(adev, &adev->psp.sos_fw, fw_name); if (err) goto out; @@ -3203,10 +3152,7 @@ int psp_init_sos_microcode(struct psp_context *psp, return 0; out: - dev_err(adev->dev, - "failed to init sos firmware\n"); - release_firmware(adev->psp.sos_fw); - adev->psp.sos_fw = NULL; + amdgpu_ucode_release(&adev->psp.sos_fw); return err; } @@ -3272,41 +3218,76 @@ static int parse_ta_bin_descriptor(struct psp_context *psp, return 0; } -int psp_init_ta_microcode(struct psp_context *psp, - const char *chip_name) +static int parse_ta_v1_microcode(struct psp_context *psp) { + const struct ta_firmware_header_v1_0 *ta_hdr; struct amdgpu_device *adev = psp->adev; - char fw_name[PSP_FW_NAME_LEN]; - const struct ta_firmware_header_v2_0 *ta_hdr; - int err = 0; - int ta_index = 0; - if (!chip_name) { - dev_err(adev->dev, "invalid chip name for ta microcode\n"); + ta_hdr = (const struct ta_firmware_header_v1_0 *) adev->psp.ta_fw->data; + + if (le16_to_cpu(ta_hdr->header.header_version_major) != 1) return -EINVAL; - } - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ta.bin", chip_name); - err = request_firmware(&adev->psp.ta_fw, fw_name, adev->dev); - if (err) - goto out; + adev->psp.xgmi_context.context.bin_desc.fw_version = + le32_to_cpu(ta_hdr->xgmi.fw_version); + adev->psp.xgmi_context.context.bin_desc.size_bytes = + le32_to_cpu(ta_hdr->xgmi.size_bytes); + adev->psp.xgmi_context.context.bin_desc.start_addr = + (uint8_t *)ta_hdr + + le32_to_cpu(ta_hdr->header.ucode_array_offset_bytes); + + adev->psp.ras_context.context.bin_desc.fw_version = + le32_to_cpu(ta_hdr->ras.fw_version); + adev->psp.ras_context.context.bin_desc.size_bytes = + le32_to_cpu(ta_hdr->ras.size_bytes); + adev->psp.ras_context.context.bin_desc.start_addr = + (uint8_t *)adev->psp.xgmi_context.context.bin_desc.start_addr + + le32_to_cpu(ta_hdr->ras.offset_bytes); + + adev->psp.hdcp_context.context.bin_desc.fw_version = + le32_to_cpu(ta_hdr->hdcp.fw_version); + adev->psp.hdcp_context.context.bin_desc.size_bytes = + le32_to_cpu(ta_hdr->hdcp.size_bytes); + adev->psp.hdcp_context.context.bin_desc.start_addr = + (uint8_t *)ta_hdr + + le32_to_cpu(ta_hdr->header.ucode_array_offset_bytes); + + adev->psp.dtm_context.context.bin_desc.fw_version = + le32_to_cpu(ta_hdr->dtm.fw_version); + adev->psp.dtm_context.context.bin_desc.size_bytes = + le32_to_cpu(ta_hdr->dtm.size_bytes); + adev->psp.dtm_context.context.bin_desc.start_addr = + (uint8_t *)adev->psp.hdcp_context.context.bin_desc.start_addr + + le32_to_cpu(ta_hdr->dtm.offset_bytes); + + adev->psp.securedisplay_context.context.bin_desc.fw_version = + le32_to_cpu(ta_hdr->securedisplay.fw_version); + adev->psp.securedisplay_context.context.bin_desc.size_bytes = + le32_to_cpu(ta_hdr->securedisplay.size_bytes); + adev->psp.securedisplay_context.context.bin_desc.start_addr = + (uint8_t *)adev->psp.hdcp_context.context.bin_desc.start_addr + + le32_to_cpu(ta_hdr->securedisplay.offset_bytes); + + adev->psp.ta_fw_version = le32_to_cpu(ta_hdr->header.ucode_version); - err = amdgpu_ucode_validate(adev->psp.ta_fw); - if (err) - goto out; + return 0; +} + +static int parse_ta_v2_microcode(struct psp_context *psp) +{ + const struct ta_firmware_header_v2_0 *ta_hdr; + struct amdgpu_device *adev = psp->adev; + int err = 0; + int ta_index = 0; ta_hdr = (const struct ta_firmware_header_v2_0 *)adev->psp.ta_fw->data; - if (le16_to_cpu(ta_hdr->header.header_version_major) != 2) { - dev_err(adev->dev, "unsupported TA header version\n"); - err = -EINVAL; - goto out; - } + if (le16_to_cpu(ta_hdr->header.header_version_major) != 2) + return -EINVAL; if (le32_to_cpu(ta_hdr->ta_fw_bin_count) >= UCODE_MAX_PSP_PACKAGING) { dev_err(adev->dev, "packed TA count exceeds maximum limit\n"); - err = -EINVAL; - goto out; + return -EINVAL; } for (ta_index = 0; ta_index < le32_to_cpu(ta_hdr->ta_fw_bin_count); ta_index++) { @@ -3314,19 +3295,44 @@ int psp_init_ta_microcode(struct psp_context *psp, &ta_hdr->ta_fw_bin[ta_index], ta_hdr); if (err) - goto out; + return err; } return 0; -out: - dev_err(adev->dev, "fail to initialize ta microcode\n"); - release_firmware(adev->psp.ta_fw); - adev->psp.ta_fw = NULL; +} + +int psp_init_ta_microcode(struct psp_context *psp, const char *chip_name) +{ + const struct common_firmware_header *hdr; + struct amdgpu_device *adev = psp->adev; + char fw_name[PSP_FW_NAME_LEN]; + int err; + + snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ta.bin", chip_name); + err = amdgpu_ucode_request(adev, &adev->psp.ta_fw, fw_name); + if (err) + return err; + + hdr = (const struct common_firmware_header *)adev->psp.ta_fw->data; + switch (le16_to_cpu(hdr->header_version_major)) { + case 1: + err = parse_ta_v1_microcode(psp); + break; + case 2: + err = parse_ta_v2_microcode(psp); + break; + default: + dev_err(adev->dev, "unsupported TA header version\n"); + err = -EINVAL; + } + + if (err) + amdgpu_ucode_release(&adev->psp.ta_fw); + return err; } -int psp_init_cap_microcode(struct psp_context *psp, - const char *chip_name) +int psp_init_cap_microcode(struct psp_context *psp, const char *chip_name) { struct amdgpu_device *adev = psp->adev; char fw_name[PSP_FW_NAME_LEN]; @@ -3334,28 +3340,20 @@ int psp_init_cap_microcode(struct psp_context *psp, struct amdgpu_firmware_info *info = NULL; int err = 0; - if (!chip_name) { - dev_err(adev->dev, "invalid chip name for cap microcode\n"); - return -EINVAL; - } - if (!amdgpu_sriov_vf(adev)) { dev_err(adev->dev, "cap microcode should only be loaded under SRIOV\n"); return -EINVAL; } snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_cap.bin", chip_name); - err = request_firmware(&adev->psp.cap_fw, fw_name, adev->dev); - if (err) { - dev_warn(adev->dev, "cap microcode does not exist, skip\n"); - err = 0; - goto out; - } - - err = amdgpu_ucode_validate(adev->psp.cap_fw); + err = amdgpu_ucode_request(adev, &adev->psp.cap_fw, fw_name); if (err) { + if (err == -ENODEV) { + dev_warn(adev->dev, "cap microcode does not exist, skip\n"); + err = 0; + goto out; + } dev_err(adev->dev, "fail to initialize cap microcode\n"); - goto out; } info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CAP]; @@ -3372,8 +3370,7 @@ int psp_init_cap_microcode(struct psp_context *psp, return 0; out: - release_firmware(adev->psp.cap_fw); - adev->psp.cap_fw = NULL; + amdgpu_ucode_release(&adev->psp.cap_fw); return err; } @@ -3444,10 +3441,10 @@ static ssize_t psp_usbc_pd_fw_sysfs_write(struct device *dev, /* LFB address which is aligned to 1MB boundary per PSP request */ ret = amdgpu_bo_create_kernel(adev, usbc_pd_fw->size, 0x100000, - AMDGPU_GEM_DOMAIN_VRAM, - &fw_buf_bo, - &fw_pri_mc_addr, - &fw_pri_cpu_addr); + AMDGPU_GEM_DOMAIN_VRAM | + AMDGPU_GEM_DOMAIN_GTT, + &fw_buf_bo, &fw_pri_mc_addr, + &fw_pri_cpu_addr); if (ret) goto rel_buf; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index ad490c1e2f57..63dfcc98152d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -176,7 +176,7 @@ static int amdgpu_reserve_page_direct(struct amdgpu_device *adev, uint64_t addre if (amdgpu_bad_page_threshold != 0) { amdgpu_ras_add_bad_pages(adev, err_data.err_addr, err_data.err_addr_cnt); - amdgpu_ras_save_bad_pages(adev); + amdgpu_ras_save_bad_pages(adev, NULL); } dev_warn(adev->dev, "WARNING: THIS IS ONLY FOR TEST PURPOSES AND WILL CORRUPT RAS EEPROM\n"); @@ -706,13 +706,23 @@ static int __amdgpu_ras_feature_enable(struct amdgpu_device *adev, return 0; } +static int amdgpu_ras_check_feature_allowed(struct amdgpu_device *adev, + struct ras_common_if *head) +{ + if (amdgpu_ras_is_feature_allowed(adev, head) || + amdgpu_ras_is_poison_mode_supported(adev)) + return 1; + else + return 0; +} + /* wrapper of psp_ras_enable_features */ int amdgpu_ras_feature_enable(struct amdgpu_device *adev, struct ras_common_if *head, bool enable) { struct amdgpu_ras *con = amdgpu_ras_get_context(adev); union ta_ras_cmd_input *info; - int ret; + int ret = 0; if (!con) return -EINVAL; @@ -736,7 +746,8 @@ int amdgpu_ras_feature_enable(struct amdgpu_device *adev, } /* Do not enable if it is not allowed. */ - WARN_ON(enable && !amdgpu_ras_is_feature_allowed(adev, head)); + if (enable && !amdgpu_ras_check_feature_allowed(adev, head)) + goto out; /* Only enable ras feature operation handle on host side */ if (head->block == AMDGPU_RAS_BLOCK__GFX && @@ -754,7 +765,6 @@ int amdgpu_ras_feature_enable(struct amdgpu_device *adev, /* setup the obj */ __amdgpu_ras_feature_enable(adev, head, enable); - ret = 0; out: if (head->block == AMDGPU_RAS_BLOCK__GFX) kfree(info); @@ -910,9 +920,6 @@ static struct amdgpu_ras_block_object *amdgpu_ras_get_ras_block(struct amdgpu_de if (block >= AMDGPU_RAS_BLOCK__LAST) return NULL; - if (!amdgpu_ras_is_supported(adev, block)) - return NULL; - list_for_each_entry_safe(node, tmp, &adev->ras_list, node) { if (!node->ras_obj) { dev_warn(adev->dev, "Warning: abnormal ras list node.\n"); @@ -1087,6 +1094,10 @@ int amdgpu_ras_error_inject(struct amdgpu_device *adev, info->head.block, info->head.sub_block_index); + /* inject on guest isn't allowed, return success directly */ + if (amdgpu_sriov_vf(adev)) + return 0; + if (!obj) return -EINVAL; @@ -1122,11 +1133,54 @@ int amdgpu_ras_error_inject(struct amdgpu_device *adev, } /** - * amdgpu_ras_query_error_count -- Get error counts of all IPs + * amdgpu_ras_query_error_count_helper -- Get error counter for specific IP + * @adev: pointer to AMD GPU device + * @ce_count: pointer to an integer to be set to the count of correctible errors. + * @ue_count: pointer to an integer to be set to the count of uncorrectible errors. + * @query_info: pointer to ras_query_if + * + * Return 0 for query success or do nothing, otherwise return an error + * on failures + */ +static int amdgpu_ras_query_error_count_helper(struct amdgpu_device *adev, + unsigned long *ce_count, + unsigned long *ue_count, + struct ras_query_if *query_info) +{ + int ret; + + if (!query_info) + /* do nothing if query_info is not specified */ + return 0; + + ret = amdgpu_ras_query_error_status(adev, query_info); + if (ret) + return ret; + + *ce_count += query_info->ce_count; + *ue_count += query_info->ue_count; + + /* some hardware/IP supports read to clear + * no need to explictly reset the err status after the query call */ + if (adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 2) && + adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 4)) { + if (amdgpu_ras_reset_error_status(adev, query_info->head.block)) + dev_warn(adev->dev, + "Failed to reset error counter and error status\n"); + } + + return 0; +} + +/** + * amdgpu_ras_query_error_count -- Get error counts of all IPs or specific IP * @adev: pointer to AMD GPU device * @ce_count: pointer to an integer to be set to the count of correctible errors. * @ue_count: pointer to an integer to be set to the count of uncorrectible * errors. + * @query_info: pointer to ras_query_if if the query request is only for + * specific ip block; if info is NULL, then the qurey request is for + * all the ip blocks that support query ras error counters/status * * If set, @ce_count or @ue_count, count and return the corresponding * error counts in those integer pointers. Return 0 if the device @@ -1134,11 +1188,13 @@ int amdgpu_ras_error_inject(struct amdgpu_device *adev, */ int amdgpu_ras_query_error_count(struct amdgpu_device *adev, unsigned long *ce_count, - unsigned long *ue_count) + unsigned long *ue_count, + struct ras_query_if *query_info) { struct amdgpu_ras *con = amdgpu_ras_get_context(adev); struct ras_manager *obj; unsigned long ce, ue; + int ret; if (!adev->ras_enabled || !con) return -EOPNOTSUPP; @@ -1150,26 +1206,23 @@ int amdgpu_ras_query_error_count(struct amdgpu_device *adev, ce = 0; ue = 0; - list_for_each_entry(obj, &con->head, node) { - struct ras_query_if info = { - .head = obj->head, - }; - int res; - - res = amdgpu_ras_query_error_status(adev, &info); - if (res) - return res; + if (!query_info) { + /* query all the ip blocks that support ras query interface */ + list_for_each_entry(obj, &con->head, node) { + struct ras_query_if info = { + .head = obj->head, + }; - if (adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 2) && - adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 4)) { - if (amdgpu_ras_reset_error_status(adev, info.head.block)) - dev_warn(adev->dev, "Failed to reset error counter and error status"); + ret = amdgpu_ras_query_error_count_helper(adev, &ce, &ue, &info); } - - ce += info.ce_count; - ue += info.ue_count; + } else { + /* query specific ip block */ + ret = amdgpu_ras_query_error_count_helper(adev, &ce, &ue, query_info); } + if (ret) + return ret; + if (ce_count) *ce_count = ce; @@ -1564,14 +1617,14 @@ static void amdgpu_ras_interrupt_poison_consumption_handler(struct ras_manager * struct amdgpu_ras_block_object *block_obj = amdgpu_ras_get_ras_block(adev, obj->head.block, 0); - if (!block_obj || !block_obj->hw_ops) + if (!block_obj) return; /* both query_poison_status and handle_poison_consumption are optional, * but at least one of them should be implemented if we need poison * consumption handler */ - if (block_obj->hw_ops->query_poison_status) { + if (block_obj->hw_ops && block_obj->hw_ops->query_poison_status) { poison_stat = block_obj->hw_ops->query_poison_status(adev); if (!poison_stat) { /* Not poison consumption interrupt, no need to handle it */ @@ -1585,7 +1638,7 @@ static void amdgpu_ras_interrupt_poison_consumption_handler(struct ras_manager * if (!adev->gmc.xgmi.connected_to_cpu) amdgpu_umc_poison_handler(adev, false); - if (block_obj->hw_ops->handle_poison_consumption) + if (block_obj->hw_ops && block_obj->hw_ops->handle_poison_consumption) poison_stat = block_obj->hw_ops->handle_poison_consumption(adev); /* gpu reset is fallback for failed and default cases */ @@ -1593,6 +1646,8 @@ static void amdgpu_ras_interrupt_poison_consumption_handler(struct ras_manager * dev_info(adev->dev, "GPU reset for %s RAS poison consumption is issued!\n", block_obj->ras_comm.name); amdgpu_ras_reset_gpu(adev); + } else { + amdgpu_gfx_poison_consumption_handler(adev, entry); } } @@ -2029,22 +2084,32 @@ out: /* * write error record array to eeprom, the function should be * protected by recovery_lock + * new_cnt: new added UE count, excluding reserved bad pages, can be NULL */ -int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev) +int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev, + unsigned long *new_cnt) { struct amdgpu_ras *con = amdgpu_ras_get_context(adev); struct ras_err_handler_data *data; struct amdgpu_ras_eeprom_control *control; int save_count; - if (!con || !con->eh_data) + if (!con || !con->eh_data) { + if (new_cnt) + *new_cnt = 0; + return 0; + } mutex_lock(&con->recovery_lock); control = &con->eeprom_control; data = con->eh_data; save_count = data->count - control->ras_num_recs; mutex_unlock(&con->recovery_lock); + + if (new_cnt) + *new_cnt = save_count / adev->umc.retire_unit; + /* only new entries are saved */ if (save_count > 0) { if (amdgpu_ras_eeprom_append(control, @@ -2131,11 +2196,12 @@ static void amdgpu_ras_validate_threshold(struct amdgpu_device *adev, /* * Justification of value bad_page_cnt_threshold in ras structure * - * Generally, -1 <= amdgpu_bad_page_threshold <= max record length - * in eeprom, and introduce two scenarios accordingly. + * Generally, 0 <= amdgpu_bad_page_threshold <= max record length + * in eeprom or amdgpu_bad_page_threshold == -2, introduce two + * scenarios accordingly. * * Bad page retirement enablement: - * - If amdgpu_bad_page_threshold = -1, + * - If amdgpu_bad_page_threshold = -2, * bad_page_cnt_threshold = typical value by formula. * * - When the value from user is 0 < amdgpu_bad_page_threshold < @@ -2344,22 +2410,24 @@ static void amdgpu_ras_check_supported(struct amdgpu_device *adev) if (amdgpu_atomfirmware_sram_ecc_supported(adev)) { dev_info(adev->dev, "SRAM ECC is active.\n"); - if (!amdgpu_sriov_vf(adev)) { + if (!amdgpu_sriov_vf(adev)) adev->ras_hw_enabled |= ~(1 << AMDGPU_RAS_BLOCK__UMC | 1 << AMDGPU_RAS_BLOCK__DF); - - if (adev->ip_versions[VCN_HWIP][0] == IP_VERSION(2, 6, 0) || - adev->ip_versions[VCN_HWIP][0] == IP_VERSION(4, 0, 0)) - adev->ras_hw_enabled |= (1 << AMDGPU_RAS_BLOCK__VCN | - 1 << AMDGPU_RAS_BLOCK__JPEG); - else - adev->ras_hw_enabled &= ~(1 << AMDGPU_RAS_BLOCK__VCN | - 1 << AMDGPU_RAS_BLOCK__JPEG); - } else { + else adev->ras_hw_enabled |= (1 << AMDGPU_RAS_BLOCK__PCIE_BIF | 1 << AMDGPU_RAS_BLOCK__SDMA | 1 << AMDGPU_RAS_BLOCK__GFX); - } + + /* VCN/JPEG RAS can be supported on both bare metal and + * SRIOV environment + */ + if (adev->ip_versions[VCN_HWIP][0] == IP_VERSION(2, 6, 0) || + adev->ip_versions[VCN_HWIP][0] == IP_VERSION(4, 0, 0)) + adev->ras_hw_enabled |= (1 << AMDGPU_RAS_BLOCK__VCN | + 1 << AMDGPU_RAS_BLOCK__JPEG); + else + adev->ras_hw_enabled &= ~(1 << AMDGPU_RAS_BLOCK__VCN | + 1 << AMDGPU_RAS_BLOCK__JPEG); } else { dev_info(adev->dev, "SRAM ECC is not presented.\n"); } @@ -2395,7 +2463,7 @@ static void amdgpu_ras_counte_dw(struct work_struct *work) /* Cache new values. */ - if (amdgpu_ras_query_error_count(adev, &ce_count, &ue_count) == 0) { + if (amdgpu_ras_query_error_count(adev, &ce_count, &ue_count, NULL) == 0) { atomic_set(&con->ras_ce_count, ce_count); atomic_set(&con->ras_ue_count, ue_count); } @@ -2405,11 +2473,42 @@ Out: pm_runtime_put_autosuspend(dev->dev); } +static void amdgpu_ras_query_poison_mode(struct amdgpu_device *adev) +{ + struct amdgpu_ras *con = amdgpu_ras_get_context(adev); + bool df_poison, umc_poison; + + /* poison setting is useless on SRIOV guest */ + if (amdgpu_sriov_vf(adev) || !con) + return; + + /* Init poison supported flag, the default value is false */ + if (adev->gmc.xgmi.connected_to_cpu) { + /* enabled by default when GPU is connected to CPU */ + con->poison_supported = true; + } else if (adev->df.funcs && + adev->df.funcs->query_ras_poison_mode && + adev->umc.ras && + adev->umc.ras->query_ras_poison_mode) { + df_poison = + adev->df.funcs->query_ras_poison_mode(adev); + umc_poison = + adev->umc.ras->query_ras_poison_mode(adev); + + /* Only poison is set in both DF and UMC, we can support it */ + if (df_poison && umc_poison) + con->poison_supported = true; + else if (df_poison != umc_poison) + dev_warn(adev->dev, + "Poison setting is inconsistent in DF/UMC(%d:%d)!\n", + df_poison, umc_poison); + } +} + int amdgpu_ras_init(struct amdgpu_device *adev) { struct amdgpu_ras *con = amdgpu_ras_get_context(adev); int r; - bool df_poison, umc_poison; if (con) return 0; @@ -2484,26 +2583,7 @@ int amdgpu_ras_init(struct amdgpu_device *adev) goto release_con; } - /* Init poison supported flag, the default value is false */ - if (adev->gmc.xgmi.connected_to_cpu) { - /* enabled by default when GPU is connected to CPU */ - con->poison_supported = true; - } - else if (adev->df.funcs && - adev->df.funcs->query_ras_poison_mode && - adev->umc.ras && - adev->umc.ras->query_ras_poison_mode) { - df_poison = - adev->df.funcs->query_ras_poison_mode(adev); - umc_poison = - adev->umc.ras->query_ras_poison_mode(adev); - /* Only poison is set in both DF and UMC, we can support it */ - if (df_poison && umc_poison) - con->poison_supported = true; - else if (df_poison != umc_poison) - dev_warn(adev->dev, "Poison setting is inconsistent in DF/UMC(%d:%d)!\n", - df_poison, umc_poison); - } + amdgpu_ras_query_poison_mode(adev); if (amdgpu_ras_fs_init(adev)) { r = -EINVAL; @@ -2564,6 +2644,7 @@ int amdgpu_ras_block_late_init(struct amdgpu_device *adev, { struct amdgpu_ras_block_object *ras_obj = NULL; struct amdgpu_ras *con = amdgpu_ras_get_context(adev); + struct ras_query_if *query_info; unsigned long ue_count, ce_count; int r; @@ -2605,11 +2686,17 @@ int amdgpu_ras_block_late_init(struct amdgpu_device *adev, /* Those are the cached values at init. */ - if (amdgpu_ras_query_error_count(adev, &ce_count, &ue_count) == 0) { + query_info = kzalloc(sizeof(struct ras_query_if), GFP_KERNEL); + if (!query_info) + return -ENOMEM; + memcpy(&query_info->head, ras_block, sizeof(struct ras_common_if)); + + if (amdgpu_ras_query_error_count(adev, &ce_count, &ue_count, query_info) == 0) { atomic_set(&con->ras_ce_count, ce_count); atomic_set(&con->ras_ue_count, ue_count); } + kfree(query_info); return 0; interrupt: @@ -2946,11 +3033,26 @@ int amdgpu_ras_set_context(struct amdgpu_device *adev, struct amdgpu_ras *ras_co int amdgpu_ras_is_supported(struct amdgpu_device *adev, unsigned int block) { + int ret = 0; struct amdgpu_ras *ras = amdgpu_ras_get_context(adev); if (block >= AMDGPU_RAS_BLOCK_COUNT) return 0; - return ras && (adev->ras_enabled & (1 << block)); + + ret = ras && (adev->ras_enabled & (1 << block)); + + /* For the special asic with mem ecc enabled but sram ecc + * not enabled, even if the ras block is not supported on + * .ras_enabled, if the asic supports poison mode and the + * ras block has ras configuration, it can be considered + * that the ras block supports ras function. + */ + if (!ret && + amdgpu_ras_is_poison_mode_supported(adev) && + amdgpu_ras_get_ras_block(adev, block, 0)) + ret = 1; + + return ret; } int amdgpu_ras_reset_gpu(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h index bf5a95104ec1..ef38f4c93df0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h @@ -540,13 +540,15 @@ void amdgpu_ras_suspend(struct amdgpu_device *adev); int amdgpu_ras_query_error_count(struct amdgpu_device *adev, unsigned long *ce_count, - unsigned long *ue_count); + unsigned long *ue_count, + struct ras_query_if *query_info); /* error handling functions */ int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev, struct eeprom_table_record *bps, int pages); -int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev); +int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev, + unsigned long *new_cnt); static inline enum ta_ras_block amdgpu_ras_block_to_ta(enum amdgpu_ras_block block) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c index 2d9f3f4cd79e..2e08fce87521 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c @@ -417,7 +417,8 @@ bool amdgpu_ras_eeprom_check_err_threshold(struct amdgpu_device *adev) { struct amdgpu_ras *con = amdgpu_ras_get_context(adev); - if (!__is_ras_eeprom_supported(adev)) + if (!__is_ras_eeprom_supported(adev) || + !amdgpu_bad_page_threshold) return false; /* skip check eeprom table for VEGA20 Gaming */ @@ -428,10 +429,18 @@ bool amdgpu_ras_eeprom_check_err_threshold(struct amdgpu_device *adev) return false; if (con->eeprom_control.tbl_hdr.header == RAS_TABLE_HDR_BAD) { - dev_warn(adev->dev, "This GPU is in BAD status."); - dev_warn(adev->dev, "Please retire it or set a larger " - "threshold value when reloading driver.\n"); - return true; + if (amdgpu_bad_page_threshold == -1) { + dev_warn(adev->dev, "RAS records:%d exceed threshold:%d", + con->eeprom_control.ras_num_recs, con->bad_page_cnt_threshold); + dev_warn(adev->dev, + "But GPU can be operated due to bad_page_threshold = -1.\n"); + return false; + } else { + dev_warn(adev->dev, "This GPU is in BAD status."); + dev_warn(adev->dev, "Please retire it or set a larger " + "threshold value when reloading driver.\n"); + return true; + } } return false; @@ -1191,8 +1200,8 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control, } else { dev_err(adev->dev, "RAS records:%d exceed threshold:%d", control->ras_num_recs, ras->bad_page_cnt_threshold); - if (amdgpu_bad_page_threshold == -2) { - dev_warn(adev->dev, "GPU will be initialized due to bad_page_threshold = -2."); + if (amdgpu_bad_page_threshold == -1) { + dev_warn(adev->dev, "GPU will be initialized due to bad_page_threshold = -1."); res = 0; } else { *exceed_err_limit = true; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c index f778466bb9db..6437ead87e5f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c @@ -24,6 +24,7 @@ #include "amdgpu_reset.h" #include "aldebaran.h" #include "sienna_cichlid.h" +#include "smu_v13_0_10.h" int amdgpu_reset_add_handler(struct amdgpu_reset_control *reset_ctl, struct amdgpu_reset_handler *handler) @@ -44,6 +45,9 @@ int amdgpu_reset_init(struct amdgpu_device *adev) case IP_VERSION(11, 0, 7): ret = sienna_cichlid_reset_init(adev); break; + case IP_VERSION(13, 0, 10): + ret = smu_v13_0_10_reset_init(adev); + break; default: break; } @@ -62,6 +66,9 @@ int amdgpu_reset_fini(struct amdgpu_device *adev) case IP_VERSION(11, 0, 7): ret = sienna_cichlid_reset_fini(adev); break; + case IP_VERSION(13, 0, 10): + ret = smu_v13_0_10_reset_fini(adev); + break; default: break; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h index f752c7ae7f60..3989e755a5b4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h @@ -295,7 +295,7 @@ struct amdgpu_ring { #define amdgpu_ring_parse_cs(r, p, job, ib) ((r)->funcs->parse_cs((p), (job), (ib))) #define amdgpu_ring_patch_cs_in_place(r, p, job, ib) ((r)->funcs->patch_cs_in_place((p), (job), (ib))) #define amdgpu_ring_test_ring(r) (r)->funcs->test_ring((r)) -#define amdgpu_ring_test_ib(r, t) (r)->funcs->test_ib((r), (t)) +#define amdgpu_ring_test_ib(r, t) ((r)->funcs->test_ib ? (r)->funcs->test_ib((r), (t)) : 0) #define amdgpu_ring_get_rptr(r) (r)->funcs->get_rptr((r)) #define amdgpu_ring_get_wptr(r) (r)->funcs->get_wptr((r)) #define amdgpu_ring_set_wptr(r) (r)->funcs->set_wptr((r)) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c index 012b72d00e04..85fb730d9fc8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c @@ -93,7 +93,8 @@ int amdgpu_gfx_rlc_init_sr(struct amdgpu_device *adev, u32 dws) /* allocate save restore block */ r = amdgpu_bo_create_reserved(adev, dws * 4, PAGE_SIZE, - AMDGPU_GEM_DOMAIN_VRAM, + AMDGPU_GEM_DOMAIN_VRAM | + AMDGPU_GEM_DOMAIN_GTT, &adev->gfx.rlc.save_restore_obj, &adev->gfx.rlc.save_restore_gpu_addr, (void **)&adev->gfx.rlc.sr_ptr); @@ -130,7 +131,8 @@ int amdgpu_gfx_rlc_init_csb(struct amdgpu_device *adev) /* allocate clear state block */ adev->gfx.rlc.clear_state_size = dws = adev->gfx.rlc.funcs->get_csb_size(adev); r = amdgpu_bo_create_kernel(adev, dws * 4, PAGE_SIZE, - AMDGPU_GEM_DOMAIN_VRAM, + AMDGPU_GEM_DOMAIN_VRAM | + AMDGPU_GEM_DOMAIN_GTT, &adev->gfx.rlc.clear_state_obj, &adev->gfx.rlc.clear_state_gpu_addr, (void **)&adev->gfx.rlc.cs_ptr); @@ -156,7 +158,8 @@ int amdgpu_gfx_rlc_init_cpt(struct amdgpu_device *adev) int r; r = amdgpu_bo_create_reserved(adev, adev->gfx.rlc.cp_table_size, - PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM, + PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM | + AMDGPU_GEM_DOMAIN_GTT, &adev->gfx.rlc.cp_table_obj, &adev->gfx.rlc.cp_table_gpu_addr, (void **)&adev->gfx.rlc.cp_table_ptr); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c index ea5278f094c0..231ca06bc9c7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c @@ -154,16 +154,11 @@ int amdgpu_sdma_process_ecc_irq(struct amdgpu_device *adev, static int amdgpu_sdma_init_inst_ctx(struct amdgpu_sdma_instance *sdma_inst) { - int err = 0; uint16_t version_major; const struct common_firmware_header *header = NULL; const struct sdma_firmware_header_v1_0 *hdr; const struct sdma_firmware_header_v2_0 *hdr_v2; - err = amdgpu_ucode_validate(sdma_inst->fw); - if (err) - return err; - header = (const struct common_firmware_header *) sdma_inst->fw->data; version_major = le16_to_cpu(header->header_version_major); @@ -195,7 +190,7 @@ void amdgpu_sdma_destroy_inst_ctx(struct amdgpu_device *adev, int i; for (i = 0; i < adev->sdma.num_instances; i++) { - release_firmware(adev->sdma.instance[i].fw); + amdgpu_ucode_release(&adev->sdma.instance[i].fw); if (duplicate) break; } @@ -205,16 +200,22 @@ void amdgpu_sdma_destroy_inst_ctx(struct amdgpu_device *adev, } int amdgpu_sdma_init_microcode(struct amdgpu_device *adev, - char *fw_name, u32 instance, - bool duplicate) + u32 instance, bool duplicate) { struct amdgpu_firmware_info *info = NULL; const struct common_firmware_header *header = NULL; - int err = 0, i; + int err, i; const struct sdma_firmware_header_v2_0 *sdma_hdr; uint16_t version_major; - - err = request_firmware(&adev->sdma.instance[instance].fw, fw_name, adev->dev); + char ucode_prefix[30]; + char fw_name[40]; + + amdgpu_ucode_ip_version_decode(adev, SDMA0_HWIP, ucode_prefix, sizeof(ucode_prefix)); + if (instance == 0) + snprintf(fw_name, sizeof(fw_name), "amdgpu/%s.bin", ucode_prefix); + else + snprintf(fw_name, sizeof(fw_name), "amdgpu/%s%d.bin", ucode_prefix, instance); + err = amdgpu_ucode_request(adev, &adev->sdma.instance[instance].fw, fw_name); if (err) goto out; @@ -279,10 +280,8 @@ int amdgpu_sdma_init_microcode(struct amdgpu_device *adev, } out: - if (err) { - DRM_ERROR("SDMA: Failed to init firmware \"%s\"\n", fw_name); + if (err) amdgpu_sdma_destroy_inst_ctx(adev, duplicate); - } return err; } @@ -306,3 +305,38 @@ void amdgpu_sdma_unset_buffer_funcs_helper(struct amdgpu_device *adev) } } } + +int amdgpu_sdma_ras_sw_init(struct amdgpu_device *adev) +{ + int err = 0; + struct amdgpu_sdma_ras *ras = NULL; + + /* adev->sdma.ras is NULL, which means sdma does not + * support ras function, then do nothing here. + */ + if (!adev->sdma.ras) + return 0; + + ras = adev->sdma.ras; + + err = amdgpu_ras_register_ras_block(adev, &ras->ras_block); + if (err) { + dev_err(adev->dev, "Failed to register sdma ras block!\n"); + return err; + } + + strcpy(ras->ras_block.ras_comm.name, "sdma"); + ras->ras_block.ras_comm.block = AMDGPU_RAS_BLOCK__SDMA; + ras->ras_block.ras_comm.type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE; + adev->sdma.ras_if = &ras->ras_block.ras_comm; + + /* If not define special ras_late_init function, use default ras_late_init */ + if (!ras->ras_block.ras_late_init) + ras->ras_block.ras_late_init = amdgpu_sdma_ras_late_init; + + /* If not defined special ras_cb function, use default ras_cb */ + if (!ras->ras_block.ras_cb) + ras->ras_block.ras_cb = amdgpu_sdma_process_ras_data_cb; + + return 0; +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h index 7d99205c2e01..fc8528812598 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h @@ -124,10 +124,11 @@ int amdgpu_sdma_process_ras_data_cb(struct amdgpu_device *adev, int amdgpu_sdma_process_ecc_irq(struct amdgpu_device *adev, struct amdgpu_irq_src *source, struct amdgpu_iv_entry *entry); -int amdgpu_sdma_init_microcode(struct amdgpu_device *adev, - char *fw_name, u32 instance, bool duplicate); +int amdgpu_sdma_init_microcode(struct amdgpu_device *adev, u32 instance, + bool duplicate); void amdgpu_sdma_destroy_inst_ctx(struct amdgpu_device *adev, bool duplicate); void amdgpu_sdma_unset_buffer_funcs_helper(struct amdgpu_device *adev); +int amdgpu_sdma_ras_sw_init(struct amdgpu_device *adev); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_securedisplay.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_securedisplay.c index 2c1d82fc4c34..8ed0e073656f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_securedisplay.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_securedisplay.c @@ -77,11 +77,11 @@ void psp_securedisplay_parse_resp_status(struct psp_context *psp, } } -void psp_prep_securedisplay_cmd_buf(struct psp_context *psp, struct securedisplay_cmd **cmd, +void psp_prep_securedisplay_cmd_buf(struct psp_context *psp, struct ta_securedisplay_cmd **cmd, enum ta_securedisplay_command command_id) { - *cmd = (struct securedisplay_cmd *)psp->securedisplay_context.context.mem_context.shared_buf; - memset(*cmd, 0, sizeof(struct securedisplay_cmd)); + *cmd = (struct ta_securedisplay_cmd *)psp->securedisplay_context.context.mem_context.shared_buf; + memset(*cmd, 0, sizeof(struct ta_securedisplay_cmd)); (*cmd)->status = TA_SECUREDISPLAY_STATUS__GENERIC_FAILURE; (*cmd)->cmd_id = command_id; } @@ -93,7 +93,7 @@ static ssize_t amdgpu_securedisplay_debugfs_write(struct file *f, const char __u { struct amdgpu_device *adev = (struct amdgpu_device *)file_inode(f)->i_private; struct psp_context *psp = &adev->psp; - struct securedisplay_cmd *securedisplay_cmd; + struct ta_securedisplay_cmd *securedisplay_cmd; struct drm_device *dev = adev_to_drm(adev); uint32_t phy_id; uint32_t op; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_securedisplay.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_securedisplay.h index fe98574748f4..456ad68ed4b2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_securedisplay.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_securedisplay.h @@ -30,7 +30,7 @@ void amdgpu_securedisplay_debugfs_init(struct amdgpu_device *adev); void psp_securedisplay_parse_resp_status(struct psp_context *psp, enum ta_securedisplay_status status); -void psp_prep_securedisplay_cmd_buf(struct psp_context *psp, struct securedisplay_cmd **cmd, +void psp_prep_securedisplay_cmd_buf(struct psp_context *psp, struct ta_securedisplay_cmd **cmd, enum ta_securedisplay_command command_id); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h index 677ad2016976..98d91ebf5c26 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h @@ -153,10 +153,10 @@ TRACE_EVENT(amdgpu_cs, TP_fast_assign( __entry->bo_list = p->bo_list; - __entry->ring = to_amdgpu_ring(job->base.sched)->idx; + __entry->ring = to_amdgpu_ring(job->base.entity->rq->sched)->idx; __entry->dw = ib->length_dw; __entry->fences = amdgpu_fence_count_emitted( - to_amdgpu_ring(job->base.sched)); + to_amdgpu_ring(job->base.entity->rq->sched)); ), TP_printk("bo_list=%p, ring=%u, dw=%u, fences=%u", __entry->bo_list, __entry->ring, __entry->dw, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 55e0284b2bdd..c5ef7f7bdc15 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -44,10 +44,10 @@ #include <linux/module.h> #include <drm/drm_drv.h> -#include <drm/ttm/ttm_bo_api.h> -#include <drm/ttm/ttm_bo_driver.h> +#include <drm/ttm/ttm_bo.h> #include <drm/ttm/ttm_placement.h> #include <drm/ttm/ttm_range_manager.h> +#include <drm/ttm/ttm_tt.h> #include <drm/amdgpu_drm.h> #include <drm/drm_drv.h> @@ -1679,10 +1679,10 @@ static int amdgpu_ttm_reserve_tmr(struct amdgpu_device *adev) /* reserve vram for mem train according to TMR location */ amdgpu_ttm_training_data_block_init(adev); ret = amdgpu_bo_create_kernel_at(adev, - ctx->c2p_train_data_offset, - ctx->train_data_size, - &ctx->c2p_bo, - NULL); + ctx->c2p_train_data_offset, + ctx->train_data_size, + &ctx->c2p_bo, + NULL); if (ret) { DRM_ERROR("alloc c2p_bo failed(%d)!\n", ret); amdgpu_ttm_training_reserve_vram_fini(adev); @@ -1692,10 +1692,10 @@ static int amdgpu_ttm_reserve_tmr(struct amdgpu_device *adev) } ret = amdgpu_bo_create_kernel_at(adev, - adev->gmc.real_vram_size - adev->mman.discovery_tmr_size, - adev->mman.discovery_tmr_size, - &adev->mman.discovery_memory, - NULL); + adev->gmc.real_vram_size - adev->mman.discovery_tmr_size, + adev->mman.discovery_tmr_size, + &adev->mman.discovery_memory, + NULL); if (ret) { DRM_ERROR("alloc tmr failed(%d)!\n", ret); amdgpu_bo_free_kernel(&adev->mman.discovery_memory, NULL, NULL); @@ -1718,7 +1718,6 @@ int amdgpu_ttm_init(struct amdgpu_device *adev) { uint64_t gtt_size; int r; - u64 vis_vram_limit; mutex_init(&adev->mman.gtt_window_lock); @@ -1741,12 +1740,6 @@ int amdgpu_ttm_init(struct amdgpu_device *adev) return r; } - /* Reduce size of CPU-visible VRAM if requested */ - vis_vram_limit = (u64)amdgpu_vis_vram_limit * 1024 * 1024; - if (amdgpu_vis_vram_limit > 0 && - vis_vram_limit <= adev->gmc.visible_vram_size) - adev->gmc.visible_vram_size = vis_vram_limit; - /* Change the size here instead of the init above so only lpfn is affected */ amdgpu_ttm_set_buffer_funcs_status(adev, false); #ifdef CONFIG_64BIT diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c index 5cb62e6249c2..380b89114341 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c @@ -504,7 +504,7 @@ void amdgpu_ucode_print_gpu_info_hdr(const struct common_firmware_header *hdr) } } -int amdgpu_ucode_validate(const struct firmware *fw) +static int amdgpu_ucode_validate(const struct firmware *fw) { const struct common_firmware_header *hdr = (const struct common_firmware_header *)fw->data; @@ -1059,12 +1059,229 @@ int amdgpu_ucode_init_bo(struct amdgpu_device *adev) return 0; } +static const char *amdgpu_ucode_legacy_naming(struct amdgpu_device *adev, int block_type) +{ + if (block_type == MP0_HWIP) { + switch (adev->ip_versions[MP0_HWIP][0]) { + case IP_VERSION(9, 0, 0): + switch (adev->asic_type) { + case CHIP_VEGA10: + return "vega10"; + case CHIP_VEGA12: + return "vega12"; + default: + return NULL; + } + case IP_VERSION(10, 0, 0): + case IP_VERSION(10, 0, 1): + if (adev->asic_type == CHIP_RAVEN) { + if (adev->apu_flags & AMD_APU_IS_RAVEN2) + return "raven2"; + else if (adev->apu_flags & AMD_APU_IS_PICASSO) + return "picasso"; + return "raven"; + } + break; + case IP_VERSION(11, 0, 0): + return "navi10"; + case IP_VERSION(11, 0, 2): + return "vega20"; + case IP_VERSION(11, 0, 3): + return "renoir"; + case IP_VERSION(11, 0, 4): + return "arcturus"; + case IP_VERSION(11, 0, 5): + return "navi14"; + case IP_VERSION(11, 0, 7): + return "sienna_cichlid"; + case IP_VERSION(11, 0, 9): + return "navi12"; + case IP_VERSION(11, 0, 11): + return "navy_flounder"; + case IP_VERSION(11, 0, 12): + return "dimgrey_cavefish"; + case IP_VERSION(11, 0, 13): + return "beige_goby"; + case IP_VERSION(11, 5, 0): + return "vangogh"; + case IP_VERSION(12, 0, 1): + return "green_sardine"; + case IP_VERSION(13, 0, 2): + return "aldebaran"; + case IP_VERSION(13, 0, 1): + case IP_VERSION(13, 0, 3): + return "yellow_carp"; + } + } else if (block_type == MP1_HWIP) { + switch (adev->ip_versions[MP1_HWIP][0]) { + case IP_VERSION(9, 0, 0): + case IP_VERSION(10, 0, 0): + case IP_VERSION(10, 0, 1): + case IP_VERSION(11, 0, 2): + if (adev->asic_type == CHIP_ARCTURUS) + return "arcturus_smc"; + return NULL; + case IP_VERSION(11, 0, 0): + return "navi10_smc"; + case IP_VERSION(11, 0, 5): + return "navi14_smc"; + case IP_VERSION(11, 0, 9): + return "navi12_smc"; + case IP_VERSION(11, 0, 7): + return "sienna_cichlid_smc"; + case IP_VERSION(11, 0, 11): + return "navy_flounder_smc"; + case IP_VERSION(11, 0, 12): + return "dimgrey_cavefish_smc"; + case IP_VERSION(11, 0, 13): + return "beige_goby_smc"; + case IP_VERSION(13, 0, 2): + return "aldebaran_smc"; + } + } else if (block_type == SDMA0_HWIP) { + switch (adev->ip_versions[SDMA0_HWIP][0]) { + case IP_VERSION(4, 0, 0): + return "vega10_sdma"; + case IP_VERSION(4, 0, 1): + return "vega12_sdma"; + case IP_VERSION(4, 1, 0): + case IP_VERSION(4, 1, 1): + if (adev->apu_flags & AMD_APU_IS_RAVEN2) + return "raven2_sdma"; + else if (adev->apu_flags & AMD_APU_IS_PICASSO) + return "picasso_sdma"; + return "raven_sdma"; + case IP_VERSION(4, 1, 2): + if (adev->apu_flags & AMD_APU_IS_RENOIR) + return "renoir_sdma"; + return "green_sardine_sdma"; + case IP_VERSION(4, 2, 0): + return "vega20_sdma"; + case IP_VERSION(4, 2, 2): + return "arcturus_sdma"; + case IP_VERSION(4, 4, 0): + return "aldebaran_sdma"; + case IP_VERSION(5, 0, 0): + return "navi10_sdma"; + case IP_VERSION(5, 0, 1): + return "cyan_skillfish2_sdma"; + case IP_VERSION(5, 0, 2): + return "navi14_sdma"; + case IP_VERSION(5, 0, 5): + return "navi12_sdma"; + case IP_VERSION(5, 2, 0): + return "sienna_cichlid_sdma"; + case IP_VERSION(5, 2, 2): + return "navy_flounder_sdma"; + case IP_VERSION(5, 2, 4): + return "dimgrey_cavefish_sdma"; + case IP_VERSION(5, 2, 5): + return "beige_goby_sdma"; + case IP_VERSION(5, 2, 3): + return "yellow_carp_sdma"; + case IP_VERSION(5, 2, 1): + return "vangogh_sdma"; + } + } else if (block_type == UVD_HWIP) { + switch (adev->ip_versions[UVD_HWIP][0]) { + case IP_VERSION(1, 0, 0): + case IP_VERSION(1, 0, 1): + if (adev->apu_flags & AMD_APU_IS_RAVEN2) + return "raven2_vcn"; + else if (adev->apu_flags & AMD_APU_IS_PICASSO) + return "picasso_vcn"; + return "raven_vcn"; + case IP_VERSION(2, 5, 0): + return "arcturus_vcn"; + case IP_VERSION(2, 2, 0): + if (adev->apu_flags & AMD_APU_IS_RENOIR) + return "renoir_vcn"; + return "green_sardine_vcn"; + case IP_VERSION(2, 6, 0): + return "aldebaran_vcn"; + case IP_VERSION(2, 0, 0): + return "navi10_vcn"; + case IP_VERSION(2, 0, 2): + if (adev->asic_type == CHIP_NAVI12) + return "navi12_vcn"; + return "navi14_vcn"; + case IP_VERSION(3, 0, 0): + case IP_VERSION(3, 0, 64): + case IP_VERSION(3, 0, 192): + if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(10, 3, 0)) + return "sienna_cichlid_vcn"; + return "navy_flounder_vcn"; + case IP_VERSION(3, 0, 2): + return "vangogh_vcn"; + case IP_VERSION(3, 0, 16): + return "dimgrey_cavefish_vcn"; + case IP_VERSION(3, 0, 33): + return "beige_goby_vcn"; + case IP_VERSION(3, 1, 1): + return "yellow_carp_vcn"; + } + } else if (block_type == GC_HWIP) { + switch (adev->ip_versions[GC_HWIP][0]) { + case IP_VERSION(9, 0, 1): + return "vega10"; + case IP_VERSION(9, 2, 1): + return "vega12"; + case IP_VERSION(9, 4, 0): + return "vega20"; + case IP_VERSION(9, 2, 2): + case IP_VERSION(9, 1, 0): + if (adev->apu_flags & AMD_APU_IS_RAVEN2) + return "raven2"; + else if (adev->apu_flags & AMD_APU_IS_PICASSO) + return "picasso"; + return "raven"; + case IP_VERSION(9, 4, 1): + return "arcturus"; + case IP_VERSION(9, 3, 0): + if (adev->apu_flags & AMD_APU_IS_RENOIR) + return "renoir"; + return "green_sardine"; + case IP_VERSION(9, 4, 2): + return "aldebaran"; + case IP_VERSION(10, 1, 10): + return "navi10"; + case IP_VERSION(10, 1, 1): + return "navi14"; + case IP_VERSION(10, 1, 2): + return "navi12"; + case IP_VERSION(10, 3, 0): + return "sienna_cichlid"; + case IP_VERSION(10, 3, 2): + return "navy_flounder"; + case IP_VERSION(10, 3, 1): + return "vangogh"; + case IP_VERSION(10, 3, 4): + return "dimgrey_cavefish"; + case IP_VERSION(10, 3, 5): + return "beige_goby"; + case IP_VERSION(10, 3, 3): + return "yellow_carp"; + case IP_VERSION(10, 1, 3): + case IP_VERSION(10, 1, 4): + return "cyan_skillfish2"; + } + } + return NULL; +} + void amdgpu_ucode_ip_version_decode(struct amdgpu_device *adev, int block_type, char *ucode_prefix, int len) { int maj, min, rev; char *ip_name; + const char *legacy; uint32_t version = adev->ip_versions[block_type][0]; + legacy = amdgpu_ucode_legacy_naming(adev, block_type); + if (legacy) { + snprintf(ucode_prefix, len, "%s", legacy); + return; + } + switch (block_type) { case GC_HWIP: ip_name = "gc"; @@ -1091,3 +1308,39 @@ void amdgpu_ucode_ip_version_decode(struct amdgpu_device *adev, int block_type, snprintf(ucode_prefix, len, "%s_%d_%d_%d", ip_name, maj, min, rev); } + +/* + * amdgpu_ucode_request - Fetch and validate amdgpu microcode + * + * @adev: amdgpu device + * @fw: pointer to load firmware to + * @fw_name: firmware to load + * + * This is a helper that will use request_firmware and amdgpu_ucode_validate + * to load and run basic validation on firmware. If the load fails, remap + * the error code to -ENODEV, so that early_init functions will fail to load. + */ +int amdgpu_ucode_request(struct amdgpu_device *adev, const struct firmware **fw, + const char *fw_name) +{ + int err = request_firmware(fw, fw_name, adev->dev); + + if (err) + return -ENODEV; + err = amdgpu_ucode_validate(*fw); + if (err) + dev_dbg(adev->dev, "\"%s\" failed to validate\n", fw_name); + + return err; +} + +/* + * amdgpu_ucode_release - Release firmware microcode + * + * @fw: pointer to firmware to release + */ +void amdgpu_ucode_release(const struct firmware **fw) +{ + release_firmware(*fw); + *fw = NULL; +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h index 552e06929229..b03321e7d2d8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h @@ -538,12 +538,15 @@ struct amdgpu_firmware { void amdgpu_ucode_print_mc_hdr(const struct common_firmware_header *hdr); void amdgpu_ucode_print_smc_hdr(const struct common_firmware_header *hdr); +void amdgpu_ucode_print_imu_hdr(const struct common_firmware_header *hdr); void amdgpu_ucode_print_gfx_hdr(const struct common_firmware_header *hdr); void amdgpu_ucode_print_rlc_hdr(const struct common_firmware_header *hdr); void amdgpu_ucode_print_sdma_hdr(const struct common_firmware_header *hdr); void amdgpu_ucode_print_psp_hdr(const struct common_firmware_header *hdr); void amdgpu_ucode_print_gpu_info_hdr(const struct common_firmware_header *hdr); -int amdgpu_ucode_validate(const struct firmware *fw); +int amdgpu_ucode_request(struct amdgpu_device *adev, const struct firmware **fw, + const char *fw_name); +void amdgpu_ucode_release(const struct firmware **fw); bool amdgpu_ucode_hdr_version(union amdgpu_firmware_header *hdr, uint16_t hdr_major, uint16_t hdr_minor); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c index f76c19fc0392..1b8574bc4463 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c @@ -68,7 +68,7 @@ int amdgpu_umc_page_retirement_mca(struct amdgpu_device *adev, if (amdgpu_bad_page_threshold != 0) { amdgpu_ras_add_bad_pages(adev, err_data.err_addr, err_data.err_addr_cnt); - amdgpu_ras_save_bad_pages(adev); + amdgpu_ras_save_bad_pages(adev, NULL); } out: @@ -147,7 +147,7 @@ static int amdgpu_umc_do_page_retirement(struct amdgpu_device *adev, err_data->err_addr_cnt) { amdgpu_ras_add_bad_pages(adev, err_data->err_addr, err_data->err_addr_cnt); - amdgpu_ras_save_bad_pages(adev); + amdgpu_ras_save_bad_pages(adev, &(err_data->ue_count)); amdgpu_dpm_send_hbm_bad_pages_num(adev, con->eeprom_control.ras_num_recs); @@ -169,25 +169,33 @@ int amdgpu_umc_poison_handler(struct amdgpu_device *adev, bool reset) { int ret = AMDGPU_RAS_SUCCESS; - if (!adev->gmc.xgmi.connected_to_cpu) { - struct ras_err_data err_data = {0, 0, 0, NULL}; - struct ras_common_if head = { - .block = AMDGPU_RAS_BLOCK__UMC, - }; - struct ras_manager *obj = amdgpu_ras_find_obj(adev, &head); + if (!amdgpu_sriov_vf(adev)) { + if (!adev->gmc.xgmi.connected_to_cpu) { + struct ras_err_data err_data = {0, 0, 0, NULL}; + struct ras_common_if head = { + .block = AMDGPU_RAS_BLOCK__UMC, + }; + struct ras_manager *obj = amdgpu_ras_find_obj(adev, &head); - ret = amdgpu_umc_do_page_retirement(adev, &err_data, NULL, reset); + ret = amdgpu_umc_do_page_retirement(adev, &err_data, NULL, reset); - if (ret == AMDGPU_RAS_SUCCESS && obj) { - obj->err_data.ue_count += err_data.ue_count; - obj->err_data.ce_count += err_data.ce_count; + if (ret == AMDGPU_RAS_SUCCESS && obj) { + obj->err_data.ue_count += err_data.ue_count; + obj->err_data.ce_count += err_data.ce_count; + } + } else if (reset) { + /* MCA poison handler is only responsible for GPU reset, + * let MCA notifier do page retirement. + */ + kgd2kfd_set_sram_ecc_flag(adev->kfd.dev); + amdgpu_ras_reset_gpu(adev); } - } else if (reset) { - /* MCA poison handler is only responsible for GPU reset, - * let MCA notifier do page retirement. - */ - kgd2kfd_set_sram_ecc_flag(adev->kfd.dev); - amdgpu_ras_reset_gpu(adev); + } else { + if (adev->virt.ops && adev->virt.ops->ras_poison_handler) + adev->virt.ops->ras_poison_handler(adev); + else + dev_warn(adev->dev, + "No ras_poison_handler interface in SRIOV!\n"); } return ret; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h index a6951160f13a..36e19336f3b3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h @@ -42,7 +42,7 @@ #define LOOP_UMC_INST_AND_CH(umc_inst, ch_inst) LOOP_UMC_INST((umc_inst)) LOOP_UMC_CH_INST((ch_inst)) #define LOOP_UMC_NODE_INST(node_inst) \ - for ((node_inst) = 0; (node_inst) < adev->umc.node_inst_num; (node_inst)++) + for_each_set_bit((node_inst), &(adev->umc.active_mask), adev->umc.node_inst_num) #define LOOP_UMC_EACH_NODE_INST_AND_CH(node_inst, umc_inst, ch_inst) \ LOOP_UMC_NODE_INST((node_inst)) LOOP_UMC_INST_AND_CH((umc_inst), (ch_inst)) @@ -69,17 +69,22 @@ struct amdgpu_umc { /* number of umc instance with memory map register access */ uint32_t umc_inst_num; - /*number of umc node instance with memory map register access*/ + /* Total number of umc node instance including harvest one */ uint32_t node_inst_num; /* UMC regiser per channel offset */ uint32_t channel_offs; + /* how many pages are retired in one UE */ + uint32_t retire_unit; /* channel index table of interleaved memory */ const uint32_t *channel_idx_tbl; struct ras_common_if *ras_if; const struct amdgpu_umc_funcs *funcs; struct amdgpu_umc_ras *ras; + + /* active mask for umc node instance */ + unsigned long active_mask; }; int amdgpu_umc_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *ras_block); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index e00bb654e24b..632a6ded5735 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -260,19 +260,11 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev) return -EINVAL; } - r = request_firmware(&adev->uvd.fw, fw_name, adev->dev); - if (r) { - dev_err(adev->dev, "amdgpu_uvd: Can't load firmware \"%s\"\n", - fw_name); - return r; - } - - r = amdgpu_ucode_validate(adev->uvd.fw); + r = amdgpu_ucode_request(adev, &adev->uvd.fw, fw_name); if (r) { dev_err(adev->dev, "amdgpu_uvd: Can't validate firmware \"%s\"\n", fw_name); - release_firmware(adev->uvd.fw); - adev->uvd.fw = NULL; + amdgpu_ucode_release(&adev->uvd.fw); return r; } @@ -331,8 +323,11 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev) if (adev->uvd.harvest_config & (1 << j)) continue; r = amdgpu_bo_create_kernel(adev, bo_size, PAGE_SIZE, - AMDGPU_GEM_DOMAIN_VRAM, &adev->uvd.inst[j].vcpu_bo, - &adev->uvd.inst[j].gpu_addr, &adev->uvd.inst[j].cpu_addr); + AMDGPU_GEM_DOMAIN_VRAM | + AMDGPU_GEM_DOMAIN_GTT, + &adev->uvd.inst[j].vcpu_bo, + &adev->uvd.inst[j].gpu_addr, + &adev->uvd.inst[j].cpu_addr); if (r) { dev_err(adev->dev, "(%d) failed to allocate UVD bo\n", r); return r; @@ -394,7 +389,7 @@ int amdgpu_uvd_sw_fini(struct amdgpu_device *adev) amdgpu_ring_fini(&adev->uvd.inst[j].ring_enc[i]); } amdgpu_bo_free_kernel(&adev->uvd.ib_bo, NULL, &addr); - release_firmware(adev->uvd.fw); + amdgpu_ucode_release(&adev->uvd.fw); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c index b239e874f2d5..2fb61410b1c0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c @@ -158,19 +158,11 @@ int amdgpu_vce_sw_init(struct amdgpu_device *adev, unsigned long size) return -EINVAL; } - r = request_firmware(&adev->vce.fw, fw_name, adev->dev); - if (r) { - dev_err(adev->dev, "amdgpu_vce: Can't load firmware \"%s\"\n", - fw_name); - return r; - } - - r = amdgpu_ucode_validate(adev->vce.fw); + r = amdgpu_ucode_request(adev, &adev->vce.fw, fw_name); if (r) { dev_err(adev->dev, "amdgpu_vce: Can't validate firmware \"%s\"\n", fw_name); - release_firmware(adev->vce.fw); - adev->vce.fw = NULL; + amdgpu_ucode_release(&adev->vce.fw); return r; } @@ -186,7 +178,9 @@ int amdgpu_vce_sw_init(struct amdgpu_device *adev, unsigned long size) (binary_id << 8)); r = amdgpu_bo_create_kernel(adev, size, PAGE_SIZE, - AMDGPU_GEM_DOMAIN_VRAM, &adev->vce.vcpu_bo, + AMDGPU_GEM_DOMAIN_VRAM | + AMDGPU_GEM_DOMAIN_GTT, + &adev->vce.vcpu_bo, &adev->vce.gpu_addr, &adev->vce.cpu_addr); if (r) { dev_err(adev->dev, "(%d) failed to allocate VCE bo\n", r); @@ -226,7 +220,7 @@ int amdgpu_vce_sw_fini(struct amdgpu_device *adev) for (i = 0; i < adev->vce.num_rings; i++) amdgpu_ring_fini(&adev->vce.ring[i]); - release_firmware(adev->vce.fw); + amdgpu_ucode_release(&adev->vce.fw); mutex_destroy(&adev->vce.idle_mutex); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index b1622ac9949f..e7974de8b035 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -26,6 +26,7 @@ #include <linux/firmware.h> #include <linux/module.h> +#include <linux/dmi.h> #include <linux/pci.h> #include <linux/debugfs.h> #include <drm/drm_drv.h> @@ -36,26 +37,26 @@ #include "soc15d.h" /* Firmware Names */ -#define FIRMWARE_RAVEN "amdgpu/raven_vcn.bin" -#define FIRMWARE_PICASSO "amdgpu/picasso_vcn.bin" -#define FIRMWARE_RAVEN2 "amdgpu/raven2_vcn.bin" -#define FIRMWARE_ARCTURUS "amdgpu/arcturus_vcn.bin" -#define FIRMWARE_RENOIR "amdgpu/renoir_vcn.bin" -#define FIRMWARE_GREEN_SARDINE "amdgpu/green_sardine_vcn.bin" -#define FIRMWARE_NAVI10 "amdgpu/navi10_vcn.bin" -#define FIRMWARE_NAVI14 "amdgpu/navi14_vcn.bin" -#define FIRMWARE_NAVI12 "amdgpu/navi12_vcn.bin" -#define FIRMWARE_SIENNA_CICHLID "amdgpu/sienna_cichlid_vcn.bin" -#define FIRMWARE_NAVY_FLOUNDER "amdgpu/navy_flounder_vcn.bin" -#define FIRMWARE_VANGOGH "amdgpu/vangogh_vcn.bin" +#define FIRMWARE_RAVEN "amdgpu/raven_vcn.bin" +#define FIRMWARE_PICASSO "amdgpu/picasso_vcn.bin" +#define FIRMWARE_RAVEN2 "amdgpu/raven2_vcn.bin" +#define FIRMWARE_ARCTURUS "amdgpu/arcturus_vcn.bin" +#define FIRMWARE_RENOIR "amdgpu/renoir_vcn.bin" +#define FIRMWARE_GREEN_SARDINE "amdgpu/green_sardine_vcn.bin" +#define FIRMWARE_NAVI10 "amdgpu/navi10_vcn.bin" +#define FIRMWARE_NAVI14 "amdgpu/navi14_vcn.bin" +#define FIRMWARE_NAVI12 "amdgpu/navi12_vcn.bin" +#define FIRMWARE_SIENNA_CICHLID "amdgpu/sienna_cichlid_vcn.bin" +#define FIRMWARE_NAVY_FLOUNDER "amdgpu/navy_flounder_vcn.bin" +#define FIRMWARE_VANGOGH "amdgpu/vangogh_vcn.bin" #define FIRMWARE_DIMGREY_CAVEFISH "amdgpu/dimgrey_cavefish_vcn.bin" -#define FIRMWARE_ALDEBARAN "amdgpu/aldebaran_vcn.bin" -#define FIRMWARE_BEIGE_GOBY "amdgpu/beige_goby_vcn.bin" -#define FIRMWARE_YELLOW_CARP "amdgpu/yellow_carp_vcn.bin" -#define FIRMWARE_VCN_3_1_2 "amdgpu/vcn_3_1_2.bin" -#define FIRMWARE_VCN4_0_0 "amdgpu/vcn_4_0_0.bin" -#define FIRMWARE_VCN4_0_2 "amdgpu/vcn_4_0_2.bin" -#define FIRMWARE_VCN4_0_4 "amdgpu/vcn_4_0_4.bin" +#define FIRMWARE_ALDEBARAN "amdgpu/aldebaran_vcn.bin" +#define FIRMWARE_BEIGE_GOBY "amdgpu/beige_goby_vcn.bin" +#define FIRMWARE_YELLOW_CARP "amdgpu/yellow_carp_vcn.bin" +#define FIRMWARE_VCN_3_1_2 "amdgpu/vcn_3_1_2.bin" +#define FIRMWARE_VCN4_0_0 "amdgpu/vcn_4_0_0.bin" +#define FIRMWARE_VCN4_0_2 "amdgpu/vcn_4_0_2.bin" +#define FIRMWARE_VCN4_0_4 "amdgpu/vcn_4_0_4.bin" MODULE_FIRMWARE(FIRMWARE_RAVEN); MODULE_FIRMWARE(FIRMWARE_PICASSO); @@ -80,10 +81,24 @@ MODULE_FIRMWARE(FIRMWARE_VCN4_0_4); static void amdgpu_vcn_idle_work_handler(struct work_struct *work); +int amdgpu_vcn_early_init(struct amdgpu_device *adev) +{ + char ucode_prefix[30]; + char fw_name[40]; + int r; + + amdgpu_ucode_ip_version_decode(adev, UVD_HWIP, ucode_prefix, sizeof(ucode_prefix)); + snprintf(fw_name, sizeof(fw_name), "amdgpu/%s.bin", ucode_prefix); + r = amdgpu_ucode_request(adev, &adev->vcn.fw, fw_name); + if (r) + amdgpu_ucode_release(&adev->vcn.fw); + + return r; +} + int amdgpu_vcn_sw_init(struct amdgpu_device *adev) { unsigned long bo_size; - const char *fw_name; const struct common_firmware_header *hdr; unsigned char fw_check; unsigned int fw_shared_size, log_offset; @@ -96,130 +111,26 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev) for (i = 0; i < adev->vcn.num_vcn_inst; i++) atomic_set(&adev->vcn.inst[i].dpg_enc_submission_cnt, 0); - switch (adev->ip_versions[UVD_HWIP][0]) { - case IP_VERSION(1, 0, 0): - case IP_VERSION(1, 0, 1): - if (adev->apu_flags & AMD_APU_IS_RAVEN2) - fw_name = FIRMWARE_RAVEN2; - else if (adev->apu_flags & AMD_APU_IS_PICASSO) - fw_name = FIRMWARE_PICASSO; - else - fw_name = FIRMWARE_RAVEN; - break; - case IP_VERSION(2, 5, 0): - fw_name = FIRMWARE_ARCTURUS; - if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) && - (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)) - adev->vcn.indirect_sram = true; - break; - case IP_VERSION(2, 2, 0): - if (adev->apu_flags & AMD_APU_IS_RENOIR) - fw_name = FIRMWARE_RENOIR; - else - fw_name = FIRMWARE_GREEN_SARDINE; - - if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) && - (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)) - adev->vcn.indirect_sram = true; - break; - case IP_VERSION(2, 6, 0): - fw_name = FIRMWARE_ALDEBARAN; - if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) && - (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)) - adev->vcn.indirect_sram = true; - break; - case IP_VERSION(2, 0, 0): - fw_name = FIRMWARE_NAVI10; - if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) && - (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)) - adev->vcn.indirect_sram = true; - break; - case IP_VERSION(2, 0, 2): - if (adev->asic_type == CHIP_NAVI12) - fw_name = FIRMWARE_NAVI12; - else - fw_name = FIRMWARE_NAVI14; - if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) && - (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)) - adev->vcn.indirect_sram = true; - break; - case IP_VERSION(3, 0, 0): - case IP_VERSION(3, 0, 64): - case IP_VERSION(3, 0, 192): - if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(10, 3, 0)) - fw_name = FIRMWARE_SIENNA_CICHLID; - else - fw_name = FIRMWARE_NAVY_FLOUNDER; - if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) && - (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)) - adev->vcn.indirect_sram = true; - break; - case IP_VERSION(3, 0, 2): - fw_name = FIRMWARE_VANGOGH; - if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) && - (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)) - adev->vcn.indirect_sram = true; - break; - case IP_VERSION(3, 0, 16): - fw_name = FIRMWARE_DIMGREY_CAVEFISH; - if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) && - (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)) - adev->vcn.indirect_sram = true; - break; - case IP_VERSION(3, 0, 33): - fw_name = FIRMWARE_BEIGE_GOBY; - if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) && - (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)) - adev->vcn.indirect_sram = true; - break; - case IP_VERSION(3, 1, 1): - fw_name = FIRMWARE_YELLOW_CARP; - if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) && - (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)) - adev->vcn.indirect_sram = true; - break; - case IP_VERSION(3, 1, 2): - fw_name = FIRMWARE_VCN_3_1_2; - if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) && - (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)) - adev->vcn.indirect_sram = true; - break; - case IP_VERSION(4, 0, 0): - fw_name = FIRMWARE_VCN4_0_0; - if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) && - (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)) - adev->vcn.indirect_sram = true; - break; - case IP_VERSION(4, 0, 2): - fw_name = FIRMWARE_VCN4_0_2; - if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) && - (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)) - adev->vcn.indirect_sram = true; - break; - case IP_VERSION(4, 0, 4): - fw_name = FIRMWARE_VCN4_0_4; - if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) && - (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)) - adev->vcn.indirect_sram = true; - break; - default: - return -EINVAL; - } - - r = request_firmware(&adev->vcn.fw, fw_name, adev->dev); - if (r) { - dev_err(adev->dev, "amdgpu_vcn: Can't load firmware \"%s\"\n", - fw_name); - return r; - } + if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) && + (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)) + adev->vcn.indirect_sram = true; - r = amdgpu_ucode_validate(adev->vcn.fw); - if (r) { - dev_err(adev->dev, "amdgpu_vcn: Can't validate firmware \"%s\"\n", - fw_name); - release_firmware(adev->vcn.fw); - adev->vcn.fw = NULL; - return r; + /* + * Some Steam Deck's BIOS versions are incompatible with the + * indirect SRAM mode, leading to amdgpu being unable to get + * properly probed (and even potentially crashing the kernel). + * Hence, check for these versions here - notice this is + * restricted to Vangogh (Deck's APU). + */ + if (adev->ip_versions[UVD_HWIP][0] == IP_VERSION(3, 0, 2)) { + const char *bios_ver = dmi_get_system_info(DMI_BIOS_VERSION); + + if (bios_ver && (!strncmp("F7A0113", bios_ver, 7) || + !strncmp("F7A0114", bios_ver, 7))) { + adev->vcn.indirect_sram = false; + dev_info(adev->dev, + "Steam Deck quirk: indirect SRAM disabled on BIOS %s\n", bios_ver); + } } hdr = (const struct common_firmware_header *)adev->vcn.fw->data; @@ -274,8 +185,11 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev) continue; r = amdgpu_bo_create_kernel(adev, bo_size, PAGE_SIZE, - AMDGPU_GEM_DOMAIN_VRAM, &adev->vcn.inst[i].vcpu_bo, - &adev->vcn.inst[i].gpu_addr, &adev->vcn.inst[i].cpu_addr); + AMDGPU_GEM_DOMAIN_VRAM | + AMDGPU_GEM_DOMAIN_GTT, + &adev->vcn.inst[i].vcpu_bo, + &adev->vcn.inst[i].gpu_addr, + &adev->vcn.inst[i].cpu_addr); if (r) { dev_err(adev->dev, "(%d) failed to allocate vcn bo\n", r); return r; @@ -296,8 +210,11 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev) if (adev->vcn.indirect_sram) { r = amdgpu_bo_create_kernel(adev, 64 * 2 * 4, PAGE_SIZE, - AMDGPU_GEM_DOMAIN_VRAM, &adev->vcn.inst[i].dpg_sram_bo, - &adev->vcn.inst[i].dpg_sram_gpu_addr, &adev->vcn.inst[i].dpg_sram_cpu_addr); + AMDGPU_GEM_DOMAIN_VRAM | + AMDGPU_GEM_DOMAIN_GTT, + &adev->vcn.inst[i].dpg_sram_bo, + &adev->vcn.inst[i].dpg_sram_gpu_addr, + &adev->vcn.inst[i].dpg_sram_cpu_addr); if (r) { dev_err(adev->dev, "VCN %d (%d) failed to allocate DPG bo\n", i, r); return r; @@ -333,7 +250,7 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev) amdgpu_ring_fini(&adev->vcn.inst[j].ring_enc[i]); } - release_firmware(adev->vcn.fw); + amdgpu_ucode_release(&adev->vcn.fw); mutex_destroy(&adev->vcn.vcn1_jpeg1_workaround); mutex_destroy(&adev->vcn.vcn_pg_lock); @@ -1250,8 +1167,16 @@ int amdgpu_vcn_process_poison_irq(struct amdgpu_device *adev, if (!ras_if) return 0; - ih_data.head = *ras_if; - amdgpu_ras_interrupt_dispatch(adev, &ih_data); + if (!amdgpu_sriov_vf(adev)) { + ih_data.head = *ras_if; + amdgpu_ras_interrupt_dispatch(adev, &ih_data); + } else { + if (adev->virt.ops && adev->virt.ops->ras_poison_handler) + adev->virt.ops->ras_poison_handler(adev); + else + dev_warn(adev->dev, + "No ras_poison_handler interface in SRIOV for VCN!\n"); + } return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h index dbb8d68a30c6..d3e2af902907 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h @@ -369,6 +369,7 @@ enum vcn_ring_type { VCN_UNIFIED_RING, }; +int amdgpu_vcn_early_init(struct amdgpu_device *adev); int amdgpu_vcn_sw_init(struct amdgpu_device *adev); int amdgpu_vcn_sw_fini(struct amdgpu_device *adev); int amdgpu_vcn_suspend(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c index 2994b9db196f..f2e2cbaa7fde 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c @@ -232,7 +232,8 @@ int amdgpu_virt_alloc_mm_table(struct amdgpu_device *adev) return 0; r = amdgpu_bo_create_kernel(adev, PAGE_SIZE, PAGE_SIZE, - AMDGPU_GEM_DOMAIN_VRAM, + AMDGPU_GEM_DOMAIN_VRAM | + AMDGPU_GEM_DOMAIN_GTT, &adev->virt.mm_table.bo, &adev->virt.mm_table.gpu_addr, (void *)&adev->virt.mm_table.cpu_addr); @@ -982,11 +983,13 @@ static u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v if (offset == reg_access_ctrl->grbm_cntl) { /* if the target reg offset is grbm_cntl, write to scratch_reg2 */ writel(v, scratch_reg2); - writel(v, ((void __iomem *)adev->rmmio) + (offset * 4)); + if (flag == AMDGPU_RLCG_GC_WRITE_LEGACY) + writel(v, ((void __iomem *)adev->rmmio) + (offset * 4)); } else if (offset == reg_access_ctrl->grbm_idx) { /* if the target reg offset is grbm_idx, write to scratch_reg3 */ writel(v, scratch_reg3); - writel(v, ((void __iomem *)adev->rmmio) + (offset * 4)); + if (flag == AMDGPU_RLCG_GC_WRITE_LEGACY) + writel(v, ((void __iomem *)adev->rmmio) + (offset * 4)); } else { /* * SCRATCH_REG0 = read/write value diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h index 2b9d806e23af..4f7bab52282a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h @@ -88,6 +88,7 @@ struct amdgpu_virt_ops { int (*wait_reset)(struct amdgpu_device *adev); void (*trans_msg)(struct amdgpu_device *adev, enum idh_request req, u32 data1, u32 data2, u32 data3); + void (*ras_poison_handler)(struct amdgpu_device *adev); }; /* @@ -123,6 +124,8 @@ enum AMDGIM_FEATURE_FLAG { AMDGIM_FEATURE_PP_ONE_VF = (1 << 4), /* Indirect Reg Access enabled */ AMDGIM_FEATURE_INDIRECT_REG_ACCESS = (1 << 5), + /* AV1 Support MODE*/ + AMDGIM_FEATURE_AV1_SUPPORT = (1 << 6), }; enum AMDGIM_REG_ACCESS_FLAG { @@ -321,6 +324,8 @@ static inline bool is_virtual_machine(void) ((!amdgpu_in_reset(adev)) && adev->virt.tdr_debug) #define amdgpu_sriov_is_normal(adev) \ ((!amdgpu_in_reset(adev)) && (!adev->virt.tdr_debug)) +#define amdgpu_sriov_is_av1_support(adev) \ + ((adev)->virt.gim_feature & AMDGIM_FEATURE_AV1_SUPPORT) bool amdgpu_virt_mmio_blocked(struct amdgpu_device *adev); void amdgpu_virt_init_setting(struct amdgpu_device *adev); void amdgpu_virt_kiq_reg_write_reg_wait(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index dc379dc22c77..b9441ab457ea 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -33,6 +33,7 @@ #include <drm/amdgpu_drm.h> #include <drm/drm_drv.h> +#include <drm/ttm/ttm_tt.h> #include "amdgpu.h" #include "amdgpu_trace.h" #include "amdgpu_amdkfd.h" diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h index 094bb4807303..856a64bc7a89 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h @@ -29,7 +29,7 @@ #include <linux/rbtree.h> #include <drm/gpu_scheduler.h> #include <drm/drm_file.h> -#include <drm/ttm/ttm_bo_driver.h> +#include <drm/ttm/ttm_bo.h> #include <linux/sched/mm.h> #include "amdgpu_sync.h" diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c index b5f3bba851db..01e42bdd8e4e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c @@ -974,7 +974,7 @@ int amdgpu_vm_ptes_update(struct amdgpu_vm_update_params *params, trace_amdgpu_vm_update_ptes(params, frag_start, upd_end, min(nptes, 32u), dst, incr, upd_flags, - vm->task_info.pid, + vm->task_info.tgid, vm->immediate.fence_context); amdgpu_vm_pte_update_flags(params, to_amdgpu_bo_vm(pt), cursor.level, pe_start, dst, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index 9fa1d814508a..43d6a9d6a538 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -453,7 +453,8 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man, /* Limit maximum size to 2GiB due to SG table limitations */ size = min(remaining_size, 2ULL << 30); - if (size >= (u64)pages_per_block << PAGE_SHIFT) + if ((size >= (u64)pages_per_block << PAGE_SHIFT) && + !(size & (((u64)pages_per_block << PAGE_SHIFT) - 1))) min_block_size = (u64)pages_per_block << PAGE_SHIFT; cur_size = size; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c index 4b9e7b050ccd..4340d08f7607 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c @@ -29,13 +29,16 @@ #include "df/df_3_6_offset.h" #include "xgmi/xgmi_4_0_0_smn.h" #include "xgmi/xgmi_4_0_0_sh_mask.h" +#include "xgmi/xgmi_6_1_0_sh_mask.h" #include "wafl/wafl2_4_0_0_smn.h" #include "wafl/wafl2_4_0_0_sh_mask.h" #include "amdgpu_reset.h" #define smnPCS_XGMI3X16_PCS_ERROR_STATUS 0x11a0020c +#define smnPCS_XGMI3X16_PCS_ERROR_NONCORRECTABLE_MASK 0x11a00218 #define smnPCS_GOPX1_PCS_ERROR_STATUS 0x12200210 +#define smnPCS_GOPX1_PCS_ERROR_NONCORRECTABLE_MASK 0x12200218 static DEFINE_MUTEX(xgmi_mutex); @@ -79,11 +82,27 @@ static const int xgmi3x16_pcs_err_status_reg_aldebaran[] = { smnPCS_XGMI3X16_PCS_ERROR_STATUS + 0x700000 }; +static const int xgmi3x16_pcs_err_noncorrectable_mask_reg_aldebaran[] = { + smnPCS_XGMI3X16_PCS_ERROR_NONCORRECTABLE_MASK, + smnPCS_XGMI3X16_PCS_ERROR_NONCORRECTABLE_MASK + 0x100000, + smnPCS_XGMI3X16_PCS_ERROR_NONCORRECTABLE_MASK + 0x200000, + smnPCS_XGMI3X16_PCS_ERROR_NONCORRECTABLE_MASK + 0x300000, + smnPCS_XGMI3X16_PCS_ERROR_NONCORRECTABLE_MASK + 0x400000, + smnPCS_XGMI3X16_PCS_ERROR_NONCORRECTABLE_MASK + 0x500000, + smnPCS_XGMI3X16_PCS_ERROR_NONCORRECTABLE_MASK + 0x600000, + smnPCS_XGMI3X16_PCS_ERROR_NONCORRECTABLE_MASK + 0x700000 +}; + static const int walf_pcs_err_status_reg_aldebaran[] = { smnPCS_GOPX1_PCS_ERROR_STATUS, smnPCS_GOPX1_PCS_ERROR_STATUS + 0x100000 }; +static const int walf_pcs_err_noncorrectable_mask_reg_aldebaran[] = { + smnPCS_GOPX1_PCS_ERROR_NONCORRECTABLE_MASK, + smnPCS_GOPX1_PCS_ERROR_NONCORRECTABLE_MASK + 0x100000 +}; + static const struct amdgpu_pcs_ras_field xgmi_pcs_ras_fields[] = { {"XGMI PCS DataLossErr", SOC15_REG_FIELD(XGMI0_PCS_GOPX16_PCS_ERROR_STATUS, DataLossErr)}, @@ -162,6 +181,67 @@ static const struct amdgpu_pcs_ras_field wafl_pcs_ras_fields[] = { SOC15_REG_FIELD(PCS_GOPX1_0_PCS_GOPX1_PCS_ERROR_STATUS, RecoveryRelockAttemptErr)}, }; +static const struct amdgpu_pcs_ras_field xgmi3x16_pcs_ras_fields[] = { + {"XGMI3X16 PCS DataLossErr", + SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, DataLossErr)}, + {"XGMI3X16 PCS TrainingErr", + SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, TrainingErr)}, + {"XGMI3X16 PCS FlowCtrlAckErr", + SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, FlowCtrlAckErr)}, + {"XGMI3X16 PCS RxFifoUnderflowErr", + SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, RxFifoUnderflowErr)}, + {"XGMI3X16 PCS RxFifoOverflowErr", + SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, RxFifoOverflowErr)}, + {"XGMI3X16 PCS CRCErr", + SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, CRCErr)}, + {"XGMI3X16 PCS BERExceededErr", + SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, BERExceededErr)}, + {"XGMI3X16 PCS TxVcidDataErr", + SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, TxVcidDataErr)}, + {"XGMI3X16 PCS ReplayBufParityErr", + SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, ReplayBufParityErr)}, + {"XGMI3X16 PCS DataParityErr", + SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, DataParityErr)}, + {"XGMI3X16 PCS ReplayFifoOverflowErr", + SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, ReplayFifoOverflowErr)}, + {"XGMI3X16 PCS ReplayFifoUnderflowErr", + SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, ReplayFifoUnderflowErr)}, + {"XGMI3X16 PCS ElasticFifoOverflowErr", + SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, ElasticFifoOverflowErr)}, + {"XGMI3X16 PCS DeskewErr", + SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, DeskewErr)}, + {"XGMI3X16 PCS FlowCtrlCRCErr", + SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, FlowCtrlCRCErr)}, + {"XGMI3X16 PCS DataStartupLimitErr", + SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, DataStartupLimitErr)}, + {"XGMI3X16 PCS FCInitTimeoutErr", + SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, FCInitTimeoutErr)}, + {"XGMI3X16 PCS RecoveryTimeoutErr", + SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, RecoveryTimeoutErr)}, + {"XGMI3X16 PCS ReadySerialTimeoutErr", + SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, ReadySerialTimeoutErr)}, + {"XGMI3X16 PCS ReadySerialAttemptErr", + SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, ReadySerialAttemptErr)}, + {"XGMI3X16 PCS RecoveryAttemptErr", + SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, RecoveryAttemptErr)}, + {"XGMI3X16 PCS RecoveryRelockAttemptErr", + SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, RecoveryRelockAttemptErr)}, + {"XGMI3X16 PCS ReplayAttemptErr", + SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, ReplayAttemptErr)}, + {"XGMI3X16 PCS SyncHdrErr", + SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, SyncHdrErr)}, + {"XGMI3X16 PCS TxReplayTimeoutErr", + SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, TxReplayTimeoutErr)}, + {"XGMI3X16 PCS RxReplayTimeoutErr", + SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, RxReplayTimeoutErr)}, + {"XGMI3X16 PCS LinkSubTxTimeoutErr", + SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, LinkSubTxTimeoutErr)}, + {"XGMI3X16 PCS LinkSubRxTimeoutErr", + SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, LinkSubRxTimeoutErr)}, + {"XGMI3X16 PCS RxCMDPktErr", + SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, RxCMDPktErr)}, +}; + /** * DOC: AMDGPU XGMI Support * @@ -809,39 +889,47 @@ static void amdgpu_xgmi_reset_ras_error_count(struct amdgpu_device *adev) static int amdgpu_xgmi_query_pcs_error_status(struct amdgpu_device *adev, uint32_t value, + uint32_t mask_value, uint32_t *ue_count, uint32_t *ce_count, - bool is_xgmi_pcs) + bool is_xgmi_pcs, + bool check_mask) { int i; - int ue_cnt; + int ue_cnt = 0; + const struct amdgpu_pcs_ras_field *pcs_ras_fields = NULL; + uint32_t field_array_size = 0; if (is_xgmi_pcs) { - /* query xgmi pcs error status, - * only ue is supported */ - for (i = 0; i < ARRAY_SIZE(xgmi_pcs_ras_fields); i ++) { - ue_cnt = (value & - xgmi_pcs_ras_fields[i].pcs_err_mask) >> - xgmi_pcs_ras_fields[i].pcs_err_shift; - if (ue_cnt) { - dev_info(adev->dev, "%s detected\n", - xgmi_pcs_ras_fields[i].err_name); - *ue_count += ue_cnt; - } + if (adev->ip_versions[XGMI_HWIP][0] == IP_VERSION(6, 1, 0)) { + pcs_ras_fields = &xgmi3x16_pcs_ras_fields[0]; + field_array_size = ARRAY_SIZE(xgmi3x16_pcs_ras_fields); + } else { + pcs_ras_fields = &xgmi_pcs_ras_fields[0]; + field_array_size = ARRAY_SIZE(xgmi_pcs_ras_fields); } } else { - /* query wafl pcs error status, - * only ue is supported */ - for (i = 0; i < ARRAY_SIZE(wafl_pcs_ras_fields); i++) { - ue_cnt = (value & - wafl_pcs_ras_fields[i].pcs_err_mask) >> - wafl_pcs_ras_fields[i].pcs_err_shift; - if (ue_cnt) { - dev_info(adev->dev, "%s detected\n", - wafl_pcs_ras_fields[i].err_name); - *ue_count += ue_cnt; - } + pcs_ras_fields = &wafl_pcs_ras_fields[0]; + field_array_size = ARRAY_SIZE(wafl_pcs_ras_fields); + } + + if (check_mask) + value = value & ~mask_value; + + /* query xgmi/walf pcs error status, + * only ue is supported */ + for (i = 0; value && i < field_array_size; i++) { + ue_cnt = (value & + pcs_ras_fields[i].pcs_err_mask) >> + pcs_ras_fields[i].pcs_err_shift; + if (ue_cnt) { + dev_info(adev->dev, "%s detected\n", + pcs_ras_fields[i].err_name); + *ue_count += ue_cnt; } + + /* reset bit value if the bit is checked */ + value &= ~(pcs_ras_fields[i].pcs_err_mask); } return 0; @@ -852,7 +940,7 @@ static void amdgpu_xgmi_query_ras_error_count(struct amdgpu_device *adev, { struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status; int i; - uint32_t data; + uint32_t data, mask_data = 0; uint32_t ue_cnt = 0, ce_cnt = 0; if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__XGMI_WAFL)) @@ -867,15 +955,15 @@ static void amdgpu_xgmi_query_ras_error_count(struct amdgpu_device *adev, for (i = 0; i < ARRAY_SIZE(xgmi_pcs_err_status_reg_arct); i++) { data = RREG32_PCIE(xgmi_pcs_err_status_reg_arct[i]); if (data) - amdgpu_xgmi_query_pcs_error_status(adev, - data, &ue_cnt, &ce_cnt, true); + amdgpu_xgmi_query_pcs_error_status(adev, data, + mask_data, &ue_cnt, &ce_cnt, true, false); } /* check wafl pcs error */ for (i = 0; i < ARRAY_SIZE(wafl_pcs_err_status_reg_arct); i++) { data = RREG32_PCIE(wafl_pcs_err_status_reg_arct[i]); if (data) - amdgpu_xgmi_query_pcs_error_status(adev, - data, &ue_cnt, &ce_cnt, false); + amdgpu_xgmi_query_pcs_error_status(adev, data, + mask_data, &ue_cnt, &ce_cnt, false, false); } break; case CHIP_VEGA20: @@ -883,31 +971,35 @@ static void amdgpu_xgmi_query_ras_error_count(struct amdgpu_device *adev, for (i = 0; i < ARRAY_SIZE(xgmi_pcs_err_status_reg_vg20); i++) { data = RREG32_PCIE(xgmi_pcs_err_status_reg_vg20[i]); if (data) - amdgpu_xgmi_query_pcs_error_status(adev, - data, &ue_cnt, &ce_cnt, true); + amdgpu_xgmi_query_pcs_error_status(adev, data, + mask_data, &ue_cnt, &ce_cnt, true, false); } /* check wafl pcs error */ for (i = 0; i < ARRAY_SIZE(wafl_pcs_err_status_reg_vg20); i++) { data = RREG32_PCIE(wafl_pcs_err_status_reg_vg20[i]); if (data) - amdgpu_xgmi_query_pcs_error_status(adev, - data, &ue_cnt, &ce_cnt, false); + amdgpu_xgmi_query_pcs_error_status(adev, data, + mask_data, &ue_cnt, &ce_cnt, false, false); } break; case CHIP_ALDEBARAN: /* check xgmi3x16 pcs error */ for (i = 0; i < ARRAY_SIZE(xgmi3x16_pcs_err_status_reg_aldebaran); i++) { data = RREG32_PCIE(xgmi3x16_pcs_err_status_reg_aldebaran[i]); + mask_data = + RREG32_PCIE(xgmi3x16_pcs_err_noncorrectable_mask_reg_aldebaran[i]); if (data) - amdgpu_xgmi_query_pcs_error_status(adev, - data, &ue_cnt, &ce_cnt, true); + amdgpu_xgmi_query_pcs_error_status(adev, data, + mask_data, &ue_cnt, &ce_cnt, true, true); } /* check wafl pcs error */ for (i = 0; i < ARRAY_SIZE(walf_pcs_err_status_reg_aldebaran); i++) { data = RREG32_PCIE(walf_pcs_err_status_reg_aldebaran[i]); + mask_data = + RREG32_PCIE(walf_pcs_err_noncorrectable_mask_reg_aldebaran[i]); if (data) - amdgpu_xgmi_query_pcs_error_status(adev, - data, &ue_cnt, &ce_cnt, false); + amdgpu_xgmi_query_pcs_error_status(adev, data, + mask_data, &ue_cnt, &ce_cnt, false, true); } break; default: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h index 6c97148ca0ed..24d42d24e6a0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h @@ -93,7 +93,8 @@ union amd_sriov_msg_feature_flags { uint32_t mm_bw_management : 1; uint32_t pp_one_vf_mode : 1; uint32_t reg_indirect_acc : 1; - uint32_t reserved : 26; + uint32_t av1_support : 1; + uint32_t reserved : 25; } flags; uint32_t all; }; diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_crtc.c b/drivers/gpu/drm/amd/amdgpu/atombios_crtc.c index afad094f84c2..10098fdd33fc 100644 --- a/drivers/gpu/drm/amd/amdgpu/atombios_crtc.c +++ b/drivers/gpu/drm/amd/amdgpu/atombios_crtc.c @@ -24,7 +24,6 @@ * Alex Deucher */ -#include <drm/drm_crtc_helper.h> #include <drm/amdgpu_drm.h> #include <drm/drm_fixed.h> #include "amdgpu.h" diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c index 18ae9433e463..d95b2dc78063 100644 --- a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c +++ b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c @@ -28,7 +28,6 @@ #include <acpi/video.h> -#include <drm/drm_crtc_helper.h> #include <drm/amdgpu_drm.h> #include "amdgpu.h" #include "amdgpu_connectors.h" diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c index cbca9866645c..67d16236b216 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c @@ -73,10 +73,9 @@ u32 amdgpu_cik_gpu_check_soft_reset(struct amdgpu_device *adev); static void cik_sdma_free_microcode(struct amdgpu_device *adev) { int i; - for (i = 0; i < adev->sdma.num_instances; i++) { - release_firmware(adev->sdma.instance[i].fw); - adev->sdma.instance[i].fw = NULL; - } + + for (i = 0; i < adev->sdma.num_instances; i++) + amdgpu_ucode_release(&adev->sdma.instance[i].fw); } /* @@ -137,18 +136,15 @@ static int cik_sdma_init_microcode(struct amdgpu_device *adev) snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma.bin", chip_name); else snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma1.bin", chip_name); - err = request_firmware(&adev->sdma.instance[i].fw, fw_name, adev->dev); + err = amdgpu_ucode_request(adev, &adev->sdma.instance[i].fw, fw_name); if (err) goto out; - err = amdgpu_ucode_validate(adev->sdma.instance[i].fw); } out: if (err) { pr_err("cik_sdma: Failed to load firmware \"%s\"\n", fw_name); - for (i = 0; i < adev->sdma.num_instances; i++) { - release_firmware(adev->sdma.instance[i].fw); - adev->sdma.instance[i].fw = NULL; - } + for (i = 0; i < adev->sdma.num_instances; i++) + amdgpu_ucode_release(&adev->sdma.instance[i].fw); } return err; } diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c index 248f1a4e915f..9a24ed463abd 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c @@ -21,8 +21,9 @@ * */ -#include <drm/drm_fb_helper.h> #include <drm/drm_fourcc.h> +#include <drm/drm_modeset_helper.h> +#include <drm/drm_modeset_helper_vtables.h> #include <drm/drm_vblank.h> #include "amdgpu.h" @@ -2837,7 +2838,7 @@ static int dce_v10_0_sw_init(void *handle) if (r) return r; - INIT_WORK(&adev->hotplug_work, + INIT_DELAYED_WORK(&adev->hotplug_work, amdgpu_display_hotplug_work_func); drm_kms_helper_poll_init(adev_to_drm(adev)); @@ -2902,7 +2903,7 @@ static int dce_v10_0_hw_fini(void *handle) dce_v10_0_pageflip_interrupt_fini(adev); - flush_work(&adev->hotplug_work); + flush_delayed_work(&adev->hotplug_work); return 0; } @@ -3302,7 +3303,7 @@ static int dce_v10_0_hpd_irq(struct amdgpu_device *adev, if (disp_int & mask) { dce_v10_0_hpd_int_ack(adev, hpd); - schedule_work(&adev->hotplug_work); + schedule_delayed_work(&adev->hotplug_work, 0); DRM_DEBUG("IH: HPD%d\n", hpd + 1); } diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c index cd9c19060d89..c14b70350a51 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c @@ -21,8 +21,9 @@ * */ -#include <drm/drm_fb_helper.h> #include <drm/drm_fourcc.h> +#include <drm/drm_modeset_helper.h> +#include <drm/drm_modeset_helper_vtables.h> #include <drm/drm_vblank.h> #include "amdgpu.h" @@ -2956,7 +2957,7 @@ static int dce_v11_0_sw_init(void *handle) if (r) return r; - INIT_WORK(&adev->hotplug_work, + INIT_DELAYED_WORK(&adev->hotplug_work, amdgpu_display_hotplug_work_func); drm_kms_helper_poll_init(adev_to_drm(adev)); @@ -3032,7 +3033,7 @@ static int dce_v11_0_hw_fini(void *handle) dce_v11_0_pageflip_interrupt_fini(adev); - flush_work(&adev->hotplug_work); + flush_delayed_work(&adev->hotplug_work); return 0; } @@ -3426,7 +3427,7 @@ static int dce_v11_0_hpd_irq(struct amdgpu_device *adev, if (disp_int & mask) { dce_v11_0_hpd_int_ack(adev, hpd); - schedule_work(&adev->hotplug_work); + schedule_delayed_work(&adev->hotplug_work, 0); DRM_DEBUG("IH: HPD%d\n", hpd + 1); } diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c index 76323deecc58..7f85ba5b726f 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c @@ -23,8 +23,9 @@ #include <linux/pci.h> -#include <drm/drm_fb_helper.h> #include <drm/drm_fourcc.h> +#include <drm/drm_modeset_helper.h> +#include <drm/drm_modeset_helper_vtables.h> #include <drm/drm_vblank.h> #include "amdgpu.h" @@ -2715,7 +2716,7 @@ static int dce_v6_0_sw_init(void *handle) return r; /* Pre-DCE11 */ - INIT_WORK(&adev->hotplug_work, + INIT_DELAYED_WORK(&adev->hotplug_work, amdgpu_display_hotplug_work_func); drm_kms_helper_poll_init(adev_to_drm(adev)); @@ -2776,7 +2777,7 @@ static int dce_v6_0_hw_fini(void *handle) dce_v6_0_pageflip_interrupt_fini(adev); - flush_work(&adev->hotplug_work); + flush_delayed_work(&adev->hotplug_work); return 0; } @@ -3103,7 +3104,7 @@ static int dce_v6_0_hpd_irq(struct amdgpu_device *adev, tmp = RREG32(mmDC_HPD1_INT_CONTROL + hpd_offsets[hpd]); tmp |= DC_HPD1_INT_CONTROL__DC_HPD1_INT_ACK_MASK; WREG32(mmDC_HPD1_INT_CONTROL + hpd_offsets[hpd], tmp); - schedule_work(&adev->hotplug_work); + schedule_delayed_work(&adev->hotplug_work, 0); DRM_DEBUG("IH: HPD%d\n", hpd + 1); } diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c index 01cf3ab111cb..d421a268c9ff 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c @@ -21,8 +21,9 @@ * */ -#include <drm/drm_fb_helper.h> #include <drm/drm_fourcc.h> +#include <drm/drm_modeset_helper.h> +#include <drm/drm_modeset_helper_vtables.h> #include <drm/drm_vblank.h> #include "amdgpu.h" @@ -2739,7 +2740,7 @@ static int dce_v8_0_sw_init(void *handle) return r; /* Pre-DCE11 */ - INIT_WORK(&adev->hotplug_work, + INIT_DELAYED_WORK(&adev->hotplug_work, amdgpu_display_hotplug_work_func); drm_kms_helper_poll_init(adev_to_drm(adev)); @@ -2802,7 +2803,7 @@ static int dce_v8_0_hw_fini(void *handle) dce_v8_0_pageflip_interrupt_fini(adev); - flush_work(&adev->hotplug_work); + flush_delayed_work(&adev->hotplug_work); return 0; } @@ -3195,7 +3196,7 @@ static int dce_v8_0_hpd_irq(struct amdgpu_device *adev, tmp = RREG32(mmDC_HPD1_INT_CONTROL + hpd_offsets[hpd]); tmp |= DC_HPD1_INT_CONTROL__DC_HPD1_INT_ACK_MASK; WREG32(mmDC_HPD1_INT_CONTROL + hpd_offsets[hpd], tmp); - schedule_work(&adev->hotplug_work); + schedule_delayed_work(&adev->hotplug_work, 0); DRM_DEBUG("IH: HPD%d\n", hpd + 1); } diff --git a/drivers/gpu/drm/amd/amdgpu/df_v1_7.c b/drivers/gpu/drm/amd/amdgpu/df_v1_7.c index b991609f46c1..5dfab80ffff2 100644 --- a/drivers/gpu/drm/amd/amdgpu/df_v1_7.c +++ b/drivers/gpu/drm/amd/amdgpu/df_v1_7.c @@ -94,7 +94,7 @@ static void df_v1_7_update_medium_grain_clock_gating(struct amdgpu_device *adev, WREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater, tmp); } - /* Exit boradcast mode */ + /* Exit broadcast mode */ adev->df.funcs->enable_broadcast_mode(adev, false); } diff --git a/drivers/gpu/drm/amd/amdgpu/df_v4_3.c b/drivers/gpu/drm/amd/amdgpu/df_v4_3.c new file mode 100644 index 000000000000..e8b9e19ede2e --- /dev/null +++ b/drivers/gpu/drm/amd/amdgpu/df_v4_3.c @@ -0,0 +1,61 @@ +/* + * Copyright 2022 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + */ +#include "amdgpu.h" +#include "df_v4_3.h" + +#include "df/df_4_3_offset.h" +#include "df/df_4_3_sh_mask.h" + +static bool df_v4_3_query_ras_poison_mode(struct amdgpu_device *adev) +{ + uint32_t hw_assert_msklo, hw_assert_mskhi; + uint32_t v0, v1, v28, v31; + + hw_assert_msklo = RREG32_SOC15(DF, 0, + regDF_CS_UMC_AON0_HardwareAssertMaskLow); + hw_assert_mskhi = RREG32_SOC15(DF, 0, + regDF_NCS_PG0_HardwareAssertMaskHigh); + + v0 = REG_GET_FIELD(hw_assert_msklo, + DF_CS_UMC_AON0_HardwareAssertMaskLow, HWAssertMsk0); + v1 = REG_GET_FIELD(hw_assert_msklo, + DF_CS_UMC_AON0_HardwareAssertMaskLow, HWAssertMsk1); + v28 = REG_GET_FIELD(hw_assert_mskhi, + DF_NCS_PG0_HardwareAssertMaskHigh, HWAssertMsk28); + v31 = REG_GET_FIELD(hw_assert_mskhi, + DF_NCS_PG0_HardwareAssertMaskHigh, HWAssertMsk31); + + if (v0 && v1 && v28 && v31) + return true; + else if (!v0 && !v1 && !v28 && !v31) + return false; + else { + dev_warn(adev->dev, "DF poison setting is inconsistent(%d:%d:%d:%d)!\n", + v0, v1, v28, v31); + return false; + } +} + +const struct amdgpu_df_funcs df_v4_3_funcs = { + .query_ras_poison_mode = df_v4_3_query_ras_poison_mode, +}; diff --git a/drivers/gpu/drm/amd/amdgpu/df_v4_3.h b/drivers/gpu/drm/amd/amdgpu/df_v4_3.h new file mode 100644 index 000000000000..06ef0724edd3 --- /dev/null +++ b/drivers/gpu/drm/amd/amdgpu/df_v4_3.h @@ -0,0 +1,31 @@ +/* + * Copyright 2022 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + */ + +#ifndef __DF_V4_3_H__ +#define __DF_V4_3_H__ + +#include "soc15_common.h" + +extern const struct amdgpu_df_funcs df_v4_3_funcs; + +#endif diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 49d34c7bbf20..6983acc456b2 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -3891,18 +3891,12 @@ err1: static void gfx_v10_0_free_microcode(struct amdgpu_device *adev) { - release_firmware(adev->gfx.pfp_fw); - adev->gfx.pfp_fw = NULL; - release_firmware(adev->gfx.me_fw); - adev->gfx.me_fw = NULL; - release_firmware(adev->gfx.ce_fw); - adev->gfx.ce_fw = NULL; - release_firmware(adev->gfx.rlc_fw); - adev->gfx.rlc_fw = NULL; - release_firmware(adev->gfx.mec_fw); - adev->gfx.mec_fw = NULL; - release_firmware(adev->gfx.mec2_fw); - adev->gfx.mec2_fw = NULL; + amdgpu_ucode_release(&adev->gfx.pfp_fw); + amdgpu_ucode_release(&adev->gfx.me_fw); + amdgpu_ucode_release(&adev->gfx.ce_fw); + amdgpu_ucode_release(&adev->gfx.rlc_fw); + amdgpu_ucode_release(&adev->gfx.mec_fw); + amdgpu_ucode_release(&adev->gfx.mec2_fw); kfree(adev->gfx.rlc.register_list_format); } @@ -3974,9 +3968,9 @@ static void gfx_v10_0_check_gfxoff_flag(struct amdgpu_device *adev) static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) { - const char *chip_name; char fw_name[40]; - char *wks = ""; + char ucode_prefix[30]; + const char *wks = ""; int err; const struct rlc_firmware_header_v2_0 *rlc_hdr; uint16_t version_major; @@ -3984,90 +3978,40 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) DRM_DEBUG("\n"); - switch (adev->ip_versions[GC_HWIP][0]) { - case IP_VERSION(10, 1, 10): - chip_name = "navi10"; - break; - case IP_VERSION(10, 1, 1): - chip_name = "navi14"; - if (!(adev->pdev->device == 0x7340 && - adev->pdev->revision != 0x00)) - wks = "_wks"; - break; - case IP_VERSION(10, 1, 2): - chip_name = "navi12"; - break; - case IP_VERSION(10, 3, 0): - chip_name = "sienna_cichlid"; - break; - case IP_VERSION(10, 3, 2): - chip_name = "navy_flounder"; - break; - case IP_VERSION(10, 3, 1): - chip_name = "vangogh"; - break; - case IP_VERSION(10, 3, 4): - chip_name = "dimgrey_cavefish"; - break; - case IP_VERSION(10, 3, 5): - chip_name = "beige_goby"; - break; - case IP_VERSION(10, 3, 3): - chip_name = "yellow_carp"; - break; - case IP_VERSION(10, 3, 6): - chip_name = "gc_10_3_6"; - break; - case IP_VERSION(10, 1, 3): - case IP_VERSION(10, 1, 4): - chip_name = "cyan_skillfish2"; - break; - case IP_VERSION(10, 3, 7): - chip_name = "gc_10_3_7"; - break; - default: - BUG(); - } + if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(10, 1, 1) && + (!(adev->pdev->device == 0x7340 && adev->pdev->revision != 0x00))) + wks = "_wks"; + amdgpu_ucode_ip_version_decode(adev, GC_HWIP, ucode_prefix, sizeof(ucode_prefix)); - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_pfp%s.bin", chip_name, wks); - err = request_firmware(&adev->gfx.pfp_fw, fw_name, adev->dev); - if (err) - goto out; - err = amdgpu_ucode_validate(adev->gfx.pfp_fw); + snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_pfp%s.bin", ucode_prefix, wks); + err = amdgpu_ucode_request(adev, &adev->gfx.pfp_fw, fw_name); if (err) goto out; amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_PFP); - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me%s.bin", chip_name, wks); - err = request_firmware(&adev->gfx.me_fw, fw_name, adev->dev); - if (err) - goto out; - err = amdgpu_ucode_validate(adev->gfx.me_fw); + snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me%s.bin", ucode_prefix, wks); + err = amdgpu_ucode_request(adev, &adev->gfx.me_fw, fw_name); if (err) goto out; amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_ME); - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce%s.bin", chip_name, wks); - err = request_firmware(&adev->gfx.ce_fw, fw_name, adev->dev); - if (err) - goto out; - err = amdgpu_ucode_validate(adev->gfx.ce_fw); + snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce%s.bin", ucode_prefix, wks); + err = amdgpu_ucode_request(adev, &adev->gfx.ce_fw, fw_name); if (err) goto out; amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_CE); if (!amdgpu_sriov_vf(adev)) { - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", chip_name); - err = request_firmware(&adev->gfx.rlc_fw, fw_name, adev->dev); - if (err) - goto out; + snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", ucode_prefix); + err = amdgpu_ucode_request(adev, &adev->gfx.rlc_fw, fw_name); /* don't check this. There are apparently firmwares in the wild with * incorrect size in the header */ - err = amdgpu_ucode_validate(adev->gfx.rlc_fw); + if (err == -ENODEV) + goto out; if (err) dev_dbg(adev->dev, - "gfx10: amdgpu_ucode_validate() failed \"%s\"\n", + "gfx10: amdgpu_ucode_request() failed \"%s\"\n", fw_name); rlc_hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data; version_major = le16_to_cpu(rlc_hdr->header.header_version_major); @@ -4077,47 +4021,34 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) goto out; } - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec%s.bin", chip_name, wks); - err = request_firmware(&adev->gfx.mec_fw, fw_name, adev->dev); - if (err) - goto out; - err = amdgpu_ucode_validate(adev->gfx.mec_fw); + snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec%s.bin", ucode_prefix, wks); + err = amdgpu_ucode_request(adev, &adev->gfx.mec_fw, fw_name); if (err) goto out; amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC1); amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC1_JT); - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec2%s.bin", chip_name, wks); - err = request_firmware(&adev->gfx.mec2_fw, fw_name, adev->dev); + snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec2%s.bin", ucode_prefix, wks); + err = amdgpu_ucode_request(adev, &adev->gfx.mec2_fw, fw_name); if (!err) { - err = amdgpu_ucode_validate(adev->gfx.mec2_fw); - if (err) - goto out; amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC2); amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC2_JT); } else { err = 0; adev->gfx.mec2_fw = NULL; } + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC2); + amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC2_JT); gfx_v10_0_check_fw_write_wait(adev); out: if (err) { - dev_err(adev->dev, - "gfx10: Failed to init firmware \"%s\"\n", - fw_name); - release_firmware(adev->gfx.pfp_fw); - adev->gfx.pfp_fw = NULL; - release_firmware(adev->gfx.me_fw); - adev->gfx.me_fw = NULL; - release_firmware(adev->gfx.ce_fw); - adev->gfx.ce_fw = NULL; - release_firmware(adev->gfx.rlc_fw); - adev->gfx.rlc_fw = NULL; - release_firmware(adev->gfx.mec_fw); - adev->gfx.mec_fw = NULL; - release_firmware(adev->gfx.mec2_fw); - adev->gfx.mec2_fw = NULL; + amdgpu_ucode_release(&adev->gfx.pfp_fw); + amdgpu_ucode_release(&adev->gfx.me_fw); + amdgpu_ucode_release(&adev->gfx.ce_fw); + amdgpu_ucode_release(&adev->gfx.rlc_fw); + amdgpu_ucode_release(&adev->gfx.mec_fw); + amdgpu_ucode_release(&adev->gfx.mec2_fw); } gfx_v10_0_check_gfxoff_flag(adev); @@ -4270,19 +4201,11 @@ static void gfx_v10_0_mec_fini(struct amdgpu_device *adev) amdgpu_bo_free_kernel(&adev->gfx.mec.mec_fw_obj, NULL, NULL); } -static int gfx_v10_0_me_init(struct amdgpu_device *adev) +static void gfx_v10_0_me_init(struct amdgpu_device *adev) { - int r; - bitmap_zero(adev->gfx.me.queue_bitmap, AMDGPU_MAX_GFX_QUEUES); amdgpu_gfx_graphics_queue_acquire(adev); - - r = gfx_v10_0_init_microcode(adev); - if (r) - DRM_ERROR("Failed to load gfx firmware!\n"); - - return r; } static int gfx_v10_0_mec_init(struct amdgpu_device *adev) @@ -4650,9 +4573,7 @@ static int gfx_v10_0_sw_init(void *handle) adev->gfx.gfx_current_status = AMDGPU_GFX_NORMAL_MODE; - r = gfx_v10_0_me_init(adev); - if (r) - return r; + gfx_v10_0_me_init(adev); if (adev->gfx.rlc.funcs) { if (adev->gfx.rlc.funcs->init) { @@ -7630,7 +7551,7 @@ static int gfx_v10_0_early_init(void *handle) /* init rlcg reg access ctrl */ gfx_v10_0_init_rlcg_reg_access_ctrl(adev); - return 0; + return gfx_v10_0_init_microcode(adev); } static int gfx_v10_0_late_init(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index b9b57a66e113..3bf697a80cf2 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -46,6 +46,7 @@ #include "clearstate_gfx11.h" #include "v11_structs.h" #include "gfx_v11_0.h" +#include "gfx_v11_0_3.h" #include "nbio_v4_3.h" #include "mes_v11_0.h" @@ -431,18 +432,37 @@ err1: static void gfx_v11_0_free_microcode(struct amdgpu_device *adev) { - release_firmware(adev->gfx.pfp_fw); - adev->gfx.pfp_fw = NULL; - release_firmware(adev->gfx.me_fw); - adev->gfx.me_fw = NULL; - release_firmware(adev->gfx.rlc_fw); - adev->gfx.rlc_fw = NULL; - release_firmware(adev->gfx.mec_fw); - adev->gfx.mec_fw = NULL; + amdgpu_ucode_release(&adev->gfx.pfp_fw); + amdgpu_ucode_release(&adev->gfx.me_fw); + amdgpu_ucode_release(&adev->gfx.rlc_fw); + amdgpu_ucode_release(&adev->gfx.mec_fw); kfree(adev->gfx.rlc.register_list_format); } +static int gfx_v11_0_init_toc_microcode(struct amdgpu_device *adev, const char *ucode_prefix) +{ + const struct psp_firmware_header_v1_0 *toc_hdr; + int err = 0; + char fw_name[40]; + + snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_toc.bin", ucode_prefix); + err = amdgpu_ucode_request(adev, &adev->psp.toc_fw, fw_name); + if (err) + goto out; + + toc_hdr = (const struct psp_firmware_header_v1_0 *)adev->psp.toc_fw->data; + adev->psp.toc.fw_version = le32_to_cpu(toc_hdr->header.ucode_version); + adev->psp.toc.feature_version = le32_to_cpu(toc_hdr->sos.fw_version); + adev->psp.toc.size_bytes = le32_to_cpu(toc_hdr->header.ucode_size_bytes); + adev->psp.toc.start_addr = (uint8_t *)toc_hdr + + le32_to_cpu(toc_hdr->header.ucode_array_offset_bytes); + return 0; +out: + amdgpu_ucode_release(&adev->psp.toc_fw); + return err; +} + static int gfx_v11_0_init_microcode(struct amdgpu_device *adev) { char fw_name[40]; @@ -457,10 +477,7 @@ static int gfx_v11_0_init_microcode(struct amdgpu_device *adev) amdgpu_ucode_ip_version_decode(adev, GC_HWIP, ucode_prefix, sizeof(ucode_prefix)); snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_pfp.bin", ucode_prefix); - err = request_firmware(&adev->gfx.pfp_fw, fw_name, adev->dev); - if (err) - goto out; - err = amdgpu_ucode_validate(adev->gfx.pfp_fw); + err = amdgpu_ucode_request(adev, &adev->gfx.pfp_fw, fw_name); if (err) goto out; /* check pfp fw hdr version to decide if enable rs64 for gfx11.*/ @@ -477,10 +494,7 @@ static int gfx_v11_0_init_microcode(struct amdgpu_device *adev) } snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me.bin", ucode_prefix); - err = request_firmware(&adev->gfx.me_fw, fw_name, adev->dev); - if (err) - goto out; - err = amdgpu_ucode_validate(adev->gfx.me_fw); + err = amdgpu_ucode_request(adev, &adev->gfx.me_fw, fw_name); if (err) goto out; if (adev->gfx.rs64_enable) { @@ -493,10 +507,7 @@ static int gfx_v11_0_init_microcode(struct amdgpu_device *adev) if (!amdgpu_sriov_vf(adev)) { snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", ucode_prefix); - err = request_firmware(&adev->gfx.rlc_fw, fw_name, adev->dev); - if (err) - goto out; - err = amdgpu_ucode_validate(adev->gfx.rlc_fw); + err = amdgpu_ucode_request(adev, &adev->gfx.rlc_fw, fw_name); if (err) goto out; rlc_hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data; @@ -508,10 +519,7 @@ static int gfx_v11_0_init_microcode(struct amdgpu_device *adev) } snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec.bin", ucode_prefix); - err = request_firmware(&adev->gfx.mec_fw, fw_name, adev->dev); - if (err) - goto out; - err = amdgpu_ucode_validate(adev->gfx.mec_fw); + err = amdgpu_ucode_request(adev, &adev->gfx.mec_fw, fw_name); if (err) goto out; if (adev->gfx.rs64_enable) { @@ -525,59 +533,23 @@ static int gfx_v11_0_init_microcode(struct amdgpu_device *adev) amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC1_JT); } + if (adev->firmware.load_type == AMDGPU_FW_LOAD_RLC_BACKDOOR_AUTO) + err = gfx_v11_0_init_toc_microcode(adev, ucode_prefix); + /* only one MEC for gfx 11.0.0. */ adev->gfx.mec2_fw = NULL; out: if (err) { - dev_err(adev->dev, - "gfx11: Failed to init firmware \"%s\"\n", - fw_name); - release_firmware(adev->gfx.pfp_fw); - adev->gfx.pfp_fw = NULL; - release_firmware(adev->gfx.me_fw); - adev->gfx.me_fw = NULL; - release_firmware(adev->gfx.rlc_fw); - adev->gfx.rlc_fw = NULL; - release_firmware(adev->gfx.mec_fw); - adev->gfx.mec_fw = NULL; + amdgpu_ucode_release(&adev->gfx.pfp_fw); + amdgpu_ucode_release(&adev->gfx.me_fw); + amdgpu_ucode_release(&adev->gfx.rlc_fw); + amdgpu_ucode_release(&adev->gfx.mec_fw); } return err; } -static int gfx_v11_0_init_toc_microcode(struct amdgpu_device *adev) -{ - const struct psp_firmware_header_v1_0 *toc_hdr; - int err = 0; - char fw_name[40]; - char ucode_prefix[30]; - - amdgpu_ucode_ip_version_decode(adev, GC_HWIP, ucode_prefix, sizeof(ucode_prefix)); - - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_toc.bin", ucode_prefix); - err = request_firmware(&adev->psp.toc_fw, fw_name, adev->dev); - if (err) - goto out; - - err = amdgpu_ucode_validate(adev->psp.toc_fw); - if (err) - goto out; - - toc_hdr = (const struct psp_firmware_header_v1_0 *)adev->psp.toc_fw->data; - adev->psp.toc.fw_version = le32_to_cpu(toc_hdr->header.ucode_version); - adev->psp.toc.feature_version = le32_to_cpu(toc_hdr->sos.fw_version); - adev->psp.toc.size_bytes = le32_to_cpu(toc_hdr->header.ucode_size_bytes); - adev->psp.toc.start_addr = (uint8_t *)toc_hdr + - le32_to_cpu(toc_hdr->header.ucode_array_offset_bytes); - return 0; -out: - dev_err(adev->dev, "Failed to load TOC microcode\n"); - release_firmware(adev->psp.toc_fw); - adev->psp.toc_fw = NULL; - return err; -} - static u32 gfx_v11_0_get_csb_size(struct amdgpu_device *adev) { u32 count = 0; @@ -714,19 +686,11 @@ static void gfx_v11_0_mec_fini(struct amdgpu_device *adev) amdgpu_bo_free_kernel(&adev->gfx.mec.mec_fw_data_obj, NULL, NULL); } -static int gfx_v11_0_me_init(struct amdgpu_device *adev) +static void gfx_v11_0_me_init(struct amdgpu_device *adev) { - int r; - bitmap_zero(adev->gfx.me.queue_bitmap, AMDGPU_MAX_GFX_QUEUES); amdgpu_gfx_graphics_queue_acquire(adev); - - r = gfx_v11_0_init_microcode(adev); - if (r) - DRM_ERROR("Failed to load gfx firmware!\n"); - - return r; } static int gfx_v11_0_mec_init(struct amdgpu_device *adev) @@ -790,8 +754,8 @@ static void gfx_v11_0_read_wave_data(struct amdgpu_device *adev, uint32_t simd, * zero here */ WARN_ON(simd != 0); - /* type 2 wave data */ - dst[(*no_fields)++] = 2; + /* type 3 wave data */ + dst[(*no_fields)++] = 3; dst[(*no_fields)++] = wave_read_ind(adev, wave, ixSQ_WAVE_STATUS); dst[(*no_fields)++] = wave_read_ind(adev, wave, ixSQ_WAVE_PC_LO); dst[(*no_fields)++] = wave_read_ind(adev, wave, ixSQ_WAVE_PC_HI); @@ -852,7 +816,14 @@ static int gfx_v11_0_gpu_early_init(struct amdgpu_device *adev) switch (adev->ip_versions[GC_HWIP][0]) { case IP_VERSION(11, 0, 0): case IP_VERSION(11, 0, 2): + adev->gfx.config.max_hw_contexts = 8; + adev->gfx.config.sc_prim_fifo_size_frontend = 0x20; + adev->gfx.config.sc_prim_fifo_size_backend = 0x100; + adev->gfx.config.sc_hiz_tile_fifo_size = 0; + adev->gfx.config.sc_earlyz_tile_fifo_size = 0x4C0; + break; case IP_VERSION(11, 0, 3): + adev->gfx.ras = &gfx_v11_0_3_ras; adev->gfx.config.max_hw_contexts = 8; adev->gfx.config.sc_prim_fifo_size_frontend = 0x20; adev->gfx.config.sc_prim_fifo_size_backend = 0x100; @@ -987,10 +958,11 @@ static int gfx_v11_0_rlc_autoload_buffer_init(struct amdgpu_device *adev) total_size = gfx_v11_0_calc_toc_total_size(adev); r = amdgpu_bo_create_reserved(adev, total_size, 64 * 1024, - AMDGPU_GEM_DOMAIN_VRAM, - &adev->gfx.rlc.rlc_autoload_bo, - &adev->gfx.rlc.rlc_autoload_gpu_addr, - (void **)&adev->gfx.rlc.rlc_autoload_ptr); + AMDGPU_GEM_DOMAIN_VRAM | + AMDGPU_GEM_DOMAIN_GTT, + &adev->gfx.rlc.rlc_autoload_bo, + &adev->gfx.rlc.rlc_autoload_gpu_addr, + (void **)&adev->gfx.rlc.rlc_autoload_ptr); if (r) { dev_err(adev->dev, "(%d) failed to create fw autoload bo\n", r); @@ -1336,6 +1308,20 @@ static int gfx_v11_0_sw_init(void *handle) if (r) return r; + /* ECC error */ + r = amdgpu_irq_add_id(adev, SOC21_IH_CLIENTID_GRBM_CP, + GFX_11_0_0__SRCID__CP_ECC_ERROR, + &adev->gfx.cp_ecc_error_irq); + if (r) + return r; + + /* FED error */ + r = amdgpu_irq_add_id(adev, SOC21_IH_CLIENTID_GFX, + GFX_11_0_0__SRCID__RLC_GC_FED_INTERRUPT, + &adev->gfx.rlc_gc_fed_irq); + if (r) + return r; + adev->gfx.gfx_current_status = AMDGPU_GFX_NORMAL_MODE; if (adev->gfx.imu.funcs) { @@ -1346,9 +1332,7 @@ static int gfx_v11_0_sw_init(void *handle) } } - r = gfx_v11_0_me_init(adev); - if (r) - return r; + gfx_v11_0_me_init(adev); r = gfx_v11_0_rlc_init(adev); if (r) { @@ -1416,9 +1400,6 @@ static int gfx_v11_0_sw_init(void *handle) /* allocate visible FB for rlc auto-loading fw */ if (adev->firmware.load_type == AMDGPU_FW_LOAD_RLC_BACKDOOR_AUTO) { - r = gfx_v11_0_init_toc_microcode(adev); - if (r) - dev_err(adev->dev, "Failed to load toc firmware!\n"); r = gfx_v11_0_rlc_autoload_buffer_init(adev); if (r) return r; @@ -1428,6 +1409,11 @@ static int gfx_v11_0_sw_init(void *handle) if (r) return r; + if (amdgpu_gfx_ras_sw_init(adev)) { + dev_err(adev->dev, "Failed to initialize gfx ras block!\n"); + return -EINVAL; + } + return 0; } @@ -1517,44 +1503,70 @@ static void gfx_v11_0_select_se_sh(struct amdgpu_device *adev, u32 se_num, WREG32_SOC15(GC, 0, regGRBM_GFX_INDEX, data); } -static u32 gfx_v11_0_get_rb_active_bitmap(struct amdgpu_device *adev) +static u32 gfx_v11_0_get_sa_active_bitmap(struct amdgpu_device *adev) { - u32 data, mask; + u32 gc_disabled_sa_mask, gc_user_disabled_sa_mask, sa_mask; - data = RREG32_SOC15(GC, 0, regCC_RB_BACKEND_DISABLE); - data |= RREG32_SOC15(GC, 0, regGC_USER_RB_BACKEND_DISABLE); + gc_disabled_sa_mask = RREG32_SOC15(GC, 0, regCC_GC_SA_UNIT_DISABLE); + gc_disabled_sa_mask = REG_GET_FIELD(gc_disabled_sa_mask, + CC_GC_SA_UNIT_DISABLE, + SA_DISABLE); + gc_user_disabled_sa_mask = RREG32_SOC15(GC, 0, regGC_USER_SA_UNIT_DISABLE); + gc_user_disabled_sa_mask = REG_GET_FIELD(gc_user_disabled_sa_mask, + GC_USER_SA_UNIT_DISABLE, + SA_DISABLE); + sa_mask = amdgpu_gfx_create_bitmask(adev->gfx.config.max_sh_per_se * + adev->gfx.config.max_shader_engines); - data &= CC_RB_BACKEND_DISABLE__BACKEND_DISABLE_MASK; - data >>= GC_USER_RB_BACKEND_DISABLE__BACKEND_DISABLE__SHIFT; + return sa_mask & (~(gc_disabled_sa_mask | gc_user_disabled_sa_mask)); +} - mask = amdgpu_gfx_create_bitmask(adev->gfx.config.max_backends_per_se / - adev->gfx.config.max_sh_per_se); +static u32 gfx_v11_0_get_rb_active_bitmap(struct amdgpu_device *adev) +{ + u32 gc_disabled_rb_mask, gc_user_disabled_rb_mask; + u32 rb_mask; + + gc_disabled_rb_mask = RREG32_SOC15(GC, 0, regCC_RB_BACKEND_DISABLE); + gc_disabled_rb_mask = REG_GET_FIELD(gc_disabled_rb_mask, + CC_RB_BACKEND_DISABLE, + BACKEND_DISABLE); + gc_user_disabled_rb_mask = RREG32_SOC15(GC, 0, regGC_USER_RB_BACKEND_DISABLE); + gc_user_disabled_rb_mask = REG_GET_FIELD(gc_user_disabled_rb_mask, + GC_USER_RB_BACKEND_DISABLE, + BACKEND_DISABLE); + rb_mask = amdgpu_gfx_create_bitmask(adev->gfx.config.max_backends_per_se * + adev->gfx.config.max_shader_engines); - return (~data) & mask; + return rb_mask & (~(gc_disabled_rb_mask | gc_user_disabled_rb_mask)); } static void gfx_v11_0_setup_rb(struct amdgpu_device *adev) { - int i, j; - u32 data; - u32 active_rbs = 0; - u32 rb_bitmap_width_per_sh = adev->gfx.config.max_backends_per_se / - adev->gfx.config.max_sh_per_se; + u32 rb_bitmap_width_per_sa; + u32 max_sa; + u32 active_sa_bitmap; + u32 global_active_rb_bitmap; + u32 active_rb_bitmap = 0; + u32 i; - mutex_lock(&adev->grbm_idx_mutex); - for (i = 0; i < adev->gfx.config.max_shader_engines; i++) { - for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) { - gfx_v11_0_select_se_sh(adev, i, j, 0xffffffff); - data = gfx_v11_0_get_rb_active_bitmap(adev); - active_rbs |= data << ((i * adev->gfx.config.max_sh_per_se + j) * - rb_bitmap_width_per_sh); - } + /* query sa bitmap from SA_UNIT_DISABLE registers */ + active_sa_bitmap = gfx_v11_0_get_sa_active_bitmap(adev); + /* query rb bitmap from RB_BACKEND_DISABLE registers */ + global_active_rb_bitmap = gfx_v11_0_get_rb_active_bitmap(adev); + + /* generate active rb bitmap according to active sa bitmap */ + max_sa = adev->gfx.config.max_shader_engines * + adev->gfx.config.max_sh_per_se; + rb_bitmap_width_per_sa = adev->gfx.config.max_backends_per_se / + adev->gfx.config.max_sh_per_se; + for (i = 0; i < max_sa; i++) { + if (active_sa_bitmap & (1 << i)) + active_rb_bitmap |= (0x3 << (i * rb_bitmap_width_per_sa)); } - gfx_v11_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); - mutex_unlock(&adev->grbm_idx_mutex); - adev->gfx.config.backend_enable_mask = active_rbs; - adev->gfx.config.num_rbs = hweight32(active_rbs); + active_rb_bitmap |= global_active_rb_bitmap; + adev->gfx.config.backend_enable_mask = active_rb_bitmap; + adev->gfx.config.num_rbs = hweight32(active_rb_bitmap); } #define DEFAULT_SH_MEM_BASES (0x6000) @@ -1647,6 +1659,11 @@ static void gfx_v11_0_constants_init(struct amdgpu_device *adev) gfx_v11_0_get_tcc_info(adev); adev->gfx.config.pa_sc_tile_steering_override = 0; + /* Set whether texture coordinate truncation is conformant. */ + tmp = RREG32_SOC15(GC, 0, regTA_CNTL2); + adev->gfx.config.ta_cntl2_truncate_coord_mode = + REG_GET_FIELD(tmp, TA_CNTL2, TRUNCATE_COORD_MODE); + /* XXX SH_MEM regs */ /* where to put LDS, scratch, GPUVM in FSA64 space */ mutex_lock(&adev->srbm_mutex); @@ -2656,7 +2673,9 @@ static int gfx_v11_0_cp_gfx_load_pfp_microcode_rs64(struct amdgpu_device *adev) /* 64kb align */ r = amdgpu_bo_create_reserved(adev, fw_ucode_size, - 64 * 1024, AMDGPU_GEM_DOMAIN_VRAM, + 64 * 1024, + AMDGPU_GEM_DOMAIN_VRAM | + AMDGPU_GEM_DOMAIN_GTT, &adev->gfx.pfp.pfp_fw_obj, &adev->gfx.pfp.pfp_fw_gpu_addr, (void **)&adev->gfx.pfp.pfp_fw_ptr); @@ -2667,7 +2686,9 @@ static int gfx_v11_0_cp_gfx_load_pfp_microcode_rs64(struct amdgpu_device *adev) } r = amdgpu_bo_create_reserved(adev, fw_data_size, - 64 * 1024, AMDGPU_GEM_DOMAIN_VRAM, + 64 * 1024, + AMDGPU_GEM_DOMAIN_VRAM | + AMDGPU_GEM_DOMAIN_GTT, &adev->gfx.pfp.pfp_fw_data_obj, &adev->gfx.pfp.pfp_fw_data_gpu_addr, (void **)&adev->gfx.pfp.pfp_fw_data_ptr); @@ -2870,7 +2891,9 @@ static int gfx_v11_0_cp_gfx_load_me_microcode_rs64(struct amdgpu_device *adev) /* 64kb align*/ r = amdgpu_bo_create_reserved(adev, fw_ucode_size, - 64 * 1024, AMDGPU_GEM_DOMAIN_VRAM, + 64 * 1024, + AMDGPU_GEM_DOMAIN_VRAM | + AMDGPU_GEM_DOMAIN_GTT, &adev->gfx.me.me_fw_obj, &adev->gfx.me.me_fw_gpu_addr, (void **)&adev->gfx.me.me_fw_ptr); @@ -2881,7 +2904,9 @@ static int gfx_v11_0_cp_gfx_load_me_microcode_rs64(struct amdgpu_device *adev) } r = amdgpu_bo_create_reserved(adev, fw_data_size, - 64 * 1024, AMDGPU_GEM_DOMAIN_VRAM, + 64 * 1024, + AMDGPU_GEM_DOMAIN_VRAM | + AMDGPU_GEM_DOMAIN_GTT, &adev->gfx.me.me_fw_data_obj, &adev->gfx.me.me_fw_data_gpu_addr, (void **)&adev->gfx.me.me_fw_data_ptr); @@ -3387,7 +3412,9 @@ static int gfx_v11_0_cp_compute_load_microcode_rs64(struct amdgpu_device *adev) fw_data_size = le32_to_cpu(mec_hdr->data_size_bytes); r = amdgpu_bo_create_reserved(adev, fw_ucode_size, - 64 * 1024, AMDGPU_GEM_DOMAIN_VRAM, + 64 * 1024, + AMDGPU_GEM_DOMAIN_VRAM | + AMDGPU_GEM_DOMAIN_GTT, &adev->gfx.mec.mec_fw_obj, &adev->gfx.mec.mec_fw_gpu_addr, (void **)&fw_ucode_ptr); @@ -3398,7 +3425,9 @@ static int gfx_v11_0_cp_compute_load_microcode_rs64(struct amdgpu_device *adev) } r = amdgpu_bo_create_reserved(adev, fw_data_size, - 64 * 1024, AMDGPU_GEM_DOMAIN_VRAM, + 64 * 1024, + AMDGPU_GEM_DOMAIN_VRAM | + AMDGPU_GEM_DOMAIN_GTT, &adev->gfx.mec.mec_fw_data_obj, &adev->gfx.mec.mec_fw_data_gpu_addr, (void **)&fw_data_ptr); @@ -4408,6 +4437,7 @@ static int gfx_v11_0_hw_fini(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; int r; + amdgpu_irq_put(adev, &adev->gfx.cp_ecc_error_irq, 0); amdgpu_irq_put(adev, &adev->gfx.priv_reg_irq, 0); amdgpu_irq_put(adev, &adev->gfx.priv_inst_irq, 0); @@ -4687,7 +4717,7 @@ static int gfx_v11_0_early_init(void *handle) gfx_v11_0_init_rlcg_reg_access_ctrl(adev); - return 0; + return gfx_v11_0_init_microcode(adev); } static int gfx_v11_0_ras_late_init(void *handle) @@ -5839,6 +5869,36 @@ static void gfx_v11_0_set_compute_eop_interrupt_state(struct amdgpu_device *adev } } +#define CP_ME1_PIPE_INST_ADDR_INTERVAL 0x1 +#define SET_ECC_ME_PIPE_STATE(reg_addr, state) \ + do { \ + uint32_t tmp = RREG32_SOC15_IP(GC, reg_addr); \ + tmp = REG_SET_FIELD(tmp, CP_ME1_PIPE0_INT_CNTL, CP_ECC_ERROR_INT_ENABLE, state); \ + WREG32_SOC15_IP(GC, reg_addr, tmp); \ + } while (0) + +static int gfx_v11_0_set_cp_ecc_error_state(struct amdgpu_device *adev, + struct amdgpu_irq_src *source, + unsigned type, + enum amdgpu_interrupt_state state) +{ + uint32_t ecc_irq_state = 0; + uint32_t pipe0_int_cntl_addr = 0; + int i = 0; + + ecc_irq_state = (state == AMDGPU_IRQ_STATE_ENABLE) ? 1 : 0; + + pipe0_int_cntl_addr = SOC15_REG_OFFSET(GC, 0, regCP_ME1_PIPE0_INT_CNTL); + + WREG32_FIELD15_PREREG(GC, 0, CP_INT_CNTL_RING0, CP_ECC_ERROR_INT_ENABLE, ecc_irq_state); + + for (i = 0; i < adev->gfx.mec.num_pipe_per_mec; i++) + SET_ECC_ME_PIPE_STATE(pipe0_int_cntl_addr + i * CP_ME1_PIPE_INST_ADDR_INTERVAL, + ecc_irq_state); + + return 0; +} + static int gfx_v11_0_set_eop_interrupt_state(struct amdgpu_device *adev, struct amdgpu_irq_src *src, unsigned type, @@ -6015,6 +6075,16 @@ static int gfx_v11_0_priv_inst_irq(struct amdgpu_device *adev, return 0; } +static int gfx_v11_0_rlc_gc_fed_irq(struct amdgpu_device *adev, + struct amdgpu_irq_src *source, + struct amdgpu_iv_entry *entry) +{ + if (adev->gfx.ras && adev->gfx.ras->rlc_gc_fed_irq) + return adev->gfx.ras->rlc_gc_fed_irq(adev, source, entry); + + return 0; +} + #if 0 static int gfx_v11_0_kiq_set_interrupt_state(struct amdgpu_device *adev, struct amdgpu_irq_src *src, @@ -6245,6 +6315,15 @@ static const struct amdgpu_irq_src_funcs gfx_v11_0_priv_inst_irq_funcs = { .process = gfx_v11_0_priv_inst_irq, }; +static const struct amdgpu_irq_src_funcs gfx_v11_0_cp_ecc_error_irq_funcs = { + .set = gfx_v11_0_set_cp_ecc_error_state, + .process = amdgpu_gfx_cp_ecc_error_irq, +}; + +static const struct amdgpu_irq_src_funcs gfx_v11_0_rlc_gc_fed_irq_funcs = { + .process = gfx_v11_0_rlc_gc_fed_irq, +}; + static void gfx_v11_0_set_irq_funcs(struct amdgpu_device *adev) { adev->gfx.eop_irq.num_types = AMDGPU_CP_IRQ_LAST; @@ -6255,6 +6334,13 @@ static void gfx_v11_0_set_irq_funcs(struct amdgpu_device *adev) adev->gfx.priv_inst_irq.num_types = 1; adev->gfx.priv_inst_irq.funcs = &gfx_v11_0_priv_inst_irq_funcs; + + adev->gfx.cp_ecc_error_irq.num_types = 1; /* CP ECC error */ + adev->gfx.cp_ecc_error_irq.funcs = &gfx_v11_0_cp_ecc_error_irq_funcs; + + adev->gfx.rlc_gc_fed_irq.num_types = 1; /* 0x80 FED error */ + adev->gfx.rlc_gc_fed_irq.funcs = &gfx_v11_0_rlc_gc_fed_irq_funcs; + } static void gfx_v11_0_set_imu_funcs(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0_3.c new file mode 100644 index 000000000000..b07a72ca25d9 --- /dev/null +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0_3.c @@ -0,0 +1,88 @@ +/* + * Copyright 2023 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + */ + +#include "amdgpu.h" +#include "soc21.h" +#include "gc/gc_11_0_3_offset.h" +#include "gc/gc_11_0_3_sh_mask.h" +#include "ivsrcid/gfx/irqsrcs_gfx_11_0_0.h" +#include "soc15.h" +#include "soc15d.h" +#include "gfx_v11_0.h" + + +static int gfx_v11_0_3_rlc_gc_fed_irq(struct amdgpu_device *adev, + struct amdgpu_irq_src *source, + struct amdgpu_iv_entry *entry) +{ + uint32_t rlc_status0 = 0, rlc_status1 = 0; + struct ras_common_if *ras_if = NULL; + struct ras_dispatch_if ih_data = { + .entry = entry, + }; + + rlc_status0 = RREG32(SOC15_REG_OFFSET(GC, 0, regRLC_RLCS_FED_STATUS_0)); + rlc_status1 = RREG32(SOC15_REG_OFFSET(GC, 0, regRLC_RLCS_FED_STATUS_1)); + + if (!rlc_status0 && !rlc_status1) { + dev_warn(adev->dev, "RLC_GC_FED irq is generated, but rlc_status0 and rlc_status1 are empty!\n"); + return 0; + } + + /* Use RLC_RLCS_FED_STATUS_0/1 to distinguish FED error block. */ + if (REG_GET_FIELD(rlc_status0, RLC_RLCS_FED_STATUS_0, SDMA0_FED_ERR) || + REG_GET_FIELD(rlc_status0, RLC_RLCS_FED_STATUS_0, SDMA1_FED_ERR)) + ras_if = adev->sdma.ras_if; + else + ras_if = adev->gfx.ras_if; + + if (!ras_if) { + dev_err(adev->dev, "Gfx or sdma ras block not initialized, rlc_status0:0x%x.\n", + rlc_status0); + return -EINVAL; + } + + ih_data.head = *ras_if; + + dev_warn(adev->dev, "RLC %s FED IRQ\n", ras_if->name); + amdgpu_ras_interrupt_dispatch(adev, &ih_data); + + return 0; +} + +static int gfx_v11_0_3_poison_consumption_handler(struct amdgpu_device *adev, + struct amdgpu_iv_entry *entry) +{ + /* Workaround: when vmid and pasid are both zero, trigger gpu reset in KGD. */ + if (entry && (entry->client_id == SOC21_IH_CLIENTID_GFX) && + (entry->src_id == GFX_11_0_0__SRCID__RLC_GC_FED_INTERRUPT) && + !entry->vmid && !entry->pasid) + amdgpu_ras_reset_gpu(adev); + + return 0; +} + +struct amdgpu_gfx_ras gfx_v11_0_3_ras = { + .rlc_gc_fed_irq = gfx_v11_0_3_rlc_gc_fed_irq, + .poison_consumption_handler = gfx_v11_0_3_poison_consumption_handler, +}; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0_3.h b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0_3.h new file mode 100644 index 000000000000..672c7920b3d0 --- /dev/null +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0_3.h @@ -0,0 +1,29 @@ +/* + * Copyright 2023 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + */ + +#ifndef __GFX_V11_0_3_H__ +#define __GFX_V11_0_3_H__ + +extern struct amdgpu_gfx_ras gfx_v11_0_3_ras; + +#endif diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c index 204b246f0e3f..c41219e23151 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c @@ -338,10 +338,7 @@ static int gfx_v6_0_init_microcode(struct amdgpu_device *adev) } snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_pfp.bin", chip_name); - err = request_firmware(&adev->gfx.pfp_fw, fw_name, adev->dev); - if (err) - goto out; - err = amdgpu_ucode_validate(adev->gfx.pfp_fw); + err = amdgpu_ucode_request(adev, &adev->gfx.pfp_fw, fw_name); if (err) goto out; cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.pfp_fw->data; @@ -349,10 +346,7 @@ static int gfx_v6_0_init_microcode(struct amdgpu_device *adev) adev->gfx.pfp_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version); snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me.bin", chip_name); - err = request_firmware(&adev->gfx.me_fw, fw_name, adev->dev); - if (err) - goto out; - err = amdgpu_ucode_validate(adev->gfx.me_fw); + err = amdgpu_ucode_request(adev, &adev->gfx.me_fw, fw_name); if (err) goto out; cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.me_fw->data; @@ -360,10 +354,7 @@ static int gfx_v6_0_init_microcode(struct amdgpu_device *adev) adev->gfx.me_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version); snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce.bin", chip_name); - err = request_firmware(&adev->gfx.ce_fw, fw_name, adev->dev); - if (err) - goto out; - err = amdgpu_ucode_validate(adev->gfx.ce_fw); + err = amdgpu_ucode_request(adev, &adev->gfx.ce_fw, fw_name); if (err) goto out; cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.ce_fw->data; @@ -371,10 +362,9 @@ static int gfx_v6_0_init_microcode(struct amdgpu_device *adev) adev->gfx.ce_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version); snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", chip_name); - err = request_firmware(&adev->gfx.rlc_fw, fw_name, adev->dev); + err = amdgpu_ucode_request(adev, &adev->gfx.rlc_fw, fw_name); if (err) goto out; - err = amdgpu_ucode_validate(adev->gfx.rlc_fw); rlc_hdr = (const struct rlc_firmware_header_v1_0 *)adev->gfx.rlc_fw->data; adev->gfx.rlc_fw_version = le32_to_cpu(rlc_hdr->header.ucode_version); adev->gfx.rlc_feature_version = le32_to_cpu(rlc_hdr->ucode_feature_version); @@ -382,14 +372,10 @@ static int gfx_v6_0_init_microcode(struct amdgpu_device *adev) out: if (err) { pr_err("gfx6: Failed to load firmware \"%s\"\n", fw_name); - release_firmware(adev->gfx.pfp_fw); - adev->gfx.pfp_fw = NULL; - release_firmware(adev->gfx.me_fw); - adev->gfx.me_fw = NULL; - release_firmware(adev->gfx.ce_fw); - adev->gfx.ce_fw = NULL; - release_firmware(adev->gfx.rlc_fw); - adev->gfx.rlc_fw = NULL; + amdgpu_ucode_release(&adev->gfx.pfp_fw); + amdgpu_ucode_release(&adev->gfx.me_fw); + amdgpu_ucode_release(&adev->gfx.ce_fw); + amdgpu_ucode_release(&adev->gfx.rlc_fw); } return err; } @@ -2375,7 +2361,8 @@ static int gfx_v6_0_rlc_init(struct amdgpu_device *adev) dws = adev->gfx.rlc.clear_state_size + (256 / 4); r = amdgpu_bo_create_reserved(adev, dws * 4, PAGE_SIZE, - AMDGPU_GEM_DOMAIN_VRAM, + AMDGPU_GEM_DOMAIN_VRAM | + AMDGPU_GEM_DOMAIN_GTT, &adev->gfx.rlc.clear_state_obj, &adev->gfx.rlc.clear_state_gpu_addr, (void **)&adev->gfx.rlc.cs_ptr); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c index 0f2976507e48..9d5c1e29b4a3 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c @@ -887,6 +887,16 @@ static void gfx_v7_0_get_csb_buffer(struct amdgpu_device *adev, volatile u32 *bu static void gfx_v7_0_init_pg(struct amdgpu_device *adev); static void gfx_v7_0_get_cu_info(struct amdgpu_device *adev); +static void gfx_v7_0_free_microcode(struct amdgpu_device *adev) +{ + amdgpu_ucode_release(&adev->gfx.pfp_fw); + amdgpu_ucode_release(&adev->gfx.me_fw); + amdgpu_ucode_release(&adev->gfx.ce_fw); + amdgpu_ucode_release(&adev->gfx.mec_fw); + amdgpu_ucode_release(&adev->gfx.mec2_fw); + amdgpu_ucode_release(&adev->gfx.rlc_fw); +} + /* * Core functions */ @@ -927,88 +937,44 @@ static int gfx_v7_0_init_microcode(struct amdgpu_device *adev) } snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_pfp.bin", chip_name); - err = request_firmware(&adev->gfx.pfp_fw, fw_name, adev->dev); - if (err) - goto out; - err = amdgpu_ucode_validate(adev->gfx.pfp_fw); + err = amdgpu_ucode_request(adev, &adev->gfx.pfp_fw, fw_name); if (err) goto out; snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me.bin", chip_name); - err = request_firmware(&adev->gfx.me_fw, fw_name, adev->dev); - if (err) - goto out; - err = amdgpu_ucode_validate(adev->gfx.me_fw); + err = amdgpu_ucode_request(adev, &adev->gfx.me_fw, fw_name); if (err) goto out; snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce.bin", chip_name); - err = request_firmware(&adev->gfx.ce_fw, fw_name, adev->dev); - if (err) - goto out; - err = amdgpu_ucode_validate(adev->gfx.ce_fw); + err = amdgpu_ucode_request(adev, &adev->gfx.ce_fw, fw_name); if (err) goto out; snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec.bin", chip_name); - err = request_firmware(&adev->gfx.mec_fw, fw_name, adev->dev); - if (err) - goto out; - err = amdgpu_ucode_validate(adev->gfx.mec_fw); + err = amdgpu_ucode_request(adev, &adev->gfx.mec_fw, fw_name); if (err) goto out; if (adev->asic_type == CHIP_KAVERI) { snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec2.bin", chip_name); - err = request_firmware(&adev->gfx.mec2_fw, fw_name, adev->dev); - if (err) - goto out; - err = amdgpu_ucode_validate(adev->gfx.mec2_fw); + err = amdgpu_ucode_request(adev, &adev->gfx.mec2_fw, fw_name); if (err) goto out; } snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", chip_name); - err = request_firmware(&adev->gfx.rlc_fw, fw_name, adev->dev); + err = amdgpu_ucode_request(adev, &adev->gfx.rlc_fw, fw_name); if (err) goto out; - err = amdgpu_ucode_validate(adev->gfx.rlc_fw); - out: if (err) { pr_err("gfx7: Failed to load firmware \"%s\"\n", fw_name); - release_firmware(adev->gfx.pfp_fw); - adev->gfx.pfp_fw = NULL; - release_firmware(adev->gfx.me_fw); - adev->gfx.me_fw = NULL; - release_firmware(adev->gfx.ce_fw); - adev->gfx.ce_fw = NULL; - release_firmware(adev->gfx.mec_fw); - adev->gfx.mec_fw = NULL; - release_firmware(adev->gfx.mec2_fw); - adev->gfx.mec2_fw = NULL; - release_firmware(adev->gfx.rlc_fw); - adev->gfx.rlc_fw = NULL; + gfx_v7_0_free_microcode(adev); } return err; } -static void gfx_v7_0_free_microcode(struct amdgpu_device *adev) -{ - release_firmware(adev->gfx.pfp_fw); - adev->gfx.pfp_fw = NULL; - release_firmware(adev->gfx.me_fw); - adev->gfx.me_fw = NULL; - release_firmware(adev->gfx.ce_fw); - adev->gfx.ce_fw = NULL; - release_firmware(adev->gfx.mec_fw); - adev->gfx.mec_fw = NULL; - release_firmware(adev->gfx.mec2_fw); - adev->gfx.mec2_fw = NULL; - release_firmware(adev->gfx.rlc_fw); - adev->gfx.rlc_fw = NULL; -} - /** * gfx_v7_0_tiling_mode_table_init - init the hw tiling table * @@ -2772,7 +2738,8 @@ static int gfx_v7_0_mec_init(struct amdgpu_device *adev) * GFX7_MEC_HPD_SIZE * 2; r = amdgpu_bo_create_reserved(adev, mec_hpd_size, PAGE_SIZE, - AMDGPU_GEM_DOMAIN_VRAM, + AMDGPU_GEM_DOMAIN_VRAM | + AMDGPU_GEM_DOMAIN_GTT, &adev->gfx.mec.hpd_eop_obj, &adev->gfx.mec.hpd_eop_gpu_addr, (void **)&hpd); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index d47135606e3e..b1f2684d854a 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -924,20 +924,14 @@ err1: static void gfx_v8_0_free_microcode(struct amdgpu_device *adev) { - release_firmware(adev->gfx.pfp_fw); - adev->gfx.pfp_fw = NULL; - release_firmware(adev->gfx.me_fw); - adev->gfx.me_fw = NULL; - release_firmware(adev->gfx.ce_fw); - adev->gfx.ce_fw = NULL; - release_firmware(adev->gfx.rlc_fw); - adev->gfx.rlc_fw = NULL; - release_firmware(adev->gfx.mec_fw); - adev->gfx.mec_fw = NULL; + amdgpu_ucode_release(&adev->gfx.pfp_fw); + amdgpu_ucode_release(&adev->gfx.me_fw); + amdgpu_ucode_release(&adev->gfx.ce_fw); + amdgpu_ucode_release(&adev->gfx.rlc_fw); + amdgpu_ucode_release(&adev->gfx.mec_fw); if ((adev->asic_type != CHIP_STONEY) && (adev->asic_type != CHIP_TOPAZ)) - release_firmware(adev->gfx.mec2_fw); - adev->gfx.mec2_fw = NULL; + amdgpu_ucode_release(&adev->gfx.mec2_fw); kfree(adev->gfx.rlc.register_list_format); } @@ -989,40 +983,34 @@ static int gfx_v8_0_init_microcode(struct amdgpu_device *adev) if (adev->asic_type >= CHIP_POLARIS10 && adev->asic_type <= CHIP_POLARIS12) { snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_pfp_2.bin", chip_name); - err = request_firmware(&adev->gfx.pfp_fw, fw_name, adev->dev); - if (err == -ENOENT) { + err = amdgpu_ucode_request(adev, &adev->gfx.pfp_fw, fw_name); + if (err == -ENODEV) { snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_pfp.bin", chip_name); - err = request_firmware(&adev->gfx.pfp_fw, fw_name, adev->dev); + err = amdgpu_ucode_request(adev, &adev->gfx.pfp_fw, fw_name); } } else { snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_pfp.bin", chip_name); - err = request_firmware(&adev->gfx.pfp_fw, fw_name, adev->dev); + err = amdgpu_ucode_request(adev, &adev->gfx.pfp_fw, fw_name); } if (err) goto out; - err = amdgpu_ucode_validate(adev->gfx.pfp_fw); - if (err) - goto out; cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.pfp_fw->data; adev->gfx.pfp_fw_version = le32_to_cpu(cp_hdr->header.ucode_version); adev->gfx.pfp_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version); if (adev->asic_type >= CHIP_POLARIS10 && adev->asic_type <= CHIP_POLARIS12) { snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me_2.bin", chip_name); - err = request_firmware(&adev->gfx.me_fw, fw_name, adev->dev); - if (err == -ENOENT) { + err = amdgpu_ucode_request(adev, &adev->gfx.me_fw, fw_name); + if (err == -ENODEV) { snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me.bin", chip_name); - err = request_firmware(&adev->gfx.me_fw, fw_name, adev->dev); + err = amdgpu_ucode_request(adev, &adev->gfx.me_fw, fw_name); } } else { snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me.bin", chip_name); - err = request_firmware(&adev->gfx.me_fw, fw_name, adev->dev); + err = amdgpu_ucode_request(adev, &adev->gfx.me_fw, fw_name); } if (err) goto out; - err = amdgpu_ucode_validate(adev->gfx.me_fw); - if (err) - goto out; cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.me_fw->data; adev->gfx.me_fw_version = le32_to_cpu(cp_hdr->header.ucode_version); @@ -1030,20 +1018,17 @@ static int gfx_v8_0_init_microcode(struct amdgpu_device *adev) if (adev->asic_type >= CHIP_POLARIS10 && adev->asic_type <= CHIP_POLARIS12) { snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce_2.bin", chip_name); - err = request_firmware(&adev->gfx.ce_fw, fw_name, adev->dev); - if (err == -ENOENT) { + err = amdgpu_ucode_request(adev, &adev->gfx.ce_fw, fw_name); + if (err == -ENODEV) { snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce.bin", chip_name); - err = request_firmware(&adev->gfx.ce_fw, fw_name, adev->dev); + err = amdgpu_ucode_request(adev, &adev->gfx.ce_fw, fw_name); } } else { snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce.bin", chip_name); - err = request_firmware(&adev->gfx.ce_fw, fw_name, adev->dev); + err = amdgpu_ucode_request(adev, &adev->gfx.ce_fw, fw_name); } if (err) goto out; - err = amdgpu_ucode_validate(adev->gfx.ce_fw); - if (err) - goto out; cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.ce_fw->data; adev->gfx.ce_fw_version = le32_to_cpu(cp_hdr->header.ucode_version); adev->gfx.ce_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version); @@ -1060,10 +1045,9 @@ static int gfx_v8_0_init_microcode(struct amdgpu_device *adev) adev->virt.chained_ib_support = false; snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", chip_name); - err = request_firmware(&adev->gfx.rlc_fw, fw_name, adev->dev); + err = amdgpu_ucode_request(adev, &adev->gfx.rlc_fw, fw_name); if (err) goto out; - err = amdgpu_ucode_validate(adev->gfx.rlc_fw); rlc_hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data; adev->gfx.rlc_fw_version = le32_to_cpu(rlc_hdr->header.ucode_version); adev->gfx.rlc_feature_version = le32_to_cpu(rlc_hdr->ucode_feature_version); @@ -1110,20 +1094,17 @@ static int gfx_v8_0_init_microcode(struct amdgpu_device *adev) if (adev->asic_type >= CHIP_POLARIS10 && adev->asic_type <= CHIP_POLARIS12) { snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec_2.bin", chip_name); - err = request_firmware(&adev->gfx.mec_fw, fw_name, adev->dev); - if (err == -ENOENT) { + err = amdgpu_ucode_request(adev, &adev->gfx.mec_fw, fw_name); + if (err == -ENODEV) { snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec.bin", chip_name); - err = request_firmware(&adev->gfx.mec_fw, fw_name, adev->dev); + err = amdgpu_ucode_request(adev, &adev->gfx.mec_fw, fw_name); } } else { snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec.bin", chip_name); - err = request_firmware(&adev->gfx.mec_fw, fw_name, adev->dev); + err = amdgpu_ucode_request(adev, &adev->gfx.mec_fw, fw_name); } if (err) goto out; - err = amdgpu_ucode_validate(adev->gfx.mec_fw); - if (err) - goto out; cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec_fw->data; adev->gfx.mec_fw_version = le32_to_cpu(cp_hdr->header.ucode_version); adev->gfx.mec_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version); @@ -1132,19 +1113,16 @@ static int gfx_v8_0_init_microcode(struct amdgpu_device *adev) (adev->asic_type != CHIP_TOPAZ)) { if (adev->asic_type >= CHIP_POLARIS10 && adev->asic_type <= CHIP_POLARIS12) { snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec2_2.bin", chip_name); - err = request_firmware(&adev->gfx.mec2_fw, fw_name, adev->dev); - if (err == -ENOENT) { + err = amdgpu_ucode_request(adev, &adev->gfx.mec2_fw, fw_name); + if (err == -ENODEV) { snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec2.bin", chip_name); - err = request_firmware(&adev->gfx.mec2_fw, fw_name, adev->dev); + err = amdgpu_ucode_request(adev, &adev->gfx.mec2_fw, fw_name); } } else { snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec2.bin", chip_name); - err = request_firmware(&adev->gfx.mec2_fw, fw_name, adev->dev); + err = amdgpu_ucode_request(adev, &adev->gfx.mec2_fw, fw_name); } if (!err) { - err = amdgpu_ucode_validate(adev->gfx.mec2_fw); - if (err) - goto out; cp_hdr = (const struct gfx_firmware_header_v1_0 *) adev->gfx.mec2_fw->data; adev->gfx.mec2_fw_version = @@ -1219,18 +1197,12 @@ out: dev_err(adev->dev, "gfx8: Failed to load firmware \"%s\"\n", fw_name); - release_firmware(adev->gfx.pfp_fw); - adev->gfx.pfp_fw = NULL; - release_firmware(adev->gfx.me_fw); - adev->gfx.me_fw = NULL; - release_firmware(adev->gfx.ce_fw); - adev->gfx.ce_fw = NULL; - release_firmware(adev->gfx.rlc_fw); - adev->gfx.rlc_fw = NULL; - release_firmware(adev->gfx.mec_fw); - adev->gfx.mec_fw = NULL; - release_firmware(adev->gfx.mec2_fw); - adev->gfx.mec2_fw = NULL; + amdgpu_ucode_release(&adev->gfx.pfp_fw); + amdgpu_ucode_release(&adev->gfx.me_fw); + amdgpu_ucode_release(&adev->gfx.ce_fw); + amdgpu_ucode_release(&adev->gfx.rlc_fw); + amdgpu_ucode_release(&adev->gfx.mec_fw); + amdgpu_ucode_release(&adev->gfx.mec2_fw); } return err; } @@ -1340,7 +1312,8 @@ static int gfx_v8_0_mec_init(struct amdgpu_device *adev) mec_hpd_size = adev->gfx.num_compute_rings * GFX8_MEC_HPD_SIZE; if (mec_hpd_size) { r = amdgpu_bo_create_reserved(adev, mec_hpd_size, PAGE_SIZE, - AMDGPU_GEM_DOMAIN_VRAM, + AMDGPU_GEM_DOMAIN_VRAM | + AMDGPU_GEM_DOMAIN_GTT, &adev->gfx.mec.hpd_eop_obj, &adev->gfx.mec.hpd_eop_gpu_addr, (void **)&hpd); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index f202b45c413c..ae09fc1cfe6b 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -1078,18 +1078,12 @@ err1: static void gfx_v9_0_free_microcode(struct amdgpu_device *adev) { - release_firmware(adev->gfx.pfp_fw); - adev->gfx.pfp_fw = NULL; - release_firmware(adev->gfx.me_fw); - adev->gfx.me_fw = NULL; - release_firmware(adev->gfx.ce_fw); - adev->gfx.ce_fw = NULL; - release_firmware(adev->gfx.rlc_fw); - adev->gfx.rlc_fw = NULL; - release_firmware(adev->gfx.mec_fw); - adev->gfx.mec_fw = NULL; - release_firmware(adev->gfx.mec2_fw); - adev->gfx.mec2_fw = NULL; + amdgpu_ucode_release(&adev->gfx.pfp_fw); + amdgpu_ucode_release(&adev->gfx.me_fw); + amdgpu_ucode_release(&adev->gfx.ce_fw); + amdgpu_ucode_release(&adev->gfx.rlc_fw); + amdgpu_ucode_release(&adev->gfx.mec_fw); + amdgpu_ucode_release(&adev->gfx.mec2_fw); kfree(adev->gfx.rlc.register_list_format); } @@ -1251,55 +1245,40 @@ static void gfx_v9_0_check_if_need_gfxoff(struct amdgpu_device *adev) } static int gfx_v9_0_init_cp_gfx_microcode(struct amdgpu_device *adev, - const char *chip_name) + char *chip_name) { char fw_name[30]; int err; snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_pfp.bin", chip_name); - err = request_firmware(&adev->gfx.pfp_fw, fw_name, adev->dev); - if (err) - goto out; - err = amdgpu_ucode_validate(adev->gfx.pfp_fw); + err = amdgpu_ucode_request(adev, &adev->gfx.pfp_fw, fw_name); if (err) goto out; amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_PFP); snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me.bin", chip_name); - err = request_firmware(&adev->gfx.me_fw, fw_name, adev->dev); - if (err) - goto out; - err = amdgpu_ucode_validate(adev->gfx.me_fw); + err = amdgpu_ucode_request(adev, &adev->gfx.me_fw, fw_name); if (err) goto out; amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_ME); snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce.bin", chip_name); - err = request_firmware(&adev->gfx.ce_fw, fw_name, adev->dev); - if (err) - goto out; - err = amdgpu_ucode_validate(adev->gfx.ce_fw); + err = amdgpu_ucode_request(adev, &adev->gfx.ce_fw, fw_name); if (err) goto out; amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_CE); out: if (err) { - dev_err(adev->dev, - "gfx9: Failed to init firmware \"%s\"\n", - fw_name); - release_firmware(adev->gfx.pfp_fw); - adev->gfx.pfp_fw = NULL; - release_firmware(adev->gfx.me_fw); - adev->gfx.me_fw = NULL; - release_firmware(adev->gfx.ce_fw); - adev->gfx.ce_fw = NULL; + amdgpu_ucode_release(&adev->gfx.pfp_fw); + amdgpu_ucode_release(&adev->gfx.me_fw); + amdgpu_ucode_release(&adev->gfx.ce_fw); } return err; } static int gfx_v9_0_init_rlc_microcode(struct amdgpu_device *adev, - const char *chip_name) + char *chip_name) { char fw_name[30]; int err; @@ -1328,10 +1307,7 @@ static int gfx_v9_0_init_rlc_microcode(struct amdgpu_device *adev, snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_kicker_rlc.bin", chip_name); else snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", chip_name); - err = request_firmware(&adev->gfx.rlc_fw, fw_name, adev->dev); - if (err) - goto out; - err = amdgpu_ucode_validate(adev->gfx.rlc_fw); + err = amdgpu_ucode_request(adev, &adev->gfx.rlc_fw, fw_name); if (err) goto out; rlc_hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data; @@ -1340,13 +1316,9 @@ static int gfx_v9_0_init_rlc_microcode(struct amdgpu_device *adev, version_minor = le16_to_cpu(rlc_hdr->header.header_version_minor); err = amdgpu_gfx_rlc_init_microcode(adev, version_major, version_minor); out: - if (err) { - dev_err(adev->dev, - "gfx9: Failed to init firmware \"%s\"\n", - fw_name); - release_firmware(adev->gfx.rlc_fw); - adev->gfx.rlc_fw = NULL; - } + if (err) + amdgpu_ucode_release(&adev->gfx.rlc_fw); + return err; } @@ -1361,7 +1333,7 @@ static bool gfx_v9_0_load_mec2_fw_bin_support(struct amdgpu_device *adev) } static int gfx_v9_0_init_cp_compute_microcode(struct amdgpu_device *adev, - const char *chip_name) + char *chip_name) { char fw_name[30]; int err; @@ -1371,10 +1343,7 @@ static int gfx_v9_0_init_cp_compute_microcode(struct amdgpu_device *adev, else snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec.bin", chip_name); - err = request_firmware(&adev->gfx.mec_fw, fw_name, adev->dev); - if (err) - goto out; - err = amdgpu_ucode_validate(adev->gfx.mec_fw); + err = amdgpu_ucode_request(adev, &adev->gfx.mec_fw, fw_name); if (err) goto out; amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC1); @@ -1386,91 +1355,49 @@ static int gfx_v9_0_init_cp_compute_microcode(struct amdgpu_device *adev, else snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec2.bin", chip_name); - err = request_firmware(&adev->gfx.mec2_fw, fw_name, adev->dev); + /* ignore failures to load */ + err = amdgpu_ucode_request(adev, &adev->gfx.mec2_fw, fw_name); if (!err) { - err = amdgpu_ucode_validate(adev->gfx.mec2_fw); - if (err) - goto out; amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC2); amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC2_JT); } else { err = 0; - adev->gfx.mec2_fw = NULL; + amdgpu_ucode_release(&adev->gfx.mec2_fw); } } else { adev->gfx.mec2_fw_version = adev->gfx.mec_fw_version; adev->gfx.mec2_feature_version = adev->gfx.mec_feature_version; } -out: gfx_v9_0_check_if_need_gfxoff(adev); gfx_v9_0_check_fw_write_wait(adev); - if (err) { - dev_err(adev->dev, - "gfx9: Failed to init firmware \"%s\"\n", - fw_name); - release_firmware(adev->gfx.mec_fw); - adev->gfx.mec_fw = NULL; - release_firmware(adev->gfx.mec2_fw); - adev->gfx.mec2_fw = NULL; - } + +out: + if (err) + amdgpu_ucode_release(&adev->gfx.mec_fw); return err; } static int gfx_v9_0_init_microcode(struct amdgpu_device *adev) { - const char *chip_name; + char ucode_prefix[30]; int r; DRM_DEBUG("\n"); - - switch (adev->ip_versions[GC_HWIP][0]) { - case IP_VERSION(9, 0, 1): - chip_name = "vega10"; - break; - case IP_VERSION(9, 2, 1): - chip_name = "vega12"; - break; - case IP_VERSION(9, 4, 0): - chip_name = "vega20"; - break; - case IP_VERSION(9, 2, 2): - case IP_VERSION(9, 1, 0): - if (adev->apu_flags & AMD_APU_IS_RAVEN2) - chip_name = "raven2"; - else if (adev->apu_flags & AMD_APU_IS_PICASSO) - chip_name = "picasso"; - else - chip_name = "raven"; - break; - case IP_VERSION(9, 4, 1): - chip_name = "arcturus"; - break; - case IP_VERSION(9, 3, 0): - if (adev->apu_flags & AMD_APU_IS_RENOIR) - chip_name = "renoir"; - else - chip_name = "green_sardine"; - break; - case IP_VERSION(9, 4, 2): - chip_name = "aldebaran"; - break; - default: - BUG(); - } + amdgpu_ucode_ip_version_decode(adev, GC_HWIP, ucode_prefix, sizeof(ucode_prefix)); /* No CPG in Arcturus */ if (adev->gfx.num_gfx_rings) { - r = gfx_v9_0_init_cp_gfx_microcode(adev, chip_name); + r = gfx_v9_0_init_cp_gfx_microcode(adev, ucode_prefix); if (r) return r; } - r = gfx_v9_0_init_rlc_microcode(adev, chip_name); + r = gfx_v9_0_init_rlc_microcode(adev, ucode_prefix); if (r) return r; - r = gfx_v9_0_init_cp_compute_microcode(adev, chip_name); + r = gfx_v9_0_init_cp_compute_microcode(adev, ucode_prefix); if (r) return r; @@ -1783,7 +1710,8 @@ static int gfx_v9_0_mec_init(struct amdgpu_device *adev) mec_hpd_size = adev->gfx.num_compute_rings * GFX9_MEC_HPD_SIZE; if (mec_hpd_size) { r = amdgpu_bo_create_reserved(adev, mec_hpd_size, PAGE_SIZE, - AMDGPU_GEM_DOMAIN_VRAM, + AMDGPU_GEM_DOMAIN_VRAM | + AMDGPU_GEM_DOMAIN_GTT, &adev->gfx.mec.hpd_eop_obj, &adev->gfx.mec.hpd_eop_gpu_addr, (void **)&hpd); @@ -2008,27 +1936,6 @@ static int gfx_v9_0_gpu_early_init(struct amdgpu_device *adev) break; } - if (adev->gfx.ras) { - err = amdgpu_ras_register_ras_block(adev, &adev->gfx.ras->ras_block); - if (err) { - DRM_ERROR("Failed to register gfx ras block!\n"); - return err; - } - - strcpy(adev->gfx.ras->ras_block.ras_comm.name, "gfx"); - adev->gfx.ras->ras_block.ras_comm.block = AMDGPU_RAS_BLOCK__GFX; - adev->gfx.ras->ras_block.ras_comm.type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE; - adev->gfx.ras_if = &adev->gfx.ras->ras_block.ras_comm; - - /* If not define special ras_late_init function, use gfx default ras_late_init */ - if (!adev->gfx.ras->ras_block.ras_late_init) - adev->gfx.ras->ras_block.ras_late_init = amdgpu_gfx_ras_late_init; - - /* If not defined special ras_cb function, use default ras_cb */ - if (!adev->gfx.ras->ras_block.ras_cb) - adev->gfx.ras->ras_block.ras_cb = amdgpu_gfx_process_ras_data_cb; - } - adev->gfx.config.gb_addr_config = gb_addr_config; adev->gfx.config.gb_addr_config_fields.num_pipes = 1 << @@ -2158,12 +2065,6 @@ static int gfx_v9_0_sw_init(void *handle) adev->gfx.gfx_current_status = AMDGPU_GFX_NORMAL_MODE; - r = gfx_v9_0_init_microcode(adev); - if (r) { - DRM_ERROR("Failed to load gfx firmware!\n"); - return r; - } - if (adev->gfx.rlc.funcs) { if (adev->gfx.rlc.funcs->init) { r = adev->gfx.rlc.funcs->init(adev); @@ -2276,6 +2177,11 @@ static int gfx_v9_0_sw_init(void *handle) if (r) return r; + if (amdgpu_gfx_ras_sw_init(adev)) { + dev_err(adev->dev, "Failed to initialize gfx ras block!\n"); + return -EINVAL; + } + return 0; } @@ -4605,7 +4511,7 @@ static int gfx_v9_0_early_init(void *handle) /* init rlcg reg access ctrl */ gfx_v9_0_init_rlcg_reg_access_ctrl(adev); - return 0; + return gfx_v9_0_init_microcode(adev); } static int gfx_v9_0_ecc_late_init(void *handle) @@ -6877,7 +6783,6 @@ static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_gfx = { .emit_gds_switch = gfx_v9_0_ring_emit_gds_switch, .emit_hdp_flush = gfx_v9_0_ring_emit_hdp_flush, .test_ring = gfx_v9_0_ring_test_ring, - .test_ib = gfx_v9_0_ring_test_ib, .insert_nop = amdgpu_ring_insert_nop, .pad_ib = amdgpu_ring_generic_pad_ib, .emit_switch_buffer = gfx_v9_ring_emit_sb, diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c index ec4d5e15b766..ab2325f6c7ac 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c @@ -120,7 +120,7 @@ static void gfxhub_v1_0_init_system_aperture_regs(struct amdgpu_device *adev) max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18); /* Set default page address. */ - value = amdgpu_gmc_vram_mc2pa(adev, adev->vram_scratch.gpu_addr); + value = amdgpu_gmc_vram_mc2pa(adev, adev->mem_scratch.gpu_addr); WREG32_SOC15(GC, 0, mmMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB, (u32)(value >> 12)); WREG32_SOC15(GC, 0, mmMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB, diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c index 34513e8e1519..9b3a02527318 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c @@ -165,7 +165,7 @@ static void gfxhub_v2_0_init_system_aperture_regs(struct amdgpu_device *adev) max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18); /* Set default page address. */ - value = amdgpu_gmc_vram_mc2pa(adev, adev->vram_scratch.gpu_addr); + value = amdgpu_gmc_vram_mc2pa(adev, adev->mem_scratch.gpu_addr); WREG32_SOC15(GC, 0, mmGCMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB, (u32)(value >> 12)); WREG32_SOC15(GC, 0, mmGCMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB, diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c index 3f8676d23a5e..4aacbbec31e2 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c @@ -167,7 +167,7 @@ static void gfxhub_v2_1_init_system_aperture_regs(struct amdgpu_device *adev) max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18); /* Set default page address. */ - value = amdgpu_gmc_vram_mc2pa(adev, adev->vram_scratch.gpu_addr); + value = amdgpu_gmc_vram_mc2pa(adev, adev->mem_scratch.gpu_addr); WREG32_SOC15(GC, 0, mmGCMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB, (u32)(value >> 12)); WREG32_SOC15(GC, 0, mmGCMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB, diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v3_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v3_0.c index 0e13370c2057..be0d0f47415e 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v3_0.c @@ -151,19 +151,20 @@ static void gfxhub_v3_0_init_system_aperture_regs(struct amdgpu_device *adev) { uint64_t value; - /* Disable AGP. */ + /* Program the AGP BAR */ WREG32_SOC15(GC, 0, regGCMC_VM_AGP_BASE, 0); - WREG32_SOC15(GC, 0, regGCMC_VM_AGP_TOP, 0); - WREG32_SOC15(GC, 0, regGCMC_VM_AGP_BOT, 0x00FFFFFF); + WREG32_SOC15(GC, 0, regGCMC_VM_AGP_BOT, adev->gmc.agp_start >> 24); + WREG32_SOC15(GC, 0, regGCMC_VM_AGP_TOP, adev->gmc.agp_end >> 24); + /* Program the system aperture low logical page number. */ WREG32_SOC15(GC, 0, regGCMC_VM_SYSTEM_APERTURE_LOW_ADDR, - adev->gmc.vram_start >> 18); + min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18); WREG32_SOC15(GC, 0, regGCMC_VM_SYSTEM_APERTURE_HIGH_ADDR, - adev->gmc.vram_end >> 18); + max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18); /* Set default page address. */ - value = adev->vram_scratch.gpu_addr - adev->gmc.vram_start + value = adev->mem_scratch.gpu_addr - adev->gmc.vram_start + adev->vm_manager.vram_base_offset; WREG32_SOC15(GC, 0, regGCMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB, (u32)(value >> 12)); diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v3_0_3.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v3_0_3.c index 080ff11ca305..6e0bd628c889 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v3_0_3.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v3_0_3.c @@ -159,17 +159,17 @@ static void gfxhub_v3_0_3_init_system_aperture_regs(struct amdgpu_device *adev) /* Disable AGP. */ WREG32_SOC15(GC, 0, regGCMC_VM_AGP_BASE, 0); - WREG32_SOC15(GC, 0, regGCMC_VM_AGP_TOP, 0); - WREG32_SOC15(GC, 0, regGCMC_VM_AGP_BOT, 0x00FFFFFF); + WREG32_SOC15(GC, 0, regGCMC_VM_AGP_BOT, adev->gmc.agp_start >> 24); + WREG32_SOC15(GC, 0, regGCMC_VM_AGP_TOP, adev->gmc.agp_end >> 24); /* Program the system aperture low logical page number. */ WREG32_SOC15(GC, 0, regGCMC_VM_SYSTEM_APERTURE_LOW_ADDR, - adev->gmc.vram_start >> 18); + min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18); WREG32_SOC15(GC, 0, regGCMC_VM_SYSTEM_APERTURE_HIGH_ADDR, - adev->gmc.vram_end >> 18); + max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18); /* Set default page address. */ - value = adev->vram_scratch.gpu_addr - adev->gmc.vram_start + value = adev->mem_scratch.gpu_addr - adev->gmc.vram_start + adev->vm_manager.vram_base_offset; WREG32_SOC15(GC, 0, regGCMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB, (u32)(value >> 12)); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index 21e46817d82d..ab2556ca984e 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -78,13 +78,25 @@ gmc_v10_0_vm_fault_interrupt_state(struct amdgpu_device *adev, /* MM HUB */ amdgpu_gmc_set_vm_fault_masks(adev, AMDGPU_MMHUB_0, false); /* GFX HUB */ - amdgpu_gmc_set_vm_fault_masks(adev, AMDGPU_GFXHUB_0, false); + /* This works because this interrupt is only + * enabled at init/resume and disabled in + * fini/suspend, so the overall state doesn't + * change over the course of suspend/resume. + */ + if (!adev->in_s0ix) + amdgpu_gmc_set_vm_fault_masks(adev, AMDGPU_GFXHUB_0, false); break; case AMDGPU_IRQ_STATE_ENABLE: /* MM HUB */ amdgpu_gmc_set_vm_fault_masks(adev, AMDGPU_MMHUB_0, true); /* GFX HUB */ - amdgpu_gmc_set_vm_fault_masks(adev, AMDGPU_GFXHUB_0, true); + /* This works because this interrupt is only + * enabled at init/resume and disabled in + * fini/suspend, so the overall state doesn't + * change over the course of suspend/resume. + */ + if (!adev->in_s0ix) + amdgpu_gmc_set_vm_fault_masks(adev, AMDGPU_GFXHUB_0, true); break; default: break; @@ -680,6 +692,7 @@ static void gmc_v10_0_set_umc_funcs(struct amdgpu_device *adev) adev->umc.channel_inst_num = UMC_V8_7_CHANNEL_INSTANCE_NUM; adev->umc.umc_inst_num = UMC_V8_7_UMC_INSTANCE_NUM; adev->umc.channel_offs = UMC_V8_7_PER_CHANNEL_OFFSET_SIENNA; + adev->umc.retire_unit = 1; adev->umc.channel_idx_tbl = &umc_v8_7_channel_idx_tbl[0][0]; adev->umc.ras = &umc_v8_7_ras; break; @@ -835,10 +848,7 @@ static int gmc_v10_0_mc_init(struct amdgpu_device *adev) } #endif - /* In case the PCI BAR is larger than the actual amount of vram */ adev->gmc.visible_vram_size = adev->gmc.aper_size; - if (adev->gmc.visible_vram_size > adev->gmc.real_vram_size) - adev->gmc.visible_vram_size = adev->gmc.real_vram_size; /* set the gart size */ if (amdgpu_gart_size == -1) { @@ -1061,9 +1071,12 @@ static int gmc_v10_0_gart_enable(struct amdgpu_device *adev) } amdgpu_gtt_mgr_recover(&adev->mman.gtt_mgr); - r = adev->gfxhub.funcs->gart_enable(adev); - if (r) - return r; + + if (!adev->in_s0ix) { + r = adev->gfxhub.funcs->gart_enable(adev); + if (r) + return r; + } r = adev->mmhub.funcs->gart_enable(adev); if (r) @@ -1077,10 +1090,12 @@ static int gmc_v10_0_gart_enable(struct amdgpu_device *adev) value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ? false : true; - adev->gfxhub.funcs->set_fault_enable_default(adev, value); + if (!adev->in_s0ix) + adev->gfxhub.funcs->set_fault_enable_default(adev, value); adev->mmhub.funcs->set_fault_enable_default(adev, value); gmc_v10_0_flush_gpu_tlb(adev, 0, AMDGPU_MMHUB_0, 0); - gmc_v10_0_flush_gpu_tlb(adev, 0, AMDGPU_GFXHUB_0, 0); + if (!adev->in_s0ix) + gmc_v10_0_flush_gpu_tlb(adev, 0, AMDGPU_GFXHUB_0, 0); DRM_INFO("PCIE GART of %uM enabled (table at 0x%016llX).\n", (unsigned)(adev->gmc.gart_size >> 20), @@ -1101,7 +1116,7 @@ static int gmc_v10_0_hw_init(void *handle) * harvestable groups in gc_utcl2 need to be programmed before any GFX block * register setup within GMC, or else system hang when harvesting SA. */ - if (adev->gfxhub.funcs && adev->gfxhub.funcs->utcl2_harvest) + if (!adev->in_s0ix && adev->gfxhub.funcs && adev->gfxhub.funcs->utcl2_harvest) adev->gfxhub.funcs->utcl2_harvest(adev); r = gmc_v10_0_gart_enable(adev); @@ -1129,7 +1144,8 @@ static int gmc_v10_0_hw_init(void *handle) */ static void gmc_v10_0_gart_disable(struct amdgpu_device *adev) { - adev->gfxhub.funcs->gart_disable(adev); + if (!adev->in_s0ix) + adev->gfxhub.funcs->gart_disable(adev); adev->mmhub.funcs->gart_disable(adev); } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c index 4326078689cd..af7b3ba1ca00 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c @@ -64,13 +64,25 @@ gmc_v11_0_vm_fault_interrupt_state(struct amdgpu_device *adev, /* MM HUB */ amdgpu_gmc_set_vm_fault_masks(adev, AMDGPU_MMHUB_0, false); /* GFX HUB */ - amdgpu_gmc_set_vm_fault_masks(adev, AMDGPU_GFXHUB_0, false); + /* This works because this interrupt is only + * enabled at init/resume and disabled in + * fini/suspend, so the overall state doesn't + * change over the course of suspend/resume. + */ + if (!adev->in_s0ix) + amdgpu_gmc_set_vm_fault_masks(adev, AMDGPU_GFXHUB_0, false); break; case AMDGPU_IRQ_STATE_ENABLE: /* MM HUB */ amdgpu_gmc_set_vm_fault_masks(adev, AMDGPU_MMHUB_0, true); /* GFX HUB */ - amdgpu_gmc_set_vm_fault_masks(adev, AMDGPU_GFXHUB_0, true); + /* This works because this interrupt is only + * enabled at init/resume and disabled in + * fini/suspend, so the overall state doesn't + * change over the course of suspend/resume. + */ + if (!adev->in_s0ix) + amdgpu_gmc_set_vm_fault_masks(adev, AMDGPU_GFXHUB_0, true); break; default: break; @@ -555,9 +567,9 @@ static void gmc_v11_0_set_umc_funcs(struct amdgpu_device *adev) case IP_VERSION(8, 10, 0): adev->umc.channel_inst_num = UMC_V8_10_CHANNEL_INSTANCE_NUM; adev->umc.umc_inst_num = UMC_V8_10_UMC_INSTANCE_NUM; - adev->umc.node_inst_num = adev->gmc.num_umc; adev->umc.max_ras_err_cnt_per_query = UMC_V8_10_TOTAL_CHANNEL_NUM(adev); adev->umc.channel_offs = UMC_V8_10_PER_CHANNEL_OFFSET; + adev->umc.retire_unit = UMC_V8_10_NA_COL_2BITS_POWER_OF_2_NUM; if (adev->umc.node_inst_num == 4) adev->umc.channel_idx_tbl = &umc_v8_10_channel_idx_tbl_ext0[0][0][0]; else @@ -661,6 +673,7 @@ static void gmc_v11_0_vram_gtt_location(struct amdgpu_device *adev, amdgpu_gmc_vram_location(adev, &adev->gmc, base); amdgpu_gmc_gart_location(adev, mc); + amdgpu_gmc_agp_location(adev, mc); /* base offset of vram pages */ if (amdgpu_sriov_vf(adev)) diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c index ec291d28edff..b7dad4e67813 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c @@ -131,19 +131,12 @@ static int gmc_v6_0_init_microcode(struct amdgpu_device *adev) snprintf(fw_name, sizeof(fw_name), "amdgpu/si58_mc.bin"); else snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mc.bin", chip_name); - err = request_firmware(&adev->gmc.fw, fw_name, adev->dev); - if (err) - goto out; - - err = amdgpu_ucode_validate(adev->gmc.fw); - -out: + err = amdgpu_ucode_request(adev, &adev->gmc.fw, fw_name); if (err) { dev_err(adev->dev, "si_mc: Failed to load firmware \"%s\"\n", fw_name); - release_firmware(adev->gmc.fw); - adev->gmc.fw = NULL; + amdgpu_ucode_release(&adev->gmc.fw); } return err; } @@ -258,7 +251,7 @@ static void gmc_v6_0_mc_program(struct amdgpu_device *adev) WREG32(mmMC_VM_SYSTEM_APERTURE_HIGH_ADDR, adev->gmc.vram_end >> 12); WREG32(mmMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR, - adev->vram_scratch.gpu_addr >> 12); + adev->mem_scratch.gpu_addr >> 12); WREG32(mmMC_VM_AGP_BASE, 0); WREG32(mmMC_VM_AGP_TOP, 0x0FFFFFFF); WREG32(mmMC_VM_AGP_BOT, 0x0FFFFFFF); @@ -894,8 +887,7 @@ static int gmc_v6_0_sw_fini(void *handle) amdgpu_vm_manager_fini(adev); amdgpu_gart_table_vram_free(adev); amdgpu_bo_fini(adev); - release_firmware(adev->gmc.fw); - adev->gmc.fw = NULL; + amdgpu_ucode_release(&adev->gmc.fw); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c index 979da6f510e8..402960b0174e 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c @@ -156,16 +156,10 @@ static int gmc_v7_0_init_microcode(struct amdgpu_device *adev) snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mc.bin", chip_name); - err = request_firmware(&adev->gmc.fw, fw_name, adev->dev); - if (err) - goto out; - err = amdgpu_ucode_validate(adev->gmc.fw); - -out: + err = amdgpu_ucode_request(adev, &adev->gmc.fw, fw_name); if (err) { pr_err("cik_mc: Failed to load firmware \"%s\"\n", fw_name); - release_firmware(adev->gmc.fw); - adev->gmc.fw = NULL; + amdgpu_ucode_release(&adev->gmc.fw); } return err; } @@ -292,7 +286,7 @@ static void gmc_v7_0_mc_program(struct amdgpu_device *adev) WREG32(mmMC_VM_SYSTEM_APERTURE_HIGH_ADDR, adev->gmc.vram_end >> 12); WREG32(mmMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR, - adev->vram_scratch.gpu_addr >> 12); + adev->mem_scratch.gpu_addr >> 12); WREG32(mmMC_VM_AGP_BASE, 0); WREG32(mmMC_VM_AGP_TOP, 0x0FFFFFFF); WREG32(mmMC_VM_AGP_BOT, 0x0FFFFFFF); @@ -389,10 +383,7 @@ static int gmc_v7_0_mc_init(struct amdgpu_device *adev) } #endif - /* In case the PCI BAR is larger than the actual amount of vram */ adev->gmc.visible_vram_size = adev->gmc.aper_size; - if (adev->gmc.visible_vram_size > adev->gmc.real_vram_size) - adev->gmc.visible_vram_size = adev->gmc.real_vram_size; /* set the gart size */ if (amdgpu_gart_size == -1) { @@ -1081,8 +1072,7 @@ static int gmc_v7_0_sw_fini(void *handle) kfree(adev->gmc.vm_fault_info); amdgpu_gart_table_vram_free(adev); amdgpu_bo_fini(adev); - release_firmware(adev->gmc.fw); - adev->gmc.fw = NULL; + amdgpu_ucode_release(&adev->gmc.fw); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index 382dde1ce74c..504c1b34dab7 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -264,16 +264,10 @@ static int gmc_v8_0_init_microcode(struct amdgpu_device *adev) } snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mc.bin", chip_name); - err = request_firmware(&adev->gmc.fw, fw_name, adev->dev); - if (err) - goto out; - err = amdgpu_ucode_validate(adev->gmc.fw); - -out: + err = amdgpu_ucode_request(adev, &adev->gmc.fw, fw_name); if (err) { pr_err("mc: Failed to load firmware \"%s\"\n", fw_name); - release_firmware(adev->gmc.fw); - adev->gmc.fw = NULL; + amdgpu_ucode_release(&adev->gmc.fw); } return err; } @@ -474,7 +468,7 @@ static void gmc_v8_0_mc_program(struct amdgpu_device *adev) WREG32(mmMC_VM_SYSTEM_APERTURE_HIGH_ADDR, adev->gmc.vram_end >> 12); WREG32(mmMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR, - adev->vram_scratch.gpu_addr >> 12); + adev->mem_scratch.gpu_addr >> 12); if (amdgpu_sriov_vf(adev)) { tmp = ((adev->gmc.vram_end >> 24) & 0xFFFF) << 16; @@ -587,10 +581,7 @@ static int gmc_v8_0_mc_init(struct amdgpu_device *adev) } #endif - /* In case the PCI BAR is larger than the actual amount of vram */ adev->gmc.visible_vram_size = adev->gmc.aper_size; - if (adev->gmc.visible_vram_size > adev->gmc.real_vram_size) - adev->gmc.visible_vram_size = adev->gmc.real_vram_size; /* set the gart size */ if (amdgpu_gart_size == -1) { @@ -1203,8 +1194,7 @@ static int gmc_v8_0_sw_fini(void *handle) kfree(adev->gmc.vm_fault_info); amdgpu_gart_table_vram_free(adev); amdgpu_bo_fini(adev); - release_firmware(adev->gmc.fw); - adev->gmc.fw = NULL; + amdgpu_ucode_release(&adev->gmc.fw); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 08d6cf79fb15..b06170c00dfc 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -484,6 +484,14 @@ static int gmc_v9_0_vm_fault_interrupt_state(struct amdgpu_device *adev, for (i = 0; i < 16; i++) { reg = hub->vm_context0_cntl + i; + /* This works because this interrupt is only + * enabled at init/resume and disabled in + * fini/suspend, so the overall state doesn't + * change over the course of suspend/resume. + */ + if (adev->in_s0ix && (j == AMDGPU_GFXHUB_0)) + continue; + if (j == AMDGPU_GFXHUB_0) tmp = RREG32_SOC15_IP(GC, reg); else @@ -504,6 +512,14 @@ static int gmc_v9_0_vm_fault_interrupt_state(struct amdgpu_device *adev, for (i = 0; i < 16; i++) { reg = hub->vm_context0_cntl + i; + /* This works because this interrupt is only + * enabled at init/resume and disabled in + * fini/suspend, so the overall state doesn't + * change over the course of suspend/resume. + */ + if (adev->in_s0ix && (j == AMDGPU_GFXHUB_0)) + continue; + if (j == AMDGPU_GFXHUB_0) tmp = RREG32_SOC15_IP(GC, reg); else @@ -1272,6 +1288,7 @@ static void gmc_v9_0_set_umc_funcs(struct amdgpu_device *adev) adev->umc.channel_inst_num = UMC_V6_1_CHANNEL_INSTANCE_NUM; adev->umc.umc_inst_num = UMC_V6_1_UMC_INSTANCE_NUM; adev->umc.channel_offs = UMC_V6_1_PER_CHANNEL_OFFSET_VG20; + adev->umc.retire_unit = 1; adev->umc.channel_idx_tbl = &umc_v6_1_channel_idx_tbl[0][0]; adev->umc.ras = &umc_v6_1_ras; break; @@ -1280,6 +1297,7 @@ static void gmc_v9_0_set_umc_funcs(struct amdgpu_device *adev) adev->umc.channel_inst_num = UMC_V6_1_CHANNEL_INSTANCE_NUM; adev->umc.umc_inst_num = UMC_V6_1_UMC_INSTANCE_NUM; adev->umc.channel_offs = UMC_V6_1_PER_CHANNEL_OFFSET_ARCT; + adev->umc.retire_unit = 1; adev->umc.channel_idx_tbl = &umc_v6_1_channel_idx_tbl[0][0]; adev->umc.ras = &umc_v6_1_ras; break; @@ -1289,6 +1307,7 @@ static void gmc_v9_0_set_umc_funcs(struct amdgpu_device *adev) adev->umc.channel_inst_num = UMC_V6_7_CHANNEL_INSTANCE_NUM; adev->umc.umc_inst_num = UMC_V6_7_UMC_INSTANCE_NUM; adev->umc.channel_offs = UMC_V6_7_PER_CHANNEL_OFFSET; + adev->umc.retire_unit = (UMC_V6_7_NA_MAP_PA_NUM * 2); if (!adev->gmc.xgmi.connected_to_cpu) adev->umc.ras = &umc_v6_7_ras; if (1 & adev->smuio.funcs->get_die_id(adev)) @@ -1536,10 +1555,7 @@ static int gmc_v9_0_mc_init(struct amdgpu_device *adev) } #endif - /* In case the PCI BAR is larger than the actual amount of vram */ adev->gmc.visible_vram_size = adev->gmc.aper_size; - if (adev->gmc.visible_vram_size > adev->gmc.real_vram_size) - adev->gmc.visible_vram_size = adev->gmc.real_vram_size; /* set the gart size */ if (amdgpu_gart_size == -1) { @@ -1862,9 +1878,12 @@ static int gmc_v9_0_gart_enable(struct amdgpu_device *adev) } amdgpu_gtt_mgr_recover(&adev->mman.gtt_mgr); - r = adev->gfxhub.funcs->gart_enable(adev); - if (r) - return r; + + if (!adev->in_s0ix) { + r = adev->gfxhub.funcs->gart_enable(adev); + if (r) + return r; + } r = adev->mmhub.funcs->gart_enable(adev); if (r) @@ -1911,11 +1930,15 @@ static int gmc_v9_0_hw_init(void *handle) value = true; if (!amdgpu_sriov_vf(adev)) { - adev->gfxhub.funcs->set_fault_enable_default(adev, value); + if (!adev->in_s0ix) + adev->gfxhub.funcs->set_fault_enable_default(adev, value); adev->mmhub.funcs->set_fault_enable_default(adev, value); } - for (i = 0; i < adev->num_vmhubs; ++i) + for (i = 0; i < adev->num_vmhubs; ++i) { + if (adev->in_s0ix && (i == AMDGPU_GFXHUB_0)) + continue; gmc_v9_0_flush_gpu_tlb(adev, 0, i, 0); + } if (adev->umc.funcs && adev->umc.funcs->init_registers) adev->umc.funcs->init_registers(adev); @@ -1939,7 +1962,8 @@ static int gmc_v9_0_hw_init(void *handle) */ static void gmc_v9_0_gart_disable(struct amdgpu_device *adev) { - adev->gfxhub.funcs->gart_disable(adev); + if (!adev->in_s0ix) + adev->gfxhub.funcs->gart_disable(adev); adev->mmhub.funcs->gart_disable(adev); } diff --git a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c index 95548c512f4f..4ab90c7852c3 100644 --- a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c @@ -35,6 +35,7 @@ MODULE_FIRMWARE("amdgpu/gc_11_0_0_imu.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_1_imu.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_2_imu.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_3_imu.bin"); +MODULE_FIRMWARE("amdgpu/gc_11_0_4_imu.bin"); static int imu_v11_0_init_microcode(struct amdgpu_device *adev) { @@ -49,10 +50,7 @@ static int imu_v11_0_init_microcode(struct amdgpu_device *adev) amdgpu_ucode_ip_version_decode(adev, GC_HWIP, ucode_prefix, sizeof(ucode_prefix)); snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_imu.bin", ucode_prefix); - err = request_firmware(&adev->gfx.imu_fw, fw_name, adev->dev); - if (err) - goto out; - err = amdgpu_ucode_validate(adev->gfx.imu_fw); + err = amdgpu_ucode_request(adev, &adev->gfx.imu_fw, fw_name); if (err) goto out; imu_hdr = (const struct imu_firmware_header_v1_0 *)adev->gfx.imu_fw->data; @@ -77,7 +75,7 @@ out: dev_err(adev->dev, "gfx11: Failed to load firmware \"%s\"\n", fw_name); - release_firmware(adev->gfx.imu_fw); + amdgpu_ucode_release(&adev->gfx.imu_fw); } return err; diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c b/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c index 614394118a53..2e2062636d5f 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c @@ -379,89 +379,6 @@ static const struct amdgpu_mes_funcs mes_v10_1_funcs = { .resume_gang = mes_v10_1_resume_gang, }; -static int mes_v10_1_init_microcode(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) -{ - const char *chip_name; - char fw_name[30]; - int err; - const struct mes_firmware_header_v1_0 *mes_hdr; - struct amdgpu_firmware_info *info; - - switch (adev->ip_versions[GC_HWIP][0]) { - case IP_VERSION(10, 1, 10): - chip_name = "navi10"; - break; - case IP_VERSION(10, 3, 0): - chip_name = "sienna_cichlid"; - break; - default: - BUG(); - } - - if (pipe == AMDGPU_MES_SCHED_PIPE) - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mes.bin", - chip_name); - else - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mes1.bin", - chip_name); - - err = request_firmware(&adev->mes.fw[pipe], fw_name, adev->dev); - if (err) - return err; - - err = amdgpu_ucode_validate(adev->mes.fw[pipe]); - if (err) { - release_firmware(adev->mes.fw[pipe]); - adev->mes.fw[pipe] = NULL; - return err; - } - - mes_hdr = (const struct mes_firmware_header_v1_0 *) - adev->mes.fw[pipe]->data; - adev->mes.uc_start_addr[pipe] = - le32_to_cpu(mes_hdr->mes_uc_start_addr_lo) | - ((uint64_t)(le32_to_cpu(mes_hdr->mes_uc_start_addr_hi)) << 32); - adev->mes.data_start_addr[pipe] = - le32_to_cpu(mes_hdr->mes_data_start_addr_lo) | - ((uint64_t)(le32_to_cpu(mes_hdr->mes_data_start_addr_hi)) << 32); - - if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { - int ucode, ucode_data; - - if (pipe == AMDGPU_MES_SCHED_PIPE) { - ucode = AMDGPU_UCODE_ID_CP_MES; - ucode_data = AMDGPU_UCODE_ID_CP_MES_DATA; - } else { - ucode = AMDGPU_UCODE_ID_CP_MES1; - ucode_data = AMDGPU_UCODE_ID_CP_MES1_DATA; - } - - info = &adev->firmware.ucode[ucode]; - info->ucode_id = ucode; - info->fw = adev->mes.fw[pipe]; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(mes_hdr->mes_ucode_size_bytes), - PAGE_SIZE); - - info = &adev->firmware.ucode[ucode_data]; - info->ucode_id = ucode_data; - info->fw = adev->mes.fw[pipe]; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(mes_hdr->mes_ucode_data_size_bytes), - PAGE_SIZE); - } - - return 0; -} - -static void mes_v10_1_free_microcode(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) -{ - release_firmware(adev->mes.fw[pipe]); - adev->mes.fw[pipe] = NULL; -} - static int mes_v10_1_allocate_ucode_buffer(struct amdgpu_device *adev, enum admgpu_mes_pipe pipe) { @@ -1007,7 +924,6 @@ static int mes_v10_1_sw_init(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; int pipe, r; - adev->mes.adev = adev; adev->mes.funcs = &mes_v10_1_funcs; adev->mes.kiq_hw_init = &mes_v10_1_kiq_hw_init; @@ -1019,10 +935,6 @@ static int mes_v10_1_sw_init(void *handle) if (!adev->enable_mes_kiq && pipe == AMDGPU_MES_KIQ_PIPE) continue; - r = mes_v10_1_init_microcode(adev, pipe); - if (r) - return r; - r = mes_v10_1_allocate_eop_buf(adev, pipe); if (r) return r; @@ -1059,8 +971,7 @@ static int mes_v10_1_sw_fini(void *handle) amdgpu_bo_free_kernel(&adev->mes.eop_gpu_obj[pipe], &adev->mes.eop_gpu_addr[pipe], NULL); - - mes_v10_1_free_microcode(adev, pipe); + amdgpu_ucode_release(&adev->mes.fw[pipe]); } amdgpu_bo_free_kernel(&adev->gfx.kiq.ring.mqd_obj, @@ -1229,6 +1140,22 @@ static int mes_v10_1_resume(void *handle) return amdgpu_mes_resume(adev); } +static int mes_v10_0_early_init(void *handle) +{ + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + int pipe, r; + + for (pipe = 0; pipe < AMDGPU_MAX_MES_PIPES; pipe++) { + if (!adev->enable_mes_kiq && pipe == AMDGPU_MES_KIQ_PIPE) + continue; + r = amdgpu_mes_init_microcode(adev, pipe); + if (r) + return r; + } + + return 0; +} + static int mes_v10_0_late_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; @@ -1241,6 +1168,7 @@ static int mes_v10_0_late_init(void *handle) static const struct amd_ip_funcs mes_v10_1_ip_funcs = { .name = "mes_v10_1", + .early_init = mes_v10_0_early_init, .late_init = mes_v10_0_late_init, .sw_init = mes_v10_1_sw_init, .sw_fini = mes_v10_1_sw_fini, diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index 970b066b37bb..5826eac270d7 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -40,6 +40,8 @@ MODULE_FIRMWARE("amdgpu/gc_11_0_2_mes.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_2_mes1.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_3_mes.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_3_mes1.bin"); +MODULE_FIRMWARE("amdgpu/gc_11_0_4_mes.bin"); +MODULE_FIRMWARE("amdgpu/gc_11_0_4_mes1.bin"); static int mes_v11_0_hw_fini(void *handle); static int mes_v11_0_kiq_hw_init(struct amdgpu_device *adev); @@ -196,7 +198,6 @@ static int mes_v11_0_add_hw_queue(struct amdgpu_mes *mes, mes_add_queue_pkt.trap_handler_addr = input->tba_addr; mes_add_queue_pkt.tma_addr = input->tma_addr; mes_add_queue_pkt.is_kfd_process = input->is_kfd_process; - mes_add_queue_pkt.trap_en = 1; /* For KFD, gds_size is re-used for queue size (needed in MES for AQL queues) */ mes_add_queue_pkt.is_aql_queue = input->is_aql_queue; @@ -459,80 +460,6 @@ static const struct amdgpu_mes_funcs mes_v11_0_funcs = { .misc_op = mes_v11_0_misc_op, }; -static int mes_v11_0_init_microcode(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) -{ - char fw_name[30]; - char ucode_prefix[30]; - int err; - const struct mes_firmware_header_v1_0 *mes_hdr; - struct amdgpu_firmware_info *info; - - amdgpu_ucode_ip_version_decode(adev, GC_HWIP, ucode_prefix, sizeof(ucode_prefix)); - - if (pipe == AMDGPU_MES_SCHED_PIPE) - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mes.bin", - ucode_prefix); - else - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mes1.bin", - ucode_prefix); - - err = request_firmware(&adev->mes.fw[pipe], fw_name, adev->dev); - if (err) - return err; - - err = amdgpu_ucode_validate(adev->mes.fw[pipe]); - if (err) { - release_firmware(adev->mes.fw[pipe]); - adev->mes.fw[pipe] = NULL; - return err; - } - - mes_hdr = (const struct mes_firmware_header_v1_0 *) - adev->mes.fw[pipe]->data; - adev->mes.uc_start_addr[pipe] = - le32_to_cpu(mes_hdr->mes_uc_start_addr_lo) | - ((uint64_t)(le32_to_cpu(mes_hdr->mes_uc_start_addr_hi)) << 32); - adev->mes.data_start_addr[pipe] = - le32_to_cpu(mes_hdr->mes_data_start_addr_lo) | - ((uint64_t)(le32_to_cpu(mes_hdr->mes_data_start_addr_hi)) << 32); - - if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { - int ucode, ucode_data; - - if (pipe == AMDGPU_MES_SCHED_PIPE) { - ucode = AMDGPU_UCODE_ID_CP_MES; - ucode_data = AMDGPU_UCODE_ID_CP_MES_DATA; - } else { - ucode = AMDGPU_UCODE_ID_CP_MES1; - ucode_data = AMDGPU_UCODE_ID_CP_MES1_DATA; - } - - info = &adev->firmware.ucode[ucode]; - info->ucode_id = ucode; - info->fw = adev->mes.fw[pipe]; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(mes_hdr->mes_ucode_size_bytes), - PAGE_SIZE); - - info = &adev->firmware.ucode[ucode_data]; - info->ucode_id = ucode_data; - info->fw = adev->mes.fw[pipe]; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(mes_hdr->mes_ucode_data_size_bytes), - PAGE_SIZE); - } - - return 0; -} - -static void mes_v11_0_free_microcode(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) -{ - release_firmware(adev->mes.fw[pipe]); - adev->mes.fw[pipe] = NULL; -} - static int mes_v11_0_allocate_ucode_buffer(struct amdgpu_device *adev, enum admgpu_mes_pipe pipe) { @@ -549,7 +476,9 @@ static int mes_v11_0_allocate_ucode_buffer(struct amdgpu_device *adev, fw_size = le32_to_cpu(mes_hdr->mes_ucode_size_bytes); r = amdgpu_bo_create_reserved(adev, fw_size, - PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM, + PAGE_SIZE, + AMDGPU_GEM_DOMAIN_VRAM | + AMDGPU_GEM_DOMAIN_GTT, &adev->mes.ucode_fw_obj[pipe], &adev->mes.ucode_fw_gpu_addr[pipe], (void **)&adev->mes.ucode_fw_ptr[pipe]); @@ -582,7 +511,9 @@ static int mes_v11_0_allocate_ucode_data_buffer(struct amdgpu_device *adev, fw_size = le32_to_cpu(mes_hdr->mes_ucode_data_size_bytes); r = amdgpu_bo_create_reserved(adev, fw_size, - 64 * 1024, AMDGPU_GEM_DOMAIN_VRAM, + 64 * 1024, + AMDGPU_GEM_DOMAIN_VRAM | + AMDGPU_GEM_DOMAIN_GTT, &adev->mes.data_fw_obj[pipe], &adev->mes.data_fw_gpu_addr[pipe], (void **)&adev->mes.data_fw_ptr[pipe]); @@ -1087,7 +1018,6 @@ static int mes_v11_0_sw_init(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; int pipe, r; - adev->mes.adev = adev; adev->mes.funcs = &mes_v11_0_funcs; adev->mes.kiq_hw_init = &mes_v11_0_kiq_hw_init; adev->mes.kiq_hw_fini = &mes_v11_0_kiq_hw_fini; @@ -1100,10 +1030,6 @@ static int mes_v11_0_sw_init(void *handle) if (!adev->enable_mes_kiq && pipe == AMDGPU_MES_KIQ_PIPE) continue; - r = mes_v11_0_init_microcode(adev, pipe); - if (r) - return r; - r = mes_v11_0_allocate_eop_buf(adev, pipe); if (r) return r; @@ -1140,8 +1066,7 @@ static int mes_v11_0_sw_fini(void *handle) amdgpu_bo_free_kernel(&adev->mes.eop_gpu_obj[pipe], &adev->mes.eop_gpu_addr[pipe], NULL); - - mes_v11_0_free_microcode(adev, pipe); + amdgpu_ucode_release(&adev->mes.fw[pipe]); } amdgpu_bo_free_kernel(&adev->gfx.kiq.ring.mqd_obj, @@ -1338,12 +1263,28 @@ static int mes_v11_0_resume(void *handle) return amdgpu_mes_resume(adev); } +static int mes_v11_0_early_init(void *handle) +{ + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + int pipe, r; + + for (pipe = 0; pipe < AMDGPU_MAX_MES_PIPES; pipe++) { + if (!adev->enable_mes_kiq && pipe == AMDGPU_MES_KIQ_PIPE) + continue; + r = amdgpu_mes_init_microcode(adev, pipe); + if (r) + return r; + } + + return 0; +} + static int mes_v11_0_late_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; /* it's only intended for use in mes_self_test case, not for s0ix and reset */ - if (!amdgpu_in_reset(adev) && !adev->in_s0ix && + if (!amdgpu_in_reset(adev) && !adev->in_s0ix && !adev->in_suspend && (adev->ip_versions[GC_HWIP][0] != IP_VERSION(11, 0, 3))) amdgpu_mes_self_test(adev); @@ -1352,6 +1293,7 @@ static int mes_v11_0_late_init(void *handle) static const struct amd_ip_funcs mes_v11_0_ip_funcs = { .name = "mes_v11_0", + .early_init = mes_v11_0_early_init, .late_init = mes_v11_0_late_init, .sw_init = mes_v11_0_sw_init, .sw_fini = mes_v11_0_sw_fini, diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c index 3e51e773f92b..15e7cbeae75b 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c @@ -114,7 +114,7 @@ static void mmhub_v1_0_init_system_aperture_regs(struct amdgpu_device *adev) return; /* Set default page address. */ - value = amdgpu_gmc_vram_mc2pa(adev, adev->vram_scratch.gpu_addr); + value = amdgpu_gmc_vram_mc2pa(adev, adev->mem_scratch.gpu_addr); WREG32_SOC15(MMHUB, 0, mmMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB, (u32)(value >> 12)); WREG32_SOC15(MMHUB, 0, mmMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB, diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c index 6fa7090bc6cb..73afbf2facc9 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c @@ -134,7 +134,7 @@ static void mmhub_v1_7_init_system_aperture_regs(struct amdgpu_device *adev) } /* Set default page address. */ - value = amdgpu_gmc_vram_mc2pa(adev, adev->vram_scratch.gpu_addr); + value = amdgpu_gmc_vram_mc2pa(adev, adev->mem_scratch.gpu_addr); WREG32_SOC15(MMHUB, 0, regMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB, (u32)(value >> 12)); WREG32_SOC15(MMHUB, 0, regMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB, diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c index 0e664d0cc8d5..278e32db878d 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c @@ -234,7 +234,7 @@ static void mmhub_v2_0_init_system_aperture_regs(struct amdgpu_device *adev) } /* Set default page address. */ - value = amdgpu_gmc_vram_mc2pa(adev, adev->vram_scratch.gpu_addr); + value = amdgpu_gmc_vram_mc2pa(adev, adev->mem_scratch.gpu_addr); WREG32_SOC15(MMHUB, 0, mmMMMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB, (u32)(value >> 12)); WREG32_SOC15(MMHUB, 0, mmMMMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB, diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c index 4638ea7c2eec..fcf2813e70db 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c @@ -164,7 +164,7 @@ static void mmhub_v2_3_init_system_aperture_regs(struct amdgpu_device *adev) max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18); /* Set default page address. */ - value = amdgpu_gmc_vram_mc2pa(adev, adev->vram_scratch.gpu_addr); + value = amdgpu_gmc_vram_mc2pa(adev, adev->mem_scratch.gpu_addr); WREG32_SOC15(MMHUB, 0, mmMMMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB, (u32)(value >> 12)); WREG32_SOC15(MMHUB, 0, mmMMMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB, diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0.c index 16cc82215e2e..164948c50ac3 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0.c @@ -169,26 +169,27 @@ static void mmhub_v3_0_init_system_aperture_regs(struct amdgpu_device *adev) uint64_t value; uint32_t tmp; - if (!amdgpu_sriov_vf(adev)) { - /* - * the new L1 policy will block SRIOV guest from writing - * these regs, and they will be programed at host. - * so skip programing these regs. - */ - /* Disable AGP. */ - WREG32_SOC15(MMHUB, 0, regMMMC_VM_AGP_BASE, 0); - WREG32_SOC15(MMHUB, 0, regMMMC_VM_AGP_TOP, 0); - WREG32_SOC15(MMHUB, 0, regMMMC_VM_AGP_BOT, 0x00FFFFFF); - - /* Program the system aperture low logical page number. */ - WREG32_SOC15(MMHUB, 0, regMMMC_VM_SYSTEM_APERTURE_LOW_ADDR, - adev->gmc.vram_start >> 18); - WREG32_SOC15(MMHUB, 0, regMMMC_VM_SYSTEM_APERTURE_HIGH_ADDR, - adev->gmc.vram_end >> 18); - } + if (amdgpu_sriov_vf(adev)) + return; + + /* + * the new L1 policy will block SRIOV guest from writing + * these regs, and they will be programed at host. + * so skip programing these regs. + */ + /* Program the AGP BAR */ + WREG32_SOC15(MMHUB, 0, regMMMC_VM_AGP_BASE, 0); + WREG32_SOC15(MMHUB, 0, regMMMC_VM_AGP_BOT, adev->gmc.agp_start >> 24); + WREG32_SOC15(MMHUB, 0, regMMMC_VM_AGP_TOP, adev->gmc.agp_end >> 24); + + /* Program the system aperture low logical page number. */ + WREG32_SOC15(MMHUB, 0, regMMMC_VM_SYSTEM_APERTURE_LOW_ADDR, + min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18); + WREG32_SOC15(MMHUB, 0, regMMMC_VM_SYSTEM_APERTURE_HIGH_ADDR, + max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18); /* Set default page address. */ - value = adev->vram_scratch.gpu_addr - adev->gmc.vram_start + + value = adev->mem_scratch.gpu_addr - adev->gmc.vram_start + adev->vm_manager.vram_base_offset; WREG32_SOC15(MMHUB, 0, regMMMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB, (u32)(value >> 12)); diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_1.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_1.c index 6bdf2ef0298d..26509b6b8c24 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_1.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_1.c @@ -183,12 +183,12 @@ static void mmhub_v3_0_1_init_system_aperture_regs(struct amdgpu_device *adev) */ /* Program the system aperture low logical page number. */ WREG32_SOC15(MMHUB, 0, regMMMC_VM_SYSTEM_APERTURE_LOW_ADDR, - adev->gmc.vram_start >> 18); + min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18); WREG32_SOC15(MMHUB, 0, regMMMC_VM_SYSTEM_APERTURE_HIGH_ADDR, - adev->gmc.vram_end >> 18); + max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18); /* Set default page address. */ - value = adev->vram_scratch.gpu_addr - adev->gmc.vram_start + + value = adev->mem_scratch.gpu_addr - adev->gmc.vram_start + adev->vm_manager.vram_base_offset; WREG32_SOC15(MMHUB, 0, regMMMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB, (u32)(value >> 12)); diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_2.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_2.c index 45465acaa943..26abbc6a47ab 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_2.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_2.c @@ -162,10 +162,10 @@ static void mmhub_v3_0_2_init_system_aperture_regs(struct amdgpu_device *adev) uint64_t value; uint32_t tmp; - /* Disable AGP. */ + /* Program the AGP BAR */ WREG32_SOC15(MMHUB, 0, regMMMC_VM_AGP_BASE, 0); - WREG32_SOC15(MMHUB, 0, regMMMC_VM_AGP_TOP, 0); - WREG32_SOC15(MMHUB, 0, regMMMC_VM_AGP_BOT, 0x00FFFFFF); + WREG32_SOC15(MMHUB, 0, regMMMC_VM_AGP_BOT, adev->gmc.agp_start >> 24); + WREG32_SOC15(MMHUB, 0, regMMMC_VM_AGP_TOP, adev->gmc.agp_end >> 24); if (!amdgpu_sriov_vf(adev)) { /* @@ -175,13 +175,13 @@ static void mmhub_v3_0_2_init_system_aperture_regs(struct amdgpu_device *adev) */ /* Program the system aperture low logical page number. */ WREG32_SOC15(MMHUB, 0, regMMMC_VM_SYSTEM_APERTURE_LOW_ADDR, - adev->gmc.vram_start >> 18); + min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18); WREG32_SOC15(MMHUB, 0, regMMMC_VM_SYSTEM_APERTURE_HIGH_ADDR, - adev->gmc.vram_end >> 18); + max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18); } /* Set default page address. */ - value = adev->vram_scratch.gpu_addr - adev->gmc.vram_start + + value = adev->mem_scratch.gpu_addr - adev->gmc.vram_start + adev->vm_manager.vram_base_offset; WREG32_SOC15(MMHUB, 0, regMMMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB, (u32)(value >> 12)); diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c index 445cb06b9d26..72083e96222f 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c @@ -136,7 +136,7 @@ static void mmhub_v9_4_init_system_aperture_regs(struct amdgpu_device *adev, max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18); /* Set default page address. */ - value = amdgpu_gmc_vram_mc2pa(adev, adev->vram_scratch.gpu_addr); + value = amdgpu_gmc_vram_mc2pa(adev, adev->mem_scratch.gpu_addr); WREG32_SOC15_OFFSET( MMHUB, 0, mmVMSHAREDPF0_MC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB, diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c index 12906ba74462..63725b2ebc03 100644 --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c @@ -404,6 +404,11 @@ static int xgpu_ai_request_init_data(struct amdgpu_device *adev) return xgpu_ai_send_access_requests(adev, IDH_REQ_GPU_INIT_DATA); } +static void xgpu_ai_ras_poison_handler(struct amdgpu_device *adev) +{ + xgpu_ai_send_access_requests(adev, IDH_RAS_POISON); +} + const struct amdgpu_virt_ops xgpu_ai_virt_ops = { .req_full_gpu = xgpu_ai_request_full_gpu_access, .rel_full_gpu = xgpu_ai_release_full_gpu_access, @@ -411,4 +416,5 @@ const struct amdgpu_virt_ops xgpu_ai_virt_ops = { .wait_reset = NULL, .trans_msg = xgpu_ai_mailbox_trans_msg, .req_init_data = xgpu_ai_request_init_data, + .ras_poison_handler = xgpu_ai_ras_poison_handler, }; diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.h b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.h index fa7e13e0459e..af1a784696bd 100644 --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.h +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.h @@ -39,6 +39,7 @@ enum idh_request { IDH_LOG_VF_ERROR = 200, IDH_READY_TO_RESET = 201, + IDH_RAS_POISON = 202, }; enum idh_event { diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c index e07757eea7ad..cae1aaa4ddb6 100644 --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c @@ -426,6 +426,11 @@ void xgpu_nv_mailbox_put_irq(struct amdgpu_device *adev) amdgpu_irq_put(adev, &adev->virt.rcv_irq, 0); } +static void xgpu_nv_ras_poison_handler(struct amdgpu_device *adev) +{ + xgpu_nv_send_access_requests(adev, IDH_RAS_POISON); +} + const struct amdgpu_virt_ops xgpu_nv_virt_ops = { .req_full_gpu = xgpu_nv_request_full_gpu_access, .rel_full_gpu = xgpu_nv_release_full_gpu_access, @@ -433,4 +438,5 @@ const struct amdgpu_virt_ops xgpu_nv_virt_ops = { .reset_gpu = xgpu_nv_request_reset, .wait_reset = NULL, .trans_msg = xgpu_nv_mailbox_trans_msg, + .ras_poison_handler = xgpu_nv_ras_poison_handler, }; diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h index 73887b0aa1d6..d0221ce08769 100644 --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h @@ -39,6 +39,7 @@ enum idh_request { IDH_LOG_VF_ERROR = 200, IDH_READY_TO_RESET = 201, + IDH_RAS_POISON = 202, }; enum idh_event { diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c index 15eb3658d70e..09fdcd20cb91 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c @@ -337,7 +337,13 @@ const struct nbio_hdp_flush_reg nbio_v4_3_hdp_flush_reg = { static void nbio_v4_3_init_registers(struct amdgpu_device *adev) { - return; + if (adev->ip_versions[NBIO_HWIP][0] == IP_VERSION(4, 3, 0)) { + uint32_t data; + + data = RREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF2_STRAP2); + data &= ~RCC_DEV0_EPF2_STRAP2__STRAP_NO_SOFT_RESET_DEV0_F2_MASK; + WREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF2_STRAP2, data); + } } static u32 nbio_v4_3_get_rom_offset(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_2.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_2.c index 31776b12e4c4..4ef1fa4603c8 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_2.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_2.c @@ -394,6 +394,15 @@ static void nbio_v7_2_init_registers(struct amdgpu_device *adev) break; } + switch (adev->ip_versions[NBIO_HWIP][0]) { + case IP_VERSION(7, 3, 0): + case IP_VERSION(7, 5, 1): + data = RREG32_SOC15(NBIO, 0, regRCC_DEV2_EPF0_STRAP2); + data &= ~RCC_DEV2_EPF0_STRAP2__STRAP_NO_SOFT_RESET_DEV2_F0_MASK; + WREG32_SOC15(NBIO, 0, regRCC_DEV2_EPF0_STRAP2, data); + break; + } + if (amdgpu_sriov_vf(adev)) adev->rmmio_remap.reg_offset = SOC15_REG_OFFSET(NBIO, 0, regBIF_BX_PF0_HDP_MEM_COHERENCY_FLUSH_CNTL) << 2; diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index 6853b93ac82e..22e25ca285f8 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -98,7 +98,7 @@ static const struct amdgpu_video_codecs nv_video_codecs_decode = }; /* Sienna Cichlid */ -static const struct amdgpu_video_codec_info sc_video_codecs_decode_array[] = +static const struct amdgpu_video_codec_info sc_video_codecs_decode_array_vcn0[] = { {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)}, @@ -110,10 +110,27 @@ static const struct amdgpu_video_codec_info sc_video_codecs_decode_array[] = {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)}, }; -static const struct amdgpu_video_codecs sc_video_codecs_decode = +static const struct amdgpu_video_codec_info sc_video_codecs_decode_array_vcn1[] = { - .codec_count = ARRAY_SIZE(sc_video_codecs_decode_array), - .codec_array = sc_video_codecs_decode_array, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)}, +}; + +static const struct amdgpu_video_codecs sc_video_codecs_decode_vcn0 = +{ + .codec_count = ARRAY_SIZE(sc_video_codecs_decode_array_vcn0), + .codec_array = sc_video_codecs_decode_array_vcn0, +}; + +static const struct amdgpu_video_codecs sc_video_codecs_decode_vcn1 = +{ + .codec_count = ARRAY_SIZE(sc_video_codecs_decode_array_vcn1), + .codec_array = sc_video_codecs_decode_array_vcn1, }; /* SRIOV Sienna Cichlid, not const since data is controlled by host */ @@ -123,7 +140,7 @@ static struct amdgpu_video_codec_info sriov_sc_video_codecs_encode_array[] = {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)}, }; -static struct amdgpu_video_codec_info sriov_sc_video_codecs_decode_array[] = +static struct amdgpu_video_codec_info sriov_sc_video_codecs_decode_array_vcn0[] = { {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)}, @@ -135,16 +152,33 @@ static struct amdgpu_video_codec_info sriov_sc_video_codecs_decode_array[] = {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)}, }; +static struct amdgpu_video_codec_info sriov_sc_video_codecs_decode_array_vcn1[] = +{ + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)}, +}; + static struct amdgpu_video_codecs sriov_sc_video_codecs_encode = { .codec_count = ARRAY_SIZE(sriov_sc_video_codecs_encode_array), .codec_array = sriov_sc_video_codecs_encode_array, }; -static struct amdgpu_video_codecs sriov_sc_video_codecs_decode = +static struct amdgpu_video_codecs sriov_sc_video_codecs_decode_vcn0 = { - .codec_count = ARRAY_SIZE(sriov_sc_video_codecs_decode_array), - .codec_array = sriov_sc_video_codecs_decode_array, + .codec_count = ARRAY_SIZE(sriov_sc_video_codecs_decode_array_vcn0), + .codec_array = sriov_sc_video_codecs_decode_array_vcn0, +}; + +static struct amdgpu_video_codecs sriov_sc_video_codecs_decode_vcn1 = +{ + .codec_count = ARRAY_SIZE(sriov_sc_video_codecs_decode_array_vcn1), + .codec_array = sriov_sc_video_codecs_decode_array_vcn1, }; /* Beige Goby*/ @@ -181,20 +215,37 @@ static const struct amdgpu_video_codecs yc_video_codecs_decode = { static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode, const struct amdgpu_video_codecs **codecs) { + if (adev->vcn.num_vcn_inst == hweight8(adev->vcn.harvest_config)) + return -EINVAL; + switch (adev->ip_versions[UVD_HWIP][0]) { case IP_VERSION(3, 0, 0): case IP_VERSION(3, 0, 64): case IP_VERSION(3, 0, 192): if (amdgpu_sriov_vf(adev)) { - if (encode) - *codecs = &sriov_sc_video_codecs_encode; - else - *codecs = &sriov_sc_video_codecs_decode; + if (adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) { + if (encode) + *codecs = &sriov_sc_video_codecs_encode; + else + *codecs = &sriov_sc_video_codecs_decode_vcn1; + } else { + if (encode) + *codecs = &sriov_sc_video_codecs_encode; + else + *codecs = &sriov_sc_video_codecs_decode_vcn0; + } } else { - if (encode) - *codecs = &nv_video_codecs_encode; - else - *codecs = &sc_video_codecs_decode; + if (adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) { + if (encode) + *codecs = &nv_video_codecs_encode; + else + *codecs = &sc_video_codecs_decode_vcn1; + } else { + if (encode) + *codecs = &nv_video_codecs_encode; + else + *codecs = &sc_video_codecs_decode_vcn0; + } } return 0; case IP_VERSION(3, 0, 16): @@ -202,7 +253,7 @@ static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode, if (encode) *codecs = &nv_video_codecs_encode; else - *codecs = &sc_video_codecs_decode; + *codecs = &sc_video_codecs_decode_vcn0; return 0; case IP_VERSION(3, 1, 1): case IP_VERSION(3, 1, 2): @@ -393,9 +444,10 @@ static int nv_read_register(struct amdgpu_device *adev, u32 se_num, *value = 0; for (i = 0; i < ARRAY_SIZE(nv_allowed_read_registers); i++) { en = &nv_allowed_read_registers[i]; - if (adev->reg_offset[en->hwip][en->inst] && - reg_offset != (adev->reg_offset[en->hwip][en->inst][en->seg] - + en->reg_offset)) + if (!adev->reg_offset[en->hwip][en->inst]) + continue; + else if (reg_offset != (adev->reg_offset[en->hwip][en->inst][en->seg] + + en->reg_offset)) continue; *value = nv_get_register_value(adev, @@ -993,9 +1045,19 @@ static int nv_common_late_init(void *handle) if (amdgpu_sriov_vf(adev)) { xgpu_nv_mailbox_get_irq(adev); - amdgpu_virt_update_sriov_video_codec(adev, - sriov_sc_video_codecs_encode_array, ARRAY_SIZE(sriov_sc_video_codecs_encode_array), - sriov_sc_video_codecs_decode_array, ARRAY_SIZE(sriov_sc_video_codecs_decode_array)); + if (adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) { + amdgpu_virt_update_sriov_video_codec(adev, + sriov_sc_video_codecs_encode_array, + ARRAY_SIZE(sriov_sc_video_codecs_encode_array), + sriov_sc_video_codecs_decode_array_vcn1, + ARRAY_SIZE(sriov_sc_video_codecs_decode_array_vcn1)); + } else { + amdgpu_virt_update_sriov_video_codec(adev, + sriov_sc_video_codecs_encode_array, + ARRAY_SIZE(sriov_sc_video_codecs_encode_array), + sriov_sc_video_codecs_decode_array_vcn0, + ARRAY_SIZE(sriov_sc_video_codecs_decode_array_vcn0)); + } } return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c index 9de46fa8f46c..e1b7fca09666 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c @@ -47,83 +47,17 @@ MODULE_FIRMWARE("amdgpu/raven_ta.bin"); static int psp_v10_0_init_microcode(struct psp_context *psp) { struct amdgpu_device *adev = psp->adev; - const char *chip_name; - char fw_name[30]; + char ucode_prefix[30]; int err = 0; - const struct ta_firmware_header_v1_0 *ta_hdr; DRM_DEBUG("\n"); - switch (adev->asic_type) { - case CHIP_RAVEN: - if (adev->apu_flags & AMD_APU_IS_RAVEN2) - chip_name = "raven2"; - else if (adev->apu_flags & AMD_APU_IS_PICASSO) - chip_name = "picasso"; - else - chip_name = "raven"; - break; - default: BUG(); - } - - err = psp_init_asd_microcode(psp, chip_name); + amdgpu_ucode_ip_version_decode(adev, MP0_HWIP, ucode_prefix, sizeof(ucode_prefix)); + + err = psp_init_asd_microcode(psp, ucode_prefix); if (err) - goto out; - - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ta.bin", chip_name); - err = request_firmware(&adev->psp.ta_fw, fw_name, adev->dev); - if (err) { - release_firmware(adev->psp.ta_fw); - adev->psp.ta_fw = NULL; - dev_info(adev->dev, - "psp v10.0: Failed to load firmware \"%s\"\n", - fw_name); - } else { - err = amdgpu_ucode_validate(adev->psp.ta_fw); - if (err) - goto out2; - - ta_hdr = (const struct ta_firmware_header_v1_0 *) - adev->psp.ta_fw->data; - adev->psp.hdcp_context.context.bin_desc.fw_version = - le32_to_cpu(ta_hdr->hdcp.fw_version); - adev->psp.hdcp_context.context.bin_desc.size_bytes = - le32_to_cpu(ta_hdr->hdcp.size_bytes); - adev->psp.hdcp_context.context.bin_desc.start_addr = - (uint8_t *)ta_hdr + - le32_to_cpu(ta_hdr->header.ucode_array_offset_bytes); - - adev->psp.dtm_context.context.bin_desc.fw_version = - le32_to_cpu(ta_hdr->dtm.fw_version); - adev->psp.dtm_context.context.bin_desc.size_bytes = - le32_to_cpu(ta_hdr->dtm.size_bytes); - adev->psp.dtm_context.context.bin_desc.start_addr = - (uint8_t *)adev->psp.hdcp_context.context.bin_desc.start_addr + - le32_to_cpu(ta_hdr->dtm.offset_bytes); - - adev->psp.securedisplay_context.context.bin_desc.fw_version = - le32_to_cpu(ta_hdr->securedisplay.fw_version); - adev->psp.securedisplay_context.context.bin_desc.size_bytes = - le32_to_cpu(ta_hdr->securedisplay.size_bytes); - adev->psp.securedisplay_context.context.bin_desc.start_addr = - (uint8_t *)adev->psp.hdcp_context.context.bin_desc.start_addr + - le32_to_cpu(ta_hdr->securedisplay.offset_bytes); - - adev->psp.ta_fw_version = le32_to_cpu(ta_hdr->header.ucode_version); - } - - return 0; - -out2: - release_firmware(adev->psp.ta_fw); - adev->psp.ta_fw = NULL; -out: - if (err) { - dev_err(adev->dev, - "psp v10.0: Failed to load firmware \"%s\"\n", - fw_name); - } - - return err; + return err; + + return psp_init_ta_microcode(psp, ucode_prefix); } static int psp_v10_0_ring_create(struct psp_context *psp, diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c index bd3e3e23a939..8f84fe40abbb 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c @@ -88,159 +88,56 @@ MODULE_FIRMWARE("amdgpu/beige_goby_ta.bin"); static int psp_v11_0_init_microcode(struct psp_context *psp) { struct amdgpu_device *adev = psp->adev; - const char *chip_name; - char fw_name[PSP_FW_NAME_LEN]; + char ucode_prefix[30]; int err = 0; - const struct ta_firmware_header_v1_0 *ta_hdr; DRM_DEBUG("\n"); - switch (adev->ip_versions[MP0_HWIP][0]) { - case IP_VERSION(11, 0, 2): - chip_name = "vega20"; - break; - case IP_VERSION(11, 0, 0): - chip_name = "navi10"; - break; - case IP_VERSION(11, 0, 5): - chip_name = "navi14"; - break; - case IP_VERSION(11, 0, 9): - chip_name = "navi12"; - break; - case IP_VERSION(11, 0, 4): - chip_name = "arcturus"; - break; - case IP_VERSION(11, 0, 7): - chip_name = "sienna_cichlid"; - break; - case IP_VERSION(11, 0, 11): - chip_name = "navy_flounder"; - break; - case IP_VERSION(11, 5, 0): - chip_name = "vangogh"; - break; - case IP_VERSION(11, 0, 12): - chip_name = "dimgrey_cavefish"; - break; - case IP_VERSION(11, 0, 13): - chip_name = "beige_goby"; - break; - default: - BUG(); - } - + amdgpu_ucode_ip_version_decode(adev, MP0_HWIP, ucode_prefix, sizeof(ucode_prefix)); switch (adev->ip_versions[MP0_HWIP][0]) { case IP_VERSION(11, 0, 2): case IP_VERSION(11, 0, 4): - err = psp_init_sos_microcode(psp, chip_name); + err = psp_init_sos_microcode(psp, ucode_prefix); if (err) return err; - err = psp_init_asd_microcode(psp, chip_name); + err = psp_init_asd_microcode(psp, ucode_prefix); if (err) 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); - if (err) { - release_firmware(adev->psp.ta_fw); - adev->psp.ta_fw = NULL; - dev_info(adev->dev, - "psp v11.0: Failed to load firmware \"%s\"\n", fw_name); - } else { - err = amdgpu_ucode_validate(adev->psp.ta_fw); - if (err) - goto out2; - - ta_hdr = (const struct ta_firmware_header_v1_0 *)adev->psp.ta_fw->data; - adev->psp.xgmi_context.context.bin_desc.fw_version = - le32_to_cpu(ta_hdr->xgmi.fw_version); - adev->psp.xgmi_context.context.bin_desc.size_bytes = - le32_to_cpu(ta_hdr->xgmi.size_bytes); - adev->psp.xgmi_context.context.bin_desc.start_addr = - (uint8_t *)ta_hdr + - le32_to_cpu(ta_hdr->header.ucode_array_offset_bytes); - adev->psp.ta_fw_version = le32_to_cpu(ta_hdr->header.ucode_version); - adev->psp.ras_context.context.bin_desc.fw_version = - le32_to_cpu(ta_hdr->ras.fw_version); - adev->psp.ras_context.context.bin_desc.size_bytes = - le32_to_cpu(ta_hdr->ras.size_bytes); - adev->psp.ras_context.context.bin_desc.start_addr = - (uint8_t *)adev->psp.xgmi_context.context.bin_desc.start_addr + - le32_to_cpu(ta_hdr->ras.offset_bytes); - } + err = psp_init_ta_microcode(psp, ucode_prefix); + adev->psp.securedisplay_context.context.bin_desc.size_bytes = 0; break; case IP_VERSION(11, 0, 0): case IP_VERSION(11, 0, 5): case IP_VERSION(11, 0, 9): - err = psp_init_sos_microcode(psp, chip_name); + err = psp_init_sos_microcode(psp, ucode_prefix); if (err) return err; - err = psp_init_asd_microcode(psp, chip_name); + err = psp_init_asd_microcode(psp, ucode_prefix); if (err) 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); - if (err) { - release_firmware(adev->psp.ta_fw); - adev->psp.ta_fw = NULL; - dev_info(adev->dev, - "psp v11.0: Failed to load firmware \"%s\"\n", fw_name); - } else { - err = amdgpu_ucode_validate(adev->psp.ta_fw); - if (err) - goto out2; - - ta_hdr = (const struct ta_firmware_header_v1_0 *)adev->psp.ta_fw->data; - adev->psp.hdcp_context.context.bin_desc.fw_version = - le32_to_cpu(ta_hdr->hdcp.fw_version); - adev->psp.hdcp_context.context.bin_desc.size_bytes = - le32_to_cpu(ta_hdr->hdcp.size_bytes); - adev->psp.hdcp_context.context.bin_desc.start_addr = - (uint8_t *)ta_hdr + - le32_to_cpu( - ta_hdr->header.ucode_array_offset_bytes); - - adev->psp.ta_fw_version = le32_to_cpu(ta_hdr->header.ucode_version); - - adev->psp.dtm_context.context.bin_desc.fw_version = - le32_to_cpu(ta_hdr->dtm.fw_version); - adev->psp.dtm_context.context.bin_desc.size_bytes = - le32_to_cpu(ta_hdr->dtm.size_bytes); - adev->psp.dtm_context.context.bin_desc.start_addr = - (uint8_t *)adev->psp.hdcp_context.context - .bin_desc.start_addr + - le32_to_cpu(ta_hdr->dtm.offset_bytes); - } + err = psp_init_ta_microcode(psp, ucode_prefix); + adev->psp.securedisplay_context.context.bin_desc.size_bytes = 0; break; case IP_VERSION(11, 0, 7): case IP_VERSION(11, 0, 11): case IP_VERSION(11, 0, 12): case IP_VERSION(11, 0, 13): - err = psp_init_sos_microcode(psp, chip_name); - if (err) - return err; - err = psp_init_ta_microcode(psp, chip_name); + err = psp_init_sos_microcode(psp, ucode_prefix); if (err) return err; + err = psp_init_ta_microcode(psp, ucode_prefix); break; case IP_VERSION(11, 5, 0): - err = psp_init_asd_microcode(psp, chip_name); - if (err) - return err; - err = psp_init_toc_microcode(psp, chip_name); + err = psp_init_asd_microcode(psp, ucode_prefix); if (err) return err; + err = psp_init_toc_microcode(psp, ucode_prefix); break; default: BUG(); } - return 0; - -out2: - release_firmware(adev->psp.ta_fw); - adev->psp.ta_fw = NULL; return err; } diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c index 8ed2281b6557..fcd708eae75c 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c @@ -48,83 +48,25 @@ MODULE_FIRMWARE("amdgpu/green_sardine_ta.bin"); static int psp_v12_0_init_microcode(struct psp_context *psp) { struct amdgpu_device *adev = psp->adev; - const char *chip_name; - char fw_name[30]; + char ucode_prefix[30]; int err = 0; - const struct ta_firmware_header_v1_0 *ta_hdr; DRM_DEBUG("\n"); - switch (adev->asic_type) { - case CHIP_RENOIR: - if (adev->apu_flags & AMD_APU_IS_RENOIR) - chip_name = "renoir"; - else - chip_name = "green_sardine"; - break; - default: - BUG(); - } + amdgpu_ucode_ip_version_decode(adev, MP0_HWIP, ucode_prefix, sizeof(ucode_prefix)); - err = psp_init_asd_microcode(psp, chip_name); + err = psp_init_asd_microcode(psp, ucode_prefix); if (err) 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); - if (err) { - release_firmware(adev->psp.ta_fw); - adev->psp.ta_fw = NULL; - dev_info(adev->dev, - "psp v12.0: Failed to load firmware \"%s\"\n", - fw_name); - } else { - err = amdgpu_ucode_validate(adev->psp.ta_fw); - if (err) - goto out; - - ta_hdr = (const struct ta_firmware_header_v1_0 *) - adev->psp.ta_fw->data; - adev->psp.hdcp_context.context.bin_desc.fw_version = - le32_to_cpu(ta_hdr->hdcp.fw_version); - adev->psp.hdcp_context.context.bin_desc.size_bytes = - le32_to_cpu(ta_hdr->hdcp.size_bytes); - adev->psp.hdcp_context.context.bin_desc.start_addr = - (uint8_t *)ta_hdr + - le32_to_cpu(ta_hdr->header.ucode_array_offset_bytes); - - adev->psp.ta_fw_version = le32_to_cpu(ta_hdr->header.ucode_version); - - adev->psp.dtm_context.context.bin_desc.fw_version = - le32_to_cpu(ta_hdr->dtm.fw_version); - adev->psp.dtm_context.context.bin_desc.size_bytes = - le32_to_cpu(ta_hdr->dtm.size_bytes); - adev->psp.dtm_context.context.bin_desc.start_addr = - (uint8_t *)adev->psp.hdcp_context.context.bin_desc.start_addr + - le32_to_cpu(ta_hdr->dtm.offset_bytes); - - if (adev->apu_flags & AMD_APU_IS_RENOIR) { - adev->psp.securedisplay_context.context.bin_desc.fw_version = - le32_to_cpu(ta_hdr->securedisplay.fw_version); - adev->psp.securedisplay_context.context.bin_desc.size_bytes = - le32_to_cpu(ta_hdr->securedisplay.size_bytes); - adev->psp.securedisplay_context.context.bin_desc.start_addr = - (uint8_t *)adev->psp.hdcp_context.context.bin_desc.start_addr + - le32_to_cpu(ta_hdr->securedisplay.offset_bytes); - } - } - - return 0; + err = psp_init_ta_microcode(psp, ucode_prefix); + if (err) + return err; -out: - release_firmware(adev->psp.ta_fw); - adev->psp.ta_fw = NULL; - if (err) { - dev_err(adev->dev, - "psp v12.0: Failed to load firmware \"%s\"\n", - fw_name); - } + /* only supported on renoir */ + if (!(adev->apu_flags & AMD_APU_IS_RENOIR)) + adev->psp.securedisplay_context.context.bin_desc.size_bytes = 0; - return err; + return 0; } static int psp_v12_0_bootloader_load_sysdrv(struct psp_context *psp) diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c index e6a26a7e5e5e..d62fcc77af95 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c @@ -70,32 +70,19 @@ MODULE_FIRMWARE("amdgpu/psp_13_0_11_ta.bin"); static int psp_v13_0_init_microcode(struct psp_context *psp) { struct amdgpu_device *adev = psp->adev; - const char *chip_name; char ucode_prefix[30]; int err = 0; - switch (adev->ip_versions[MP0_HWIP][0]) { - case IP_VERSION(13, 0, 2): - chip_name = "aldebaran"; - break; - case IP_VERSION(13, 0, 1): - case IP_VERSION(13, 0, 3): - chip_name = "yellow_carp"; - break; - default: - amdgpu_ucode_ip_version_decode(adev, MP0_HWIP, ucode_prefix, sizeof(ucode_prefix)); - chip_name = ucode_prefix; - break; - } + amdgpu_ucode_ip_version_decode(adev, MP0_HWIP, ucode_prefix, sizeof(ucode_prefix)); switch (adev->ip_versions[MP0_HWIP][0]) { case IP_VERSION(13, 0, 2): - err = psp_init_sos_microcode(psp, chip_name); + err = psp_init_sos_microcode(psp, ucode_prefix); if (err) return err; /* It's not necessary to load ras ta on Guest side */ if (!amdgpu_sriov_vf(adev)) { - err = psp_init_ta_microcode(&adev->psp, chip_name); + err = psp_init_ta_microcode(psp, ucode_prefix); if (err) return err; } @@ -105,21 +92,21 @@ static int psp_v13_0_init_microcode(struct psp_context *psp) case IP_VERSION(13, 0, 5): case IP_VERSION(13, 0, 8): case IP_VERSION(13, 0, 11): - err = psp_init_toc_microcode(psp, chip_name); + err = psp_init_toc_microcode(psp, ucode_prefix); if (err) return err; - err = psp_init_ta_microcode(psp, chip_name); + err = psp_init_ta_microcode(psp, ucode_prefix); if (err) return err; break; case IP_VERSION(13, 0, 0): case IP_VERSION(13, 0, 7): case IP_VERSION(13, 0, 10): - err = psp_init_sos_microcode(psp, chip_name); + err = psp_init_sos_microcode(psp, ucode_prefix); if (err) return err; /* It's not necessary to load ras ta on Guest side */ - err = psp_init_ta_microcode(psp, chip_name); + err = psp_init_ta_microcode(psp, ucode_prefix); if (err) return err; break; diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0_4.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0_4.c index 9d4e24e518e8..d5ba58eba3e2 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0_4.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0_4.c @@ -35,25 +35,17 @@ MODULE_FIRMWARE("amdgpu/psp_13_0_4_ta.bin"); static int psp_v13_0_4_init_microcode(struct psp_context *psp) { struct amdgpu_device *adev = psp->adev; - const char *chip_name; char ucode_prefix[30]; int err = 0; - switch (adev->ip_versions[MP0_HWIP][0]) { - case IP_VERSION(13, 0, 4): - amdgpu_ucode_ip_version_decode(adev, MP0_HWIP, ucode_prefix, sizeof(ucode_prefix)); - chip_name = ucode_prefix; - break; - default: - BUG(); - } + amdgpu_ucode_ip_version_decode(adev, MP0_HWIP, ucode_prefix, sizeof(ucode_prefix)); switch (adev->ip_versions[MP0_HWIP][0]) { case IP_VERSION(13, 0, 4): - err = psp_init_toc_microcode(psp, chip_name); + err = psp_init_toc_microcode(psp, ucode_prefix); if (err) return err; - err = psp_init_ta_microcode(psp, chip_name); + err = psp_init_ta_microcode(psp, ucode_prefix); if (err) return err; break; diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c index 157147c6c94e..f6b75e3e47ff 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c @@ -57,26 +57,18 @@ static int psp_v3_1_ring_stop(struct psp_context *psp, static int psp_v3_1_init_microcode(struct psp_context *psp) { struct amdgpu_device *adev = psp->adev; - const char *chip_name; + char ucode_prefix[30]; int err = 0; DRM_DEBUG("\n"); - switch (adev->asic_type) { - case CHIP_VEGA10: - chip_name = "vega10"; - break; - case CHIP_VEGA12: - chip_name = "vega12"; - break; - default: BUG(); - } + amdgpu_ucode_ip_version_decode(adev, MP0_HWIP, ucode_prefix, sizeof(ucode_prefix)); - err = psp_init_sos_microcode(psp, chip_name); + err = psp_init_sos_microcode(psp, ucode_prefix); if (err) return err; - err = psp_init_asd_microcode(psp, chip_name); + err = psp_init_asd_microcode(psp, ucode_prefix); if (err) return err; diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c index c52d246a1d96..fd2a7b66ac56 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c @@ -113,10 +113,9 @@ static void sdma_v2_4_init_golden_registers(struct amdgpu_device *adev) static void sdma_v2_4_free_microcode(struct amdgpu_device *adev) { int i; - for (i = 0; i < adev->sdma.num_instances; i++) { - release_firmware(adev->sdma.instance[i].fw); - adev->sdma.instance[i].fw = NULL; - } + + for (i = 0; i < adev->sdma.num_instances; i++) + amdgpu_ucode_release(&adev->sdma.instance[i].fw); } /** @@ -151,10 +150,7 @@ static int sdma_v2_4_init_microcode(struct amdgpu_device *adev) snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma.bin", chip_name); else snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma1.bin", chip_name); - err = request_firmware(&adev->sdma.instance[i].fw, fw_name, adev->dev); - if (err) - goto out; - err = amdgpu_ucode_validate(adev->sdma.instance[i].fw); + err = amdgpu_ucode_request(adev, &adev->sdma.instance[i].fw, fw_name); if (err) goto out; hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma.instance[i].fw->data; @@ -176,10 +172,8 @@ static int sdma_v2_4_init_microcode(struct amdgpu_device *adev) out: if (err) { pr_err("sdma_v2_4: Failed to load firmware \"%s\"\n", fw_name); - for (i = 0; i < adev->sdma.num_instances; i++) { - release_firmware(adev->sdma.instance[i].fw); - adev->sdma.instance[i].fw = NULL; - } + for (i = 0; i < adev->sdma.num_instances; i++) + amdgpu_ucode_release(&adev->sdma.instance[i].fw); } return err; } diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c index 486d9b5c1b9e..e572389089d2 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c @@ -250,10 +250,9 @@ static void sdma_v3_0_init_golden_registers(struct amdgpu_device *adev) static void sdma_v3_0_free_microcode(struct amdgpu_device *adev) { int i; - for (i = 0; i < adev->sdma.num_instances; i++) { - release_firmware(adev->sdma.instance[i].fw); - adev->sdma.instance[i].fw = NULL; - } + + for (i = 0; i < adev->sdma.num_instances; i++) + amdgpu_ucode_release(&adev->sdma.instance[i].fw); } /** @@ -309,10 +308,7 @@ static int sdma_v3_0_init_microcode(struct amdgpu_device *adev) snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma.bin", chip_name); else snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma1.bin", chip_name); - err = request_firmware(&adev->sdma.instance[i].fw, fw_name, adev->dev); - if (err) - goto out; - err = amdgpu_ucode_validate(adev->sdma.instance[i].fw); + err = amdgpu_ucode_request(adev, &adev->sdma.instance[i].fw, fw_name); if (err) goto out; hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma.instance[i].fw->data; @@ -332,10 +328,8 @@ static int sdma_v3_0_init_microcode(struct amdgpu_device *adev) out: if (err) { pr_err("sdma_v3_0: Failed to load firmware \"%s\"\n", fw_name); - for (i = 0; i < adev->sdma.num_instances; i++) { - release_firmware(adev->sdma.instance[i].fw); - adev->sdma.instance[i].fw = NULL; - } + for (i = 0; i < adev->sdma.num_instances; i++) + amdgpu_ucode_release(&adev->sdma.instance[i].fw); } return err; } diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index 4d780e4430e7..b5affba22156 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -575,60 +575,17 @@ static void sdma_v4_0_setup_ulv(struct amdgpu_device *adev) // vega10 real chip need to use PSP to load firmware static int sdma_v4_0_init_microcode(struct amdgpu_device *adev) { - const char *chip_name; - char fw_name[30]; int ret, i; - DRM_DEBUG("\n"); - - switch (adev->ip_versions[SDMA0_HWIP][0]) { - case IP_VERSION(4, 0, 0): - chip_name = "vega10"; - break; - case IP_VERSION(4, 0, 1): - chip_name = "vega12"; - break; - case IP_VERSION(4, 2, 0): - chip_name = "vega20"; - break; - case IP_VERSION(4, 1, 0): - case IP_VERSION(4, 1, 1): - if (adev->apu_flags & AMD_APU_IS_RAVEN2) - chip_name = "raven2"; - else if (adev->apu_flags & AMD_APU_IS_PICASSO) - chip_name = "picasso"; - else - chip_name = "raven"; - break; - case IP_VERSION(4, 2, 2): - chip_name = "arcturus"; - break; - case IP_VERSION(4, 1, 2): - if (adev->apu_flags & AMD_APU_IS_RENOIR) - chip_name = "renoir"; - else - chip_name = "green_sardine"; - break; - case IP_VERSION(4, 4, 0): - chip_name = "aldebaran"; - break; - default: - BUG(); - } - for (i = 0; i < adev->sdma.num_instances; i++) { - if (i == 0) - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma.bin", chip_name); - else - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma%d.bin", chip_name, i); if (adev->ip_versions[SDMA0_HWIP][0] == IP_VERSION(4, 2, 2) || adev->ip_versions[SDMA0_HWIP][0] == IP_VERSION(4, 4, 0)) { /* Acturus & Aldebaran will leverage the same FW memory for every SDMA instance */ - ret = amdgpu_sdma_init_microcode(adev, fw_name, 0, true); + ret = amdgpu_sdma_init_microcode(adev, 0, true); break; } else { - ret = amdgpu_sdma_init_microcode(adev, fw_name, i, false); + ret = amdgpu_sdma_init_microcode(adev, i, false); if (ret) return ret; } @@ -1894,6 +1851,11 @@ static int sdma_v4_0_sw_init(void *handle) } } + if (amdgpu_sdma_ras_sw_init(adev)) { + dev_err(adev->dev, "Failed to initialize sdma ras block!\n"); + return -EINVAL; + } + return r; } @@ -2731,22 +2693,6 @@ static void sdma_v4_0_set_ras_funcs(struct amdgpu_device *adev) break; } - if (adev->sdma.ras) { - amdgpu_ras_register_ras_block(adev, &adev->sdma.ras->ras_block); - - strcpy(adev->sdma.ras->ras_block.ras_comm.name, "sdma"); - adev->sdma.ras->ras_block.ras_comm.block = AMDGPU_RAS_BLOCK__SDMA; - adev->sdma.ras->ras_block.ras_comm.type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE; - adev->sdma.ras_if = &adev->sdma.ras->ras_block.ras_comm; - - /* If don't define special ras_late_init function, use default ras_late_init */ - if (!adev->sdma.ras->ras_block.ras_late_init) - adev->sdma.ras->ras_block.ras_late_init = amdgpu_sdma_ras_late_init; - - /* If not defined special ras_cb function, use default ras_cb */ - if (!adev->sdma.ras->ras_block.ras_cb) - adev->sdma.ras->ras_block.ras_cb = amdgpu_sdma_process_ras_data_cb; - } } const struct amdgpu_ip_block_version sdma_v4_0_ip_block = { diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c index d4d9f196db83..1941b3b7c5d9 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c @@ -237,39 +237,13 @@ static void sdma_v5_0_init_golden_registers(struct amdgpu_device *adev) // emulation only, won't work on real chip // navi10 real chip need to use PSP to load firmware static int sdma_v5_0_init_microcode(struct amdgpu_device *adev) -{ - const char *chip_name; - char fw_name[40]; - int ret, i; +{ int ret, i; if (amdgpu_sriov_vf(adev) && (adev->ip_versions[SDMA0_HWIP][0] == IP_VERSION(5, 0, 5))) return 0; - DRM_DEBUG("\n"); - - switch (adev->ip_versions[SDMA0_HWIP][0]) { - case IP_VERSION(5, 0, 0): - chip_name = "navi10"; - break; - case IP_VERSION(5, 0, 2): - chip_name = "navi14"; - break; - case IP_VERSION(5, 0, 5): - chip_name = "navi12"; - break; - case IP_VERSION(5, 0, 1): - chip_name = "cyan_skillfish2"; - break; - default: - BUG(); - } - for (i = 0; i < adev->sdma.num_instances; i++) { - if (i == 0) - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma.bin", chip_name); - else - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma1.bin", chip_name); - ret = amdgpu_sdma_init_microcode(adev, fw_name, i, false); + ret = amdgpu_sdma_init_microcode(adev, i, false); if (ret) return ret; } diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index 809eca54fc61..8e445eb9dd49 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c @@ -89,59 +89,6 @@ static u32 sdma_v5_2_get_reg_offset(struct amdgpu_device *adev, u32 instance, u3 return base + internal_offset; } -/** - * sdma_v5_2_init_microcode - load ucode images from disk - * - * @adev: amdgpu_device pointer - * - * Use the firmware interface to load the ucode images into - * the driver (not loaded into hw). - * Returns 0 on success, error on failure. - */ - -// emulation only, won't work on real chip -// navi10 real chip need to use PSP to load firmware -static int sdma_v5_2_init_microcode(struct amdgpu_device *adev) -{ - const char *chip_name; - char fw_name[40]; - - DRM_DEBUG("\n"); - - switch (adev->ip_versions[SDMA0_HWIP][0]) { - case IP_VERSION(5, 2, 0): - chip_name = "sienna_cichlid_sdma"; - break; - case IP_VERSION(5, 2, 2): - chip_name = "navy_flounder_sdma"; - break; - case IP_VERSION(5, 2, 1): - chip_name = "vangogh_sdma"; - break; - case IP_VERSION(5, 2, 4): - chip_name = "dimgrey_cavefish_sdma"; - break; - case IP_VERSION(5, 2, 5): - chip_name = "beige_goby_sdma"; - break; - case IP_VERSION(5, 2, 3): - chip_name = "yellow_carp_sdma"; - break; - case IP_VERSION(5, 2, 6): - chip_name = "sdma_5_2_6"; - break; - case IP_VERSION(5, 2, 7): - chip_name = "sdma_5_2_7"; - break; - default: - BUG(); - } - - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s.bin", chip_name); - - return amdgpu_sdma_init_microcode(adev, fw_name, 0, true); -} - static unsigned sdma_v5_2_ring_init_cond_exec(struct amdgpu_ring *ring) { unsigned ret; @@ -809,12 +756,6 @@ static int sdma_v5_2_start(struct amdgpu_device *adev) msleep(1000); } - /* TODO: check whether can submit a doorbell request to raise - * a doorbell fence to exit gfxoff. - */ - if (adev->in_s0ix) - amdgpu_gfx_off_ctrl(adev, false); - sdma_v5_2_soft_reset(adev); /* unhalt the MEs */ sdma_v5_2_enable(adev, true); @@ -823,8 +764,6 @@ static int sdma_v5_2_start(struct amdgpu_device *adev) /* start the gfx rings and rlc compute queues */ r = sdma_v5_2_gfx_resume(adev); - if (adev->in_s0ix) - amdgpu_gfx_off_ctrl(adev, true); if (r) return r; r = sdma_v5_2_rlc_resume(adev); @@ -1296,7 +1235,7 @@ static int sdma_v5_2_sw_init(void *handle) return r; } - r = sdma_v5_2_init_microcode(adev); + r = amdgpu_sdma_init_microcode(adev, 0, true); if (r) { DRM_ERROR("Failed to load sdma firmware!\n"); return r; diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c index 049c26a45d85..40e6b22daa22 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c @@ -78,29 +78,6 @@ static u32 sdma_v6_0_get_reg_offset(struct amdgpu_device *adev, u32 instance, u3 return base + internal_offset; } -/** - * sdma_v6_0_init_microcode - load ucode images from disk - * - * @adev: amdgpu_device pointer - * - * Use the firmware interface to load the ucode images into - * the driver (not loaded into hw). - * Returns 0 on success, error on failure. - */ -static int sdma_v6_0_init_microcode(struct amdgpu_device *adev) -{ - char fw_name[30]; - char ucode_prefix[30]; - - DRM_DEBUG("\n"); - - amdgpu_ucode_ip_version_decode(adev, SDMA0_HWIP, ucode_prefix, sizeof(ucode_prefix)); - - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s.bin", ucode_prefix); - - return amdgpu_sdma_init_microcode(adev, fw_name, 0, true); -} - static unsigned sdma_v6_0_ring_init_cond_exec(struct amdgpu_ring *ring) { unsigned ret; @@ -296,8 +273,6 @@ static void sdma_v6_0_ring_emit_ib(struct amdgpu_ring *ring, * sdma_v6_0_ring_emit_mem_sync - flush the IB by graphics cache rinse * * @ring: amdgpu ring pointer - * @job: job to retrieve vmid from - * @ib: IB object to schedule * * flush the IB by graphics cache rinse. */ @@ -349,7 +324,9 @@ static void sdma_v6_0_ring_emit_hdp_flush(struct amdgpu_ring *ring) * sdma_v6_0_ring_emit_fence - emit a fence on the DMA ring * * @ring: amdgpu ring pointer - * @fence: amdgpu fence object + * @addr: address + * @seq: fence seq number + * @flags: fence flags * * Add a DMA fence packet to the ring to write * the fence seq number and DMA trap packet to generate @@ -1083,10 +1060,9 @@ static void sdma_v6_0_vm_copy_pte(struct amdgpu_ib *ib, * * @ib: indirect buffer to fill with commands * @pe: addr of the page entry - * @addr: dst addr to write into pe + * @value: dst addr to write into pe * @count: number of page entries to update * @incr: increase next addr by incr bytes - * @flags: access flags * * Update PTEs by writing them manually using sDMA. */ @@ -1190,7 +1166,6 @@ static void sdma_v6_0_ring_emit_pipeline_sync(struct amdgpu_ring *ring) * sdma_v6_0_ring_emit_vm_flush - vm flush using sDMA * * @ring: amdgpu_ring pointer - * @vm: amdgpu_vm pointer * * Update the page table base and flush the VM TLB * using sDMA. @@ -1234,6 +1209,24 @@ static void sdma_v6_0_ring_emit_reg_write_reg_wait(struct amdgpu_ring *ring, amdgpu_ring_emit_reg_wait(ring, reg1, mask, mask); } +static struct amdgpu_sdma_ras sdma_v6_0_3_ras = { + .ras_block = { + .ras_late_init = amdgpu_ras_block_late_init, + }, +}; + +static void sdma_v6_0_set_ras_funcs(struct amdgpu_device *adev) +{ + switch (adev->ip_versions[SDMA0_HWIP][0]) { + case IP_VERSION(6, 0, 3): + adev->sdma.ras = &sdma_v6_0_3_ras; + break; + default: + break; + } + +} + static int sdma_v6_0_early_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; @@ -1243,6 +1236,7 @@ static int sdma_v6_0_early_init(void *handle) sdma_v6_0_set_vm_pte_funcs(adev); sdma_v6_0_set_irq_funcs(adev); sdma_v6_0_set_mqd_funcs(adev); + sdma_v6_0_set_ras_funcs(adev); return 0; } @@ -1260,7 +1254,7 @@ static int sdma_v6_0_sw_init(void *handle) if (r) return r; - r = sdma_v6_0_init_microcode(adev); + r = amdgpu_sdma_init_microcode(adev, 0, true); if (r) { DRM_ERROR("Failed to load sdma firmware!\n"); return r; @@ -1287,6 +1281,11 @@ static int sdma_v6_0_sw_init(void *handle) return r; } + if (amdgpu_sdma_ras_sw_init(adev)) { + dev_err(adev->dev, "Failed to initialize sdma ras block!\n"); + return -EINVAL; + } + return r; } @@ -1426,10 +1425,12 @@ static int sdma_v6_0_set_trap_irq_state(struct amdgpu_device *adev, u32 reg_offset = sdma_v6_0_get_reg_offset(adev, type, regSDMA0_CNTL); - sdma_cntl = RREG32(reg_offset); - sdma_cntl = REG_SET_FIELD(sdma_cntl, SDMA0_CNTL, TRAP_ENABLE, - state == AMDGPU_IRQ_STATE_ENABLE ? 1 : 0); - WREG32(reg_offset, sdma_cntl); + if (!amdgpu_sriov_vf(adev)) { + sdma_cntl = RREG32(reg_offset); + sdma_cntl = REG_SET_FIELD(sdma_cntl, SDMA0_CNTL, TRAP_ENABLE, + state == AMDGPU_IRQ_STATE_ENABLE ? 1 : 0); + WREG32(reg_offset, sdma_cntl); + } return 0; } @@ -1588,10 +1589,11 @@ static void sdma_v6_0_set_irq_funcs(struct amdgpu_device *adev) /** * sdma_v6_0_emit_copy_buffer - copy buffer using the sDMA engine * - * @ring: amdgpu_ring structure holding ring information + * @ib: indirect buffer to fill with commands * @src_offset: src GPU address * @dst_offset: dst GPU address * @byte_count: number of bytes to xfer + * @tmz: if a secure copy should be used * * Copy GPU buffers using the DMA engine. * Used by the amdgpu ttm implementation to move pages if @@ -1617,7 +1619,7 @@ static void sdma_v6_0_emit_copy_buffer(struct amdgpu_ib *ib, /** * sdma_v6_0_emit_fill_buffer - fill buffer using the sDMA engine * - * @ring: amdgpu_ring structure holding ring information + * @ib: indirect buffer to fill * @src_data: value to write to buffer * @dst_offset: dst GPU address * @byte_count: number of bytes to xfer diff --git a/drivers/gpu/drm/amd/amdgpu/smu_v13_0_10.c b/drivers/gpu/drm/amd/amdgpu/smu_v13_0_10.c new file mode 100644 index 000000000000..ae29620b1ea4 --- /dev/null +++ b/drivers/gpu/drm/amd/amdgpu/smu_v13_0_10.c @@ -0,0 +1,303 @@ +/* + * Copyright 2023 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + */ + +#include "smu_v13_0_10.h" +#include "amdgpu_reset.h" +#include "amdgpu_dpm.h" +#include "amdgpu_job.h" +#include "amdgpu_ring.h" +#include "amdgpu_ras.h" +#include "amdgpu_psp.h" + +static bool smu_v13_0_10_is_mode2_default(struct amdgpu_reset_control *reset_ctl) +{ + struct amdgpu_device *adev = (struct amdgpu_device *)reset_ctl->handle; + if (adev->pm.fw_version >= 0x00502005 && !amdgpu_sriov_vf(adev)) + return true; + + return false; +} + +static struct amdgpu_reset_handler * +smu_v13_0_10_get_reset_handler(struct amdgpu_reset_control *reset_ctl, + struct amdgpu_reset_context *reset_context) +{ + struct amdgpu_reset_handler *handler; + struct amdgpu_device *adev = (struct amdgpu_device *)reset_ctl->handle; + + if (reset_context->method != AMD_RESET_METHOD_NONE) { + list_for_each_entry(handler, &reset_ctl->reset_handlers, + handler_list) { + if (handler->reset_method == reset_context->method) + return handler; + } + } + + if (smu_v13_0_10_is_mode2_default(reset_ctl) && + amdgpu_asic_reset_method(adev) == AMD_RESET_METHOD_MODE2) { + list_for_each_entry (handler, &reset_ctl->reset_handlers, + handler_list) { + if (handler->reset_method == AMD_RESET_METHOD_MODE2) + return handler; + } + } + + return NULL; +} + +static int smu_v13_0_10_mode2_suspend_ip(struct amdgpu_device *adev) +{ + int r, i; + + amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE); + amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE); + + for (i = adev->num_ip_blocks - 1; i >= 0; i--) { + if (!(adev->ip_blocks[i].version->type == + AMD_IP_BLOCK_TYPE_GFX || + adev->ip_blocks[i].version->type == + AMD_IP_BLOCK_TYPE_SDMA || + adev->ip_blocks[i].version->type == + AMD_IP_BLOCK_TYPE_MES)) + continue; + + r = adev->ip_blocks[i].version->funcs->suspend(adev); + + if (r) { + dev_err(adev->dev, + "suspend of IP block <%s> failed %d\n", + adev->ip_blocks[i].version->funcs->name, r); + return r; + } + adev->ip_blocks[i].status.hw = false; + } + + return r; +} + +static int +smu_v13_0_10_mode2_prepare_hwcontext(struct amdgpu_reset_control *reset_ctl, + struct amdgpu_reset_context *reset_context) +{ + int r = 0; + struct amdgpu_device *adev = (struct amdgpu_device *)reset_ctl->handle; + + if (!amdgpu_sriov_vf(adev)) + r = smu_v13_0_10_mode2_suspend_ip(adev); + + return r; +} + +static int smu_v13_0_10_mode2_reset(struct amdgpu_device *adev) +{ + return amdgpu_dpm_mode2_reset(adev); +} + +static void smu_v13_0_10_async_reset(struct work_struct *work) +{ + struct amdgpu_reset_handler *handler; + struct amdgpu_reset_control *reset_ctl = + container_of(work, struct amdgpu_reset_control, reset_work); + struct amdgpu_device *adev = (struct amdgpu_device *)reset_ctl->handle; + + list_for_each_entry(handler, &reset_ctl->reset_handlers, + handler_list) { + if (handler->reset_method == reset_ctl->active_reset) { + dev_dbg(adev->dev, "Resetting device\n"); + handler->do_reset(adev); + break; + } + } +} +static int +smu_v13_0_10_mode2_perform_reset(struct amdgpu_reset_control *reset_ctl, + struct amdgpu_reset_context *reset_context) +{ + struct amdgpu_device *adev = (struct amdgpu_device *)reset_ctl->handle; + int r; + + r = smu_v13_0_10_mode2_reset(adev); + if (r) { + dev_err(adev->dev, + "ASIC reset failed with error, %d ", r); + } + return r; +} + +static int smu_v13_0_10_mode2_restore_ip(struct amdgpu_device *adev) +{ + int i, r; + struct psp_context *psp = &adev->psp; + struct amdgpu_firmware_info *ucode; + struct amdgpu_firmware_info *ucode_list[2]; + int ucode_count = 0; + + for (i = 0; i < adev->firmware.max_ucodes; i++) { + ucode = &adev->firmware.ucode[i]; + + switch (ucode->ucode_id) { + case AMDGPU_UCODE_ID_IMU_I: + case AMDGPU_UCODE_ID_IMU_D: + ucode_list[ucode_count++] = ucode; + break; + default: + break; + } + } + + r = psp_load_fw_list(psp, ucode_list, ucode_count); + if (r) { + dev_err(adev->dev, "IMU ucode load failed after mode2 reset\n"); + return r; + } + + r = psp_rlc_autoload_start(psp); + if (r) { + DRM_ERROR("Failed to start rlc autoload after mode2 reset\n"); + return r; + } + + amdgpu_dpm_enable_gfx_features(adev); + + for (i = 0; i < adev->num_ip_blocks; i++) { + if (!(adev->ip_blocks[i].version->type == + AMD_IP_BLOCK_TYPE_GFX || + adev->ip_blocks[i].version->type == + AMD_IP_BLOCK_TYPE_MES || + adev->ip_blocks[i].version->type == + AMD_IP_BLOCK_TYPE_SDMA)) + continue; + r = adev->ip_blocks[i].version->funcs->resume(adev); + if (r) { + dev_err(adev->dev, + "resume of IP block <%s> failed %d\n", + adev->ip_blocks[i].version->funcs->name, r); + return r; + } + + adev->ip_blocks[i].status.hw = true; + } + + for (i = 0; i < adev->num_ip_blocks; i++) { + if (!(adev->ip_blocks[i].version->type == + AMD_IP_BLOCK_TYPE_GFX || + adev->ip_blocks[i].version->type == + AMD_IP_BLOCK_TYPE_MES || + adev->ip_blocks[i].version->type == + AMD_IP_BLOCK_TYPE_SDMA)) + continue; + + if (adev->ip_blocks[i].version->funcs->late_init) { + r = adev->ip_blocks[i].version->funcs->late_init( + (void *)adev); + if (r) { + dev_err(adev->dev, + "late_init of IP block <%s> failed %d after reset\n", + adev->ip_blocks[i].version->funcs->name, + r); + return r; + } + } + adev->ip_blocks[i].status.late_initialized = true; + } + + amdgpu_device_set_cg_state(adev, AMD_CG_STATE_GATE); + amdgpu_device_set_pg_state(adev, AMD_PG_STATE_GATE); + + return r; +} + +static int +smu_v13_0_10_mode2_restore_hwcontext(struct amdgpu_reset_control *reset_ctl, + struct amdgpu_reset_context *reset_context) +{ + int r; + struct amdgpu_device *tmp_adev = (struct amdgpu_device *)reset_ctl->handle; + + dev_info(tmp_adev->dev, + "GPU reset succeeded, trying to resume\n"); + r = smu_v13_0_10_mode2_restore_ip(tmp_adev); + if (r) + goto end; + + amdgpu_register_gpu_instance(tmp_adev); + + /* Resume RAS */ + amdgpu_ras_resume(tmp_adev); + + amdgpu_irq_gpu_reset_resume_helper(tmp_adev); + + r = amdgpu_ib_ring_tests(tmp_adev); + if (r) { + dev_err(tmp_adev->dev, + "ib ring test failed (%d).\n", r); + r = -EAGAIN; + goto end; + } + +end: + if (r) + return -EAGAIN; + else + return r; +} + +static struct amdgpu_reset_handler smu_v13_0_10_mode2_handler = { + .reset_method = AMD_RESET_METHOD_MODE2, + .prepare_env = NULL, + .prepare_hwcontext = smu_v13_0_10_mode2_prepare_hwcontext, + .perform_reset = smu_v13_0_10_mode2_perform_reset, + .restore_hwcontext = smu_v13_0_10_mode2_restore_hwcontext, + .restore_env = NULL, + .do_reset = smu_v13_0_10_mode2_reset, +}; + +int smu_v13_0_10_reset_init(struct amdgpu_device *adev) +{ + struct amdgpu_reset_control *reset_ctl; + + reset_ctl = kzalloc(sizeof(*reset_ctl), GFP_KERNEL); + if (!reset_ctl) + return -ENOMEM; + + reset_ctl->handle = adev; + reset_ctl->async_reset = smu_v13_0_10_async_reset; + reset_ctl->active_reset = AMD_RESET_METHOD_NONE; + reset_ctl->get_reset_handler = smu_v13_0_10_get_reset_handler; + + INIT_LIST_HEAD(&reset_ctl->reset_handlers); + INIT_WORK(&reset_ctl->reset_work, reset_ctl->async_reset); + /* Only mode2 is handled through reset control now */ + amdgpu_reset_add_handler(reset_ctl, &smu_v13_0_10_mode2_handler); + + adev->reset_cntl = reset_ctl; + + return 0; +} + +int smu_v13_0_10_reset_fini(struct amdgpu_device *adev) +{ + kfree(adev->reset_cntl); + adev->reset_cntl = NULL; + return 0; +} diff --git a/drivers/gpu/drm/amd/amdgpu/smu_v13_0_10.h b/drivers/gpu/drm/amd/amdgpu/smu_v13_0_10.h new file mode 100644 index 000000000000..e0cb72a0eec6 --- /dev/null +++ b/drivers/gpu/drm/amd/amdgpu/smu_v13_0_10.h @@ -0,0 +1,32 @@ +/* + * Copyright 2023 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + */ + +#ifndef __SMU_V13_0_10_H__ +#define __SMU_V13_0_10_H__ + +#include "amdgpu.h" + +int smu_v13_0_10_reset_init(struct amdgpu_device *adev); +int smu_v13_0_10_reset_fini(struct amdgpu_device *adev); + +#endif diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index 7cd17dda32ce..2eddd7f6cd41 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -439,8 +439,9 @@ static int soc15_read_register(struct amdgpu_device *adev, u32 se_num, *value = 0; for (i = 0; i < ARRAY_SIZE(soc15_allowed_read_registers); i++) { en = &soc15_allowed_read_registers[i]; - if (adev->reg_offset[en->hwip][en->inst] && - reg_offset != (adev->reg_offset[en->hwip][en->inst][en->seg] + if (!adev->reg_offset[en->hwip][en->inst]) + continue; + else if (reg_offset != (adev->reg_offset[en->hwip][en->inst][en->seg] + en->reg_offset)) continue; diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index 5562670b7b52..c82b3a7ea5f0 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -48,19 +48,32 @@ static const struct amd_ip_funcs soc21_common_ip_funcs; /* SOC21 */ -static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_encode_array[] = +static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_encode_array_vcn0[] = +{ + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)}, +}; + +static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_encode_array_vcn1[] = { {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)}, }; -static const struct amdgpu_video_codecs vcn_4_0_0_video_codecs_encode = +static const struct amdgpu_video_codecs vcn_4_0_0_video_codecs_encode_vcn0 = { - .codec_count = ARRAY_SIZE(vcn_4_0_0_video_codecs_encode_array), - .codec_array = vcn_4_0_0_video_codecs_encode_array, + .codec_count = ARRAY_SIZE(vcn_4_0_0_video_codecs_encode_array_vcn0), + .codec_array = vcn_4_0_0_video_codecs_encode_array_vcn0, }; -static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_decode_array[] = +static const struct amdgpu_video_codecs vcn_4_0_0_video_codecs_encode_vcn1 = +{ + .codec_count = ARRAY_SIZE(vcn_4_0_0_video_codecs_encode_array_vcn1), + .codec_array = vcn_4_0_0_video_codecs_encode_array_vcn1, +}; + +static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_decode_array_vcn0[] = { {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)}, @@ -69,23 +82,115 @@ static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_decode_array[ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)}, }; -static const struct amdgpu_video_codecs vcn_4_0_0_video_codecs_decode = +static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_decode_array_vcn1[] = +{ + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)}, +}; + +static const struct amdgpu_video_codecs vcn_4_0_0_video_codecs_decode_vcn0 = +{ + .codec_count = ARRAY_SIZE(vcn_4_0_0_video_codecs_decode_array_vcn0), + .codec_array = vcn_4_0_0_video_codecs_decode_array_vcn0, +}; + +static const struct amdgpu_video_codecs vcn_4_0_0_video_codecs_decode_vcn1 = { - .codec_count = ARRAY_SIZE(vcn_4_0_0_video_codecs_decode_array), - .codec_array = vcn_4_0_0_video_codecs_decode_array, + .codec_count = ARRAY_SIZE(vcn_4_0_0_video_codecs_decode_array_vcn1), + .codec_array = vcn_4_0_0_video_codecs_decode_array_vcn1, +}; + +/* SRIOV SOC21, not const since data is controlled by host */ +static struct amdgpu_video_codec_info sriov_vcn_4_0_0_video_codecs_encode_array_vcn0[] = { + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)}, +}; + +static struct amdgpu_video_codec_info sriov_vcn_4_0_0_video_codecs_encode_array_vcn1[] = { + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)}, +}; + +static struct amdgpu_video_codecs sriov_vcn_4_0_0_video_codecs_encode_vcn0 = { + .codec_count = ARRAY_SIZE(sriov_vcn_4_0_0_video_codecs_encode_array_vcn0), + .codec_array = sriov_vcn_4_0_0_video_codecs_encode_array_vcn0, +}; + +static struct amdgpu_video_codecs sriov_vcn_4_0_0_video_codecs_encode_vcn1 = { + .codec_count = ARRAY_SIZE(sriov_vcn_4_0_0_video_codecs_encode_array_vcn1), + .codec_array = sriov_vcn_4_0_0_video_codecs_encode_array_vcn1, +}; + +static struct amdgpu_video_codec_info sriov_vcn_4_0_0_video_codecs_decode_array_vcn0[] = { + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)}, +}; + +static struct amdgpu_video_codec_info sriov_vcn_4_0_0_video_codecs_decode_array_vcn1[] = { + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)}, +}; + +static struct amdgpu_video_codecs sriov_vcn_4_0_0_video_codecs_decode_vcn0 = { + .codec_count = ARRAY_SIZE(sriov_vcn_4_0_0_video_codecs_decode_array_vcn0), + .codec_array = sriov_vcn_4_0_0_video_codecs_decode_array_vcn0, +}; + +static struct amdgpu_video_codecs sriov_vcn_4_0_0_video_codecs_decode_vcn1 = { + .codec_count = ARRAY_SIZE(sriov_vcn_4_0_0_video_codecs_decode_array_vcn1), + .codec_array = sriov_vcn_4_0_0_video_codecs_decode_array_vcn1, }; static int soc21_query_video_codecs(struct amdgpu_device *adev, bool encode, const struct amdgpu_video_codecs **codecs) { - switch (adev->ip_versions[UVD_HWIP][0]) { + if (adev->vcn.num_vcn_inst == hweight8(adev->vcn.harvest_config)) + return -EINVAL; + switch (adev->ip_versions[UVD_HWIP][0]) { case IP_VERSION(4, 0, 0): case IP_VERSION(4, 0, 2): - if (encode) - *codecs = &vcn_4_0_0_video_codecs_encode; - else - *codecs = &vcn_4_0_0_video_codecs_decode; + case IP_VERSION(4, 0, 4): + if (amdgpu_sriov_vf(adev)) { + if ((adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) || + !amdgpu_sriov_is_av1_support(adev)) { + if (encode) + *codecs = &sriov_vcn_4_0_0_video_codecs_encode_vcn1; + else + *codecs = &sriov_vcn_4_0_0_video_codecs_decode_vcn1; + } else { + if (encode) + *codecs = &sriov_vcn_4_0_0_video_codecs_encode_vcn0; + else + *codecs = &sriov_vcn_4_0_0_video_codecs_decode_vcn0; + } + } else { + if ((adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0)) { + if (encode) + *codecs = &vcn_4_0_0_video_codecs_encode_vcn1; + else + *codecs = &vcn_4_0_0_video_codecs_decode_vcn1; + } else { + if (encode) + *codecs = &vcn_4_0_0_video_codecs_encode_vcn0; + else + *codecs = &vcn_4_0_0_video_codecs_decode_vcn0; + } + } return 0; default: return -EINVAL; @@ -255,9 +360,10 @@ static int soc21_read_register(struct amdgpu_device *adev, u32 se_num, *value = 0; for (i = 0; i < ARRAY_SIZE(soc21_allowed_read_registers); i++) { en = &soc21_allowed_read_registers[i]; - if (adev->reg_offset[en->hwip][en->inst] && - reg_offset != (adev->reg_offset[en->hwip][en->inst][en->seg] - + en->reg_offset)) + if (!adev->reg_offset[en->hwip][en->inst]) + continue; + else if (reg_offset != (adev->reg_offset[en->hwip][en->inst][en->seg] + + en->reg_offset)) continue; *value = soc21_get_register_value(adev, @@ -640,7 +746,10 @@ static int soc21_common_early_init(void *handle) AMD_CG_SUPPORT_GFX_CGCG | AMD_CG_SUPPORT_GFX_CGLS | AMD_CG_SUPPORT_REPEATER_FGCG | - AMD_CG_SUPPORT_GFX_MGCG; + AMD_CG_SUPPORT_GFX_MGCG | + AMD_CG_SUPPORT_HDP_SD | + AMD_CG_SUPPORT_ATHUB_MGCG | + AMD_CG_SUPPORT_ATHUB_LS; adev->pg_flags = AMD_PG_SUPPORT_VCN | AMD_PG_SUPPORT_VCN_DPG | AMD_PG_SUPPORT_JPEG; @@ -689,8 +798,23 @@ static int soc21_common_late_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - if (amdgpu_sriov_vf(adev)) + if (amdgpu_sriov_vf(adev)) { xgpu_nv_mailbox_get_irq(adev); + if ((adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) || + !amdgpu_sriov_is_av1_support(adev)) { + amdgpu_virt_update_sriov_video_codec(adev, + sriov_vcn_4_0_0_video_codecs_encode_array_vcn1, + ARRAY_SIZE(sriov_vcn_4_0_0_video_codecs_encode_array_vcn1), + sriov_vcn_4_0_0_video_codecs_decode_array_vcn1, + ARRAY_SIZE(sriov_vcn_4_0_0_video_codecs_decode_array_vcn1)); + } else { + amdgpu_virt_update_sriov_video_codec(adev, + sriov_vcn_4_0_0_video_codecs_encode_array_vcn0, + ARRAY_SIZE(sriov_vcn_4_0_0_video_codecs_encode_array_vcn0), + sriov_vcn_4_0_0_video_codecs_decode_array_vcn0, + ARRAY_SIZE(sriov_vcn_4_0_0_video_codecs_decode_array_vcn0)); + } + } return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/ta_secureDisplay_if.h b/drivers/gpu/drm/amd/amdgpu/ta_secureDisplay_if.h index cf8ff064dc72..00d8bdb8254f 100644 --- a/drivers/gpu/drm/amd/amdgpu/ta_secureDisplay_if.h +++ b/drivers/gpu/drm/amd/amdgpu/ta_secureDisplay_if.h @@ -55,10 +55,10 @@ enum ta_securedisplay_status { TA_SECUREDISPLAY_STATUS__MAX = 0x7FFFFFFF,/* Maximum Value for status*/ }; -/** @enum ta_securedisplay_max_phy +/** @enum ta_securedisplay_phy_ID * Physical ID number to use for reading corresponding DIO Scratch register for ROI */ -enum ta_securedisplay_max_phy { +enum ta_securedisplay_phy_ID { TA_SECUREDISPLAY_PHY0 = 0, TA_SECUREDISPLAY_PHY1 = 1, TA_SECUREDISPLAY_PHY2 = 2, @@ -139,16 +139,16 @@ union ta_securedisplay_cmd_output { uint32_t reserved[4]; }; -/** @struct securedisplay_cmd - * Secure Display Command which is shared buffer memory - */ -struct securedisplay_cmd { - uint32_t cmd_id; /* +0 Bytes Command ID */ - enum ta_securedisplay_status status; /* +4 Bytes Status of Secure Display TA */ - uint32_t reserved[2]; /* +8 Bytes Reserved */ - union ta_securedisplay_cmd_input securedisplay_in_message; /* +16 Bytes Input Buffer */ - union ta_securedisplay_cmd_output securedisplay_out_message;/* +32 Bytes Output Buffer */ - /**@note Total 48 Bytes */ +/** @struct ta_securedisplay_cmd +* Secure display command which is shared buffer memory +*/ +struct ta_securedisplay_cmd { + uint32_t cmd_id; /**< +0 Bytes Command ID */ + enum ta_securedisplay_status status; /**< +4 Bytes Status code returned by the secure display TA */ + uint32_t reserved[2]; /**< +8 Bytes Reserved */ + union ta_securedisplay_cmd_input securedisplay_in_message; /**< +16 Bytes Command input buffer */ + union ta_securedisplay_cmd_output securedisplay_out_message; /**< +32 Bytes Command output buffer */ + /**@note Total 48 Bytes */ }; #endif //_TA_SECUREDISPLAY_IF_H diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c index 72fd963f178b..e08e25a3a1a9 100644 --- a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c +++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c @@ -57,13 +57,6 @@ static inline uint32_t get_umc_v6_7_reg_offset(struct amdgpu_device *adev, return adev->umc.channel_offs * ch_inst + UMC_V6_7_INST_DIST * umc_inst; } -static inline uint32_t get_umc_v6_7_channel_index(struct amdgpu_device *adev, - uint32_t umc_inst, - uint32_t ch_inst) -{ - return adev->umc.channel_idx_tbl[umc_inst * adev->umc.channel_inst_num + ch_inst]; -} - static void umc_v6_7_query_error_status_helper(struct amdgpu_device *adev, uint64_t mc_umc_status, uint32_t umc_reg_offset) { diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v8_10.c b/drivers/gpu/drm/amd/amdgpu/umc_v8_10.c index b7da4528cf0a..fb55e8cb9967 100644 --- a/drivers/gpu/drm/amd/amdgpu/umc_v8_10.c +++ b/drivers/gpu/drm/amd/amdgpu/umc_v8_10.c @@ -209,6 +209,45 @@ static int umc_v8_10_swizzle_mode_na_to_pa(struct amdgpu_device *adev, return 0; } +static void umc_v8_10_convert_error_address(struct amdgpu_device *adev, + struct ras_err_data *err_data, uint64_t err_addr, + uint32_t ch_inst, uint32_t umc_inst, + uint32_t node_inst, uint64_t mc_umc_status) +{ + uint64_t na_err_addr_base; + uint64_t na_err_addr, retired_page_addr; + uint32_t channel_index, addr_lsb, col = 0; + int ret = 0; + + channel_index = + adev->umc.channel_idx_tbl[node_inst * adev->umc.umc_inst_num * + adev->umc.channel_inst_num + + umc_inst * adev->umc.channel_inst_num + + ch_inst]; + + /* the lowest lsb bits should be ignored */ + addr_lsb = REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, AddrLsb); + err_addr &= ~((0x1ULL << addr_lsb) - 1); + na_err_addr_base = err_addr & ~(0x3ULL << UMC_V8_10_NA_C5_BIT); + + /* loop for all possibilities of [C6 C5] in normal address. */ + for (col = 0; col < UMC_V8_10_NA_COL_2BITS_POWER_OF_2_NUM; col++) { + na_err_addr = na_err_addr_base | (col << UMC_V8_10_NA_C5_BIT); + + /* Mapping normal error address to retired soc physical address. */ + ret = umc_v8_10_swizzle_mode_na_to_pa(adev, channel_index, + na_err_addr, &retired_page_addr); + if (ret) { + dev_err(adev->dev, "Failed to map pa from umc na.\n"); + break; + } + dev_info(adev->dev, "Error Address(PA): 0x%llx\n", + retired_page_addr); + amdgpu_umc_fill_error_record(err_data, na_err_addr, + retired_page_addr, channel_index, umc_inst); + } +} + static void umc_v8_10_query_error_address(struct amdgpu_device *adev, struct ras_err_data *err_data, uint32_t umc_reg_offset, @@ -218,10 +257,7 @@ static void umc_v8_10_query_error_address(struct amdgpu_device *adev, { uint64_t mc_umc_status_addr; uint64_t mc_umc_status, err_addr; - uint64_t mc_umc_addrt0, na_err_addr_base; - uint64_t na_err_addr, retired_page_addr; - uint32_t channel_index, addr_lsb, col = 0; - int ret = 0; + uint64_t mc_umc_addrt0; mc_umc_status_addr = SOC15_REG_OFFSET(UMC, 0, regMCA_UMC_UMC0_MCUMC_STATUST0); @@ -236,12 +272,6 @@ static void umc_v8_10_query_error_address(struct amdgpu_device *adev, return; } - channel_index = - adev->umc.channel_idx_tbl[node_inst * adev->umc.umc_inst_num * - adev->umc.channel_inst_num + - umc_inst * adev->umc.channel_inst_num + - ch_inst]; - /* calculate error address if ue error is detected */ if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 && REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, AddrV) == 1 && @@ -251,27 +281,8 @@ static void umc_v8_10_query_error_address(struct amdgpu_device *adev, err_addr = RREG64_PCIE((mc_umc_addrt0 + umc_reg_offset) * 4); err_addr = REG_GET_FIELD(err_addr, MCA_UMC_UMC0_MCUMC_ADDRT0, ErrorAddr); - /* the lowest lsb bits should be ignored */ - addr_lsb = REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, AddrLsb); - err_addr &= ~((0x1ULL << addr_lsb) - 1); - na_err_addr_base = err_addr & ~(0x3ULL << UMC_V8_10_NA_C5_BIT); - - /* loop for all possibilities of [C6 C5] in normal address. */ - for (col = 0; col < UMC_V8_10_NA_COL_2BITS_POWER_OF_2_NUM; col++) { - na_err_addr = na_err_addr_base | (col << UMC_V8_10_NA_C5_BIT); - - /* Mapping normal error address to retired soc physical address. */ - ret = umc_v8_10_swizzle_mode_na_to_pa(adev, channel_index, - na_err_addr, &retired_page_addr); - if (ret) { - dev_err(adev->dev, "Failed to map pa from umc na.\n"); - break; - } - dev_info(adev->dev, "Error Address(PA): 0x%llx\n", - retired_page_addr); - amdgpu_umc_fill_error_record(err_data, na_err_addr, - retired_page_addr, channel_index, umc_inst); - } + umc_v8_10_convert_error_address(adev, err_data, err_addr, + ch_inst, umc_inst, node_inst, mc_umc_status); } /* clear umc status */ @@ -340,29 +351,140 @@ static void umc_v8_10_err_cnt_init(struct amdgpu_device *adev) } } -static uint32_t umc_v8_10_query_ras_poison_mode_per_channel( - struct amdgpu_device *adev, - uint32_t umc_reg_offset) +static bool umc_v8_10_query_ras_poison_mode(struct amdgpu_device *adev) { - uint32_t ecc_ctrl_addr, ecc_ctrl; + /* + * Force return true, because UMCCH0_0_GeccCtrl + * is not accessible from host side + */ + return true; +} - ecc_ctrl_addr = - SOC15_REG_OFFSET(UMC, 0, regUMCCH0_0_GeccCtrl); - ecc_ctrl = RREG32_PCIE((ecc_ctrl_addr + - umc_reg_offset) * 4); +static void umc_v8_10_ecc_info_query_correctable_error_count(struct amdgpu_device *adev, + uint32_t node_inst, uint32_t umc_inst, uint32_t ch_inst, + unsigned long *error_count) +{ + uint64_t mc_umc_status; + uint32_t eccinfo_table_idx; + struct amdgpu_ras *ras = amdgpu_ras_get_context(adev); + + eccinfo_table_idx = node_inst * adev->umc.umc_inst_num * + adev->umc.channel_inst_num + + umc_inst * adev->umc.channel_inst_num + + ch_inst; - return REG_GET_FIELD(ecc_ctrl, UMCCH0_0_GeccCtrl, UCFatalEn); + /* check the MCUMC_STATUS */ + mc_umc_status = ras->umc_ecc.ecc[eccinfo_table_idx].mca_umc_status; + if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 && + REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1) { + *error_count += 1; + } } -static bool umc_v8_10_query_ras_poison_mode(struct amdgpu_device *adev) +static void umc_v8_10_ecc_info_query_uncorrectable_error_count(struct amdgpu_device *adev, + uint32_t node_inst, uint32_t umc_inst, uint32_t ch_inst, + unsigned long *error_count) { - uint32_t umc_reg_offset = 0; + uint64_t mc_umc_status; + uint32_t eccinfo_table_idx; + struct amdgpu_ras *ras = amdgpu_ras_get_context(adev); - /* Enabling fatal error in umc node0 instance0 channel0 will be - * considered as fatal error mode + eccinfo_table_idx = node_inst * adev->umc.umc_inst_num * + adev->umc.channel_inst_num + + umc_inst * adev->umc.channel_inst_num + + ch_inst; + + /* check the MCUMC_STATUS */ + mc_umc_status = ras->umc_ecc.ecc[eccinfo_table_idx].mca_umc_status; + if ((REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1) && + (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Deferred) == 1 || + REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1 || + REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, PCC) == 1 || + REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UC) == 1 || + REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, TCC) == 1)) { + *error_count += 1; + } +} + +static void umc_v8_10_ecc_info_query_ras_error_count(struct amdgpu_device *adev, + void *ras_error_status) +{ + struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status; + + uint32_t node_inst = 0; + uint32_t umc_inst = 0; + uint32_t ch_inst = 0; + + /* TODO: driver needs to toggle DF Cstate to ensure + * safe access of UMC registers. Will add the protection + */ + LOOP_UMC_EACH_NODE_INST_AND_CH(node_inst, umc_inst, ch_inst) { + umc_v8_10_ecc_info_query_correctable_error_count(adev, + node_inst, umc_inst, ch_inst, + &(err_data->ce_count)); + umc_v8_10_ecc_info_query_uncorrectable_error_count(adev, + node_inst, umc_inst, ch_inst, + &(err_data->ue_count)); + } +} + +static void umc_v8_10_ecc_info_query_error_address(struct amdgpu_device *adev, + struct ras_err_data *err_data, + uint32_t ch_inst, + uint32_t umc_inst, + uint32_t node_inst) +{ + uint32_t eccinfo_table_idx; + uint64_t mc_umc_status, err_addr; + + struct amdgpu_ras *ras = amdgpu_ras_get_context(adev); + + eccinfo_table_idx = node_inst * adev->umc.umc_inst_num * + adev->umc.channel_inst_num + + umc_inst * adev->umc.channel_inst_num + + ch_inst; + + mc_umc_status = ras->umc_ecc.ecc[eccinfo_table_idx].mca_umc_status; + + if (mc_umc_status == 0) + return; + + if (!err_data->err_addr) + return; + + /* calculate error address if ue error is detected */ + if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 && + REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, AddrV) == 1 && + (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1)) { + + err_addr = ras->umc_ecc.ecc[eccinfo_table_idx].mca_umc_addr; + err_addr = REG_GET_FIELD(err_addr, MCA_UMC_UMC0_MCUMC_ADDRT0, ErrorAddr); + + umc_v8_10_convert_error_address(adev, err_data, err_addr, + ch_inst, umc_inst, node_inst, mc_umc_status); + } +} + +static void umc_v8_10_ecc_info_query_ras_error_address(struct amdgpu_device *adev, + void *ras_error_status) +{ + struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status; + + uint32_t node_inst = 0; + uint32_t umc_inst = 0; + uint32_t ch_inst = 0; + + /* TODO: driver needs to toggle DF Cstate to ensure + * safe access of UMC resgisters. Will add the protection + * when firmware interface is ready */ - umc_reg_offset = get_umc_v8_10_reg_offset(adev, 0, 0, 0); - return !umc_v8_10_query_ras_poison_mode_per_channel(adev, umc_reg_offset); + LOOP_UMC_EACH_NODE_INST_AND_CH(node_inst, umc_inst, ch_inst) { + umc_v8_10_ecc_info_query_error_address(adev, + err_data, + ch_inst, + umc_inst, + node_inst); + } } const struct amdgpu_ras_block_hw_ops umc_v8_10_ras_hw_ops = { @@ -376,4 +498,6 @@ struct amdgpu_umc_ras umc_v8_10_ras = { }, .err_cnt_init = umc_v8_10_err_cnt_init, .query_ras_poison_mode = umc_v8_10_query_ras_poison_mode, + .ecc_info_query_ras_error_count = umc_v8_10_ecc_info_query_ras_error_count, + .ecc_info_query_ras_error_address = umc_v8_10_ecc_info_query_ras_error_address, }; diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v8_10.h b/drivers/gpu/drm/amd/amdgpu/umc_v8_10.h index 25eaf4af5fcf..c6dfd433fec7 100644 --- a/drivers/gpu/drm/amd/amdgpu/umc_v8_10.h +++ b/drivers/gpu/drm/amd/amdgpu/umc_v8_10.h @@ -31,9 +31,9 @@ /* number of umc instance with memory map register access */ #define UMC_V8_10_UMC_INSTANCE_NUM 2 -/* Total channel instances for all umc nodes */ +/* Total channel instances for all available umc nodes */ #define UMC_V8_10_TOTAL_CHANNEL_NUM(adev) \ - (UMC_V8_10_CHANNEL_INSTANCE_NUM * UMC_V8_10_UMC_INSTANCE_NUM * (adev)->umc.node_inst_num) + (UMC_V8_10_CHANNEL_INSTANCE_NUM * UMC_V8_10_UMC_INSTANCE_NUM * (adev)->gmc.num_umc) /* UMC regiser per channel offset */ #define UMC_V8_10_PER_CHANNEL_OFFSET 0x400 diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c index f0fbcda76f5e..c305b2cb8490 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c @@ -57,11 +57,12 @@ static void vcn_v1_0_idle_work_handler(struct work_struct *work); static void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring); /** - * vcn_v1_0_early_init - set function pointers + * vcn_v1_0_early_init - set function pointers and load microcode * * @handle: amdgpu_device pointer * * Set ring and irq function pointers + * Load microcode from filesystem */ static int vcn_v1_0_early_init(void *handle) { @@ -75,7 +76,7 @@ static int vcn_v1_0_early_init(void *handle) jpeg_v1_0_early_init(handle); - return 0; + return amdgpu_vcn_early_init(adev); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c index 08871bad9994..4b4cd88414e0 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c @@ -62,11 +62,12 @@ static int vcn_v2_0_pause_dpg_mode(struct amdgpu_device *adev, int inst_idx, struct dpg_pause_state *new_state); static int vcn_v2_0_start_sriov(struct amdgpu_device *adev); /** - * vcn_v2_0_early_init - set function pointers + * vcn_v2_0_early_init - set function pointers and load microcode * * @handle: amdgpu_device pointer * * Set ring and irq function pointers + * Load microcode from filesystem */ static int vcn_v2_0_early_init(void *handle) { @@ -81,7 +82,7 @@ static int vcn_v2_0_early_init(void *handle) vcn_v2_0_set_enc_ring_funcs(adev); vcn_v2_0_set_irq_funcs(adev); - return 0; + return amdgpu_vcn_early_init(adev); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c index ec87b00f2e05..b0b0e69c6a94 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c @@ -71,11 +71,12 @@ static int amdgpu_ih_clientid_vcns[] = { }; /** - * vcn_v2_5_early_init - set function pointers + * vcn_v2_5_early_init - set function pointers and load microcode * * @handle: amdgpu_device pointer * * Set ring and irq function pointers + * Load microcode from filesystem */ static int vcn_v2_5_early_init(void *handle) { @@ -107,7 +108,7 @@ static int vcn_v2_5_early_init(void *handle) vcn_v2_5_set_irq_funcs(adev); vcn_v2_5_set_ras_funcs(adev); - return 0; + return amdgpu_vcn_early_init(adev); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index 9c8b5fd99037..66439388faee 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -78,11 +78,12 @@ static void vcn_v3_0_dec_ring_set_wptr(struct amdgpu_ring *ring); static void vcn_v3_0_enc_ring_set_wptr(struct amdgpu_ring *ring); /** - * vcn_v3_0_early_init - set function pointers + * vcn_v3_0_early_init - set function pointers and load microcode * * @handle: amdgpu_device pointer * * Set ring and irq function pointers + * Load microcode from filesystem */ static int vcn_v3_0_early_init(void *handle) { @@ -109,7 +110,7 @@ static int vcn_v3_0_early_init(void *handle) vcn_v3_0_set_enc_ring_funcs(adev); vcn_v3_0_set_irq_funcs(adev); - return 0; + return amdgpu_vcn_early_init(adev); } /** @@ -1770,6 +1771,10 @@ static int vcn_v3_0_limit_sched(struct amdgpu_cs_parser *p, if (atomic_read(&job->base.entity->fence_seq)) return -EINVAL; + /* if VCN0 is harvested, we can't support AV1 */ + if (p->adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) + return -EINVAL; + scheds = p->adev->gpu_sched[AMDGPU_HW_IP_VCN_DEC] [AMDGPU_RING_PRIO_DEFAULT].sched; drm_sched_entity_modify_sched(job->base.entity, scheds, 1); diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c index 1e2b22299975..43d587404c3e 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c @@ -68,18 +68,27 @@ static void vcn_v4_0_unified_ring_set_wptr(struct amdgpu_ring *ring); static void vcn_v4_0_set_ras_funcs(struct amdgpu_device *adev); /** - * vcn_v4_0_early_init - set function pointers + * vcn_v4_0_early_init - set function pointers and load microcode * * @handle: amdgpu_device pointer * * Set ring and irq function pointers + * Load microcode from filesystem */ static int vcn_v4_0_early_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + int i; - if (amdgpu_sriov_vf(adev)) + if (amdgpu_sriov_vf(adev)) { adev->vcn.harvest_config = VCN_HARVEST_MMSCH; + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + if (amdgpu_vcn_is_disabled_vcn(adev, VCN_ENCODE_RING, i)) { + adev->vcn.harvest_config |= 1 << i; + dev_info(adev->dev, "VCN%d is disabled by hypervisor\n", i); + } + } + } /* re-use enc ring as unified ring */ adev->vcn.num_enc_rings = 1; @@ -88,7 +97,7 @@ static int vcn_v4_0_early_init(void *handle) vcn_v4_0_set_irq_funcs(adev); vcn_v4_0_set_ras_funcs(adev); - return 0; + return amdgpu_vcn_early_init(adev); } /** @@ -237,16 +246,11 @@ static int vcn_v4_0_hw_init(void *handle) continue; ring = &adev->vcn.inst[i].ring_enc[0]; - if (amdgpu_vcn_is_disabled_vcn(adev, VCN_ENCODE_RING, i)) { - ring->sched.ready = false; - ring->no_scheduler = true; - dev_info(adev->dev, "ring %s is disabled by hypervisor\n", ring->name); - } else { - ring->wptr = 0; - ring->wptr_old = 0; - vcn_v4_0_unified_ring_set_wptr(ring); - ring->sched.ready = true; - } + ring->wptr = 0; + ring->wptr_old = 0; + vcn_v4_0_unified_ring_set_wptr(ring); + ring->sched.ready = true; + } } else { for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { @@ -1631,6 +1635,10 @@ static int vcn_v4_0_limit_sched(struct amdgpu_cs_parser *p, if (atomic_read(&job->base.entity->fence_seq)) return -EINVAL; + /* if VCN0 is harvested, we can't support AV1 */ + if (p->adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) + return -EINVAL; + scheds = p->adev->gpu_sched[AMDGPU_HW_IP_VCN_ENC] [AMDGPU_RING_PRIO_0].sched; drm_sched_entity_modify_sched(job->base.entity, scheds, 1); @@ -1705,7 +1713,7 @@ static int vcn_v4_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, create = ptr + addr + offset - start; - /* H246, HEVC and VP9 can run on any instance */ + /* H264, HEVC and VP9 can run on any instance */ if (create[0] == 0x7 || create[0] == 0x10 || create[0] == 0x11) continue; @@ -1719,7 +1727,29 @@ out: return r; } -#define RADEON_VCN_ENGINE_TYPE_DECODE (0x00000003) +#define RADEON_VCN_ENGINE_TYPE_ENCODE (0x00000002) +#define RADEON_VCN_ENGINE_TYPE_DECODE (0x00000003) + +#define RADEON_VCN_ENGINE_INFO (0x30000001) +#define RADEON_VCN_ENGINE_INFO_MAX_OFFSET 16 + +#define RENCODE_ENCODE_STANDARD_AV1 2 +#define RENCODE_IB_PARAM_SESSION_INIT 0x00000003 +#define RENCODE_IB_PARAM_SESSION_INIT_MAX_OFFSET 64 + +/* return the offset in ib if id is found, -1 otherwise + * to speed up the searching we only search upto max_offset + */ +static int vcn_v4_0_enc_find_ib_param(struct amdgpu_ib *ib, uint32_t id, int max_offset) +{ + int i; + + for (i = 0; i < ib->length_dw && i < max_offset && ib->ptr[i] >= 8; i += ib->ptr[i]/4) { + if (ib->ptr[i + 1] == id) + return i; + } + return -1; +} static int vcn_v4_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, struct amdgpu_job *job, @@ -1729,27 +1759,35 @@ static int vcn_v4_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, struct amdgpu_vcn_decode_buffer *decode_buffer; uint64_t addr; uint32_t val; + int idx; /* The first instance can decode anything */ if (!ring->me) return 0; - /* unified queue ib header has 8 double words. */ - if (ib->length_dw < 8) + /* RADEON_VCN_ENGINE_INFO is at the top of ib block */ + idx = vcn_v4_0_enc_find_ib_param(ib, RADEON_VCN_ENGINE_INFO, + RADEON_VCN_ENGINE_INFO_MAX_OFFSET); + if (idx < 0) /* engine info is missing */ return 0; - val = amdgpu_ib_get_value(ib, 6); //RADEON_VCN_ENGINE_TYPE - if (val != RADEON_VCN_ENGINE_TYPE_DECODE) - return 0; - - decode_buffer = (struct amdgpu_vcn_decode_buffer *)&ib->ptr[10]; - - if (!(decode_buffer->valid_buf_flag & 0x1)) - return 0; - - addr = ((u64)decode_buffer->msg_buffer_address_hi) << 32 | - decode_buffer->msg_buffer_address_lo; - return vcn_v4_0_dec_msg(p, job, addr); + val = amdgpu_ib_get_value(ib, idx + 2); /* RADEON_VCN_ENGINE_TYPE */ + if (val == RADEON_VCN_ENGINE_TYPE_DECODE) { + decode_buffer = (struct amdgpu_vcn_decode_buffer *)&ib->ptr[idx + 6]; + + if (!(decode_buffer->valid_buf_flag & 0x1)) + return 0; + + addr = ((u64)decode_buffer->msg_buffer_address_hi) << 32 | + decode_buffer->msg_buffer_address_lo; + return vcn_v4_0_dec_msg(p, job, addr); + } else if (val == RADEON_VCN_ENGINE_TYPE_ENCODE) { + idx = vcn_v4_0_enc_find_ib_param(ib, RENCODE_IB_PARAM_SESSION_INIT, + RENCODE_IB_PARAM_SESSION_INIT_MAX_OFFSET); + if (idx >= 0 && ib->ptr[idx + 2] == RENCODE_ENCODE_STANDARD_AV1) + return vcn_v4_0_limit_sched(p, job); + } + return 0; } static const struct amdgpu_ring_funcs vcn_v4_0_unified_ring_vm_funcs = { |