diff options
Diffstat (limited to 'drivers/gpu/drm/panthor')
| -rw-r--r-- | drivers/gpu/drm/panthor/Makefile | 1 | ||||
| -rw-r--r-- | drivers/gpu/drm/panthor/panthor_device.c | 5 | ||||
| -rw-r--r-- | drivers/gpu/drm/panthor/panthor_drv.c | 25 | ||||
| -rw-r--r-- | drivers/gpu/drm/panthor/panthor_fw.c | 5 | ||||
| -rw-r--r-- | drivers/gpu/drm/panthor/panthor_gem.c | 3 | ||||
| -rw-r--r-- | drivers/gpu/drm/panthor/panthor_gem.h | 12 | ||||
| -rw-r--r-- | drivers/gpu/drm/panthor/panthor_gpu.c | 100 | ||||
| -rw-r--r-- | drivers/gpu/drm/panthor/panthor_hw.c | 125 | ||||
| -rw-r--r-- | drivers/gpu/drm/panthor/panthor_hw.h | 11 | ||||
| -rw-r--r-- | drivers/gpu/drm/panthor/panthor_mmu.c | 76 | ||||
| -rw-r--r-- | drivers/gpu/drm/panthor/panthor_regs.h | 3 | ||||
| -rw-r--r-- | drivers/gpu/drm/panthor/panthor_sched.c | 43 |
12 files changed, 259 insertions, 150 deletions
diff --git a/drivers/gpu/drm/panthor/Makefile b/drivers/gpu/drm/panthor/Makefile index 15294719b09c..02db21748c12 100644 --- a/drivers/gpu/drm/panthor/Makefile +++ b/drivers/gpu/drm/panthor/Makefile @@ -8,6 +8,7 @@ panthor-y := \ panthor_gem.o \ panthor_gpu.o \ panthor_heap.o \ + panthor_hw.o \ panthor_mmu.o \ panthor_sched.o diff --git a/drivers/gpu/drm/panthor/panthor_device.c b/drivers/gpu/drm/panthor/panthor_device.c index f0b2da5b2b96..81df49880bd8 100644 --- a/drivers/gpu/drm/panthor/panthor_device.c +++ b/drivers/gpu/drm/panthor/panthor_device.c @@ -18,6 +18,7 @@ #include "panthor_device.h" #include "panthor_fw.h" #include "panthor_gpu.h" +#include "panthor_hw.h" #include "panthor_mmu.h" #include "panthor_regs.h" #include "panthor_sched.h" @@ -244,6 +245,10 @@ int panthor_device_init(struct panthor_device *ptdev) return ret; } + ret = panthor_hw_init(ptdev); + if (ret) + goto err_rpm_put; + ret = panthor_gpu_init(ptdev); if (ret) goto err_rpm_put; diff --git a/drivers/gpu/drm/panthor/panthor_drv.c b/drivers/gpu/drm/panthor/panthor_drv.c index 4d8e9b34702a..4c202fc5ce05 100644 --- a/drivers/gpu/drm/panthor/panthor_drv.c +++ b/drivers/gpu/drm/panthor/panthor_drv.c @@ -1103,14 +1103,15 @@ static int panthor_ioctl_group_create(struct drm_device *ddev, void *data, ret = group_priority_permit(file, args->priority); if (ret) - return ret; + goto out; ret = panthor_group_create(pfile, args, queue_args); - if (ret >= 0) { - args->group_handle = ret; - ret = 0; - } + if (ret < 0) + goto out; + args->group_handle = ret; + ret = 0; +out: kvfree(queue_args); return ret; } @@ -1400,14 +1401,9 @@ panthor_open(struct drm_device *ddev, struct drm_file *file) struct panthor_file *pfile; int ret; - if (!try_module_get(THIS_MODULE)) - return -EINVAL; - pfile = kzalloc(sizeof(*pfile), GFP_KERNEL); - if (!pfile) { - ret = -ENOMEM; - goto err_put_mod; - } + if (!pfile) + return -ENOMEM; pfile->ptdev = ptdev; pfile->user_mmio.offset = DRM_PANTHOR_USER_MMIO_OFFSET; @@ -1439,9 +1435,6 @@ err_destroy_vm_pool: err_free_file: kfree(pfile); - -err_put_mod: - module_put(THIS_MODULE); return ret; } @@ -1454,7 +1447,6 @@ panthor_postclose(struct drm_device *ddev, struct drm_file *file) panthor_vm_pool_destroy(pfile); kfree(pfile); - module_put(THIS_MODULE); } static const struct drm_ioctl_desc panthor_drm_driver_ioctls[] = { @@ -1555,6 +1547,7 @@ static void panthor_show_fdinfo(struct drm_printer *p, struct drm_file *file) } static const struct file_operations panthor_drm_driver_fops = { + .owner = THIS_MODULE, .open = drm_open, .release = drm_release, .unlocked_ioctl = drm_ioctl, diff --git a/drivers/gpu/drm/panthor/panthor_fw.c b/drivers/gpu/drm/panthor/panthor_fw.c index 36f1034839c2..9bf06e55eaee 100644 --- a/drivers/gpu/drm/panthor/panthor_fw.c +++ b/drivers/gpu/drm/panthor/panthor_fw.c @@ -1402,3 +1402,8 @@ err_unplug_fw: } MODULE_FIRMWARE("arm/mali/arch10.8/mali_csffw.bin"); +MODULE_FIRMWARE("arm/mali/arch10.10/mali_csffw.bin"); +MODULE_FIRMWARE("arm/mali/arch10.12/mali_csffw.bin"); +MODULE_FIRMWARE("arm/mali/arch11.8/mali_csffw.bin"); +MODULE_FIRMWARE("arm/mali/arch12.8/mali_csffw.bin"); +MODULE_FIRMWARE("arm/mali/arch13.8/mali_csffw.bin"); diff --git a/drivers/gpu/drm/panthor/panthor_gem.c b/drivers/gpu/drm/panthor/panthor_gem.c index a123bc740ba1..156c7a0b62a2 100644 --- a/drivers/gpu/drm/panthor/panthor_gem.c +++ b/drivers/gpu/drm/panthor/panthor_gem.c @@ -74,7 +74,6 @@ static void panthor_gem_free_object(struct drm_gem_object *obj) mutex_destroy(&bo->label.lock); drm_gem_free_mmap_offset(&bo->base.base); - mutex_destroy(&bo->gpuva_list_lock); drm_gem_shmem_free(&bo->base); drm_gem_object_put(vm_root_gem); } @@ -246,8 +245,6 @@ struct drm_gem_object *panthor_gem_create_object(struct drm_device *ddev, size_t obj->base.base.funcs = &panthor_gem_funcs; obj->base.map_wc = !ptdev->coherent; - mutex_init(&obj->gpuva_list_lock); - drm_gem_gpuva_set_lock(&obj->base.base, &obj->gpuva_list_lock); mutex_init(&obj->label.lock); panthor_gem_debugfs_bo_init(obj); diff --git a/drivers/gpu/drm/panthor/panthor_gem.h b/drivers/gpu/drm/panthor/panthor_gem.h index 8fc7215e9b90..80c6e24112d0 100644 --- a/drivers/gpu/drm/panthor/panthor_gem.h +++ b/drivers/gpu/drm/panthor/panthor_gem.h @@ -79,18 +79,6 @@ struct panthor_gem_object { */ struct drm_gem_object *exclusive_vm_root_gem; - /** - * @gpuva_list_lock: Custom GPUVA lock. - * - * Used to protect insertion of drm_gpuva elements to the - * drm_gem_object.gpuva.list list. - * - * We can't use the GEM resv for that, because drm_gpuva_link() is - * called in a dma-signaling path, where we're not allowed to take - * resv locks. - */ - struct mutex gpuva_list_lock; - /** @flags: Combination of drm_panthor_bo_flags flags. */ u32 flags; diff --git a/drivers/gpu/drm/panthor/panthor_gpu.c b/drivers/gpu/drm/panthor/panthor_gpu.c index cb7a335e07d7..db69449a5be0 100644 --- a/drivers/gpu/drm/panthor/panthor_gpu.c +++ b/drivers/gpu/drm/panthor/panthor_gpu.c @@ -35,40 +35,9 @@ struct panthor_gpu { /** @reqs_acked: GPU request wait queue. */ wait_queue_head_t reqs_acked; -}; - -/** - * struct panthor_model - GPU model description - */ -struct panthor_model { - /** @name: Model name. */ - const char *name; - - /** @arch_major: Major version number of architecture. */ - u8 arch_major; - /** @product_major: Major version number of product. */ - u8 product_major; -}; - -/** - * GPU_MODEL() - Define a GPU model. A GPU product can be uniquely identified - * by a combination of the major architecture version and the major product - * version. - * @_name: Name for the GPU model. - * @_arch_major: Architecture major. - * @_product_major: Product major. - */ -#define GPU_MODEL(_name, _arch_major, _product_major) \ -{\ - .name = __stringify(_name), \ - .arch_major = _arch_major, \ - .product_major = _product_major, \ -} - -static const struct panthor_model gpu_models[] = { - GPU_MODEL(g610, 10, 7), - {}, + /** @cache_flush_lock: Lock to serialize cache flushes */ + struct mutex cache_flush_lock; }; #define GPU_INTERRUPTS_MASK \ @@ -83,66 +52,6 @@ static void panthor_gpu_coherency_set(struct panthor_device *ptdev) ptdev->coherent ? GPU_COHERENCY_PROT_BIT(ACE_LITE) : GPU_COHERENCY_NONE); } -static void panthor_gpu_init_info(struct panthor_device *ptdev) -{ - const struct panthor_model *model; - u32 arch_major, product_major; - u32 major, minor, status; - unsigned int i; - - ptdev->gpu_info.gpu_id = gpu_read(ptdev, GPU_ID); - ptdev->gpu_info.csf_id = gpu_read(ptdev, GPU_CSF_ID); - ptdev->gpu_info.gpu_rev = gpu_read(ptdev, GPU_REVID); - ptdev->gpu_info.core_features = gpu_read(ptdev, GPU_CORE_FEATURES); - ptdev->gpu_info.l2_features = gpu_read(ptdev, GPU_L2_FEATURES); - ptdev->gpu_info.tiler_features = gpu_read(ptdev, GPU_TILER_FEATURES); - ptdev->gpu_info.mem_features = gpu_read(ptdev, GPU_MEM_FEATURES); - ptdev->gpu_info.mmu_features = gpu_read(ptdev, GPU_MMU_FEATURES); - ptdev->gpu_info.thread_features = gpu_read(ptdev, GPU_THREAD_FEATURES); - ptdev->gpu_info.max_threads = gpu_read(ptdev, GPU_THREAD_MAX_THREADS); - ptdev->gpu_info.thread_max_workgroup_size = gpu_read(ptdev, GPU_THREAD_MAX_WORKGROUP_SIZE); - ptdev->gpu_info.thread_max_barrier_size = gpu_read(ptdev, GPU_THREAD_MAX_BARRIER_SIZE); - ptdev->gpu_info.coherency_features = gpu_read(ptdev, GPU_COHERENCY_FEATURES); - for (i = 0; i < 4; i++) - ptdev->gpu_info.texture_features[i] = gpu_read(ptdev, GPU_TEXTURE_FEATURES(i)); - - ptdev->gpu_info.as_present = gpu_read(ptdev, GPU_AS_PRESENT); - - ptdev->gpu_info.shader_present = gpu_read64(ptdev, GPU_SHADER_PRESENT); - ptdev->gpu_info.tiler_present = gpu_read64(ptdev, GPU_TILER_PRESENT); - ptdev->gpu_info.l2_present = gpu_read64(ptdev, GPU_L2_PRESENT); - - arch_major = GPU_ARCH_MAJOR(ptdev->gpu_info.gpu_id); - product_major = GPU_PROD_MAJOR(ptdev->gpu_info.gpu_id); - major = GPU_VER_MAJOR(ptdev->gpu_info.gpu_id); - minor = GPU_VER_MINOR(ptdev->gpu_info.gpu_id); - status = GPU_VER_STATUS(ptdev->gpu_info.gpu_id); - - for (model = gpu_models; model->name; model++) { - if (model->arch_major == arch_major && - model->product_major == product_major) - break; - } - - drm_info(&ptdev->base, - "mali-%s id 0x%x major 0x%x minor 0x%x status 0x%x", - model->name ?: "unknown", ptdev->gpu_info.gpu_id >> 16, - major, minor, status); - - drm_info(&ptdev->base, - "Features: L2:%#x Tiler:%#x Mem:%#x MMU:%#x AS:%#x", - ptdev->gpu_info.l2_features, - ptdev->gpu_info.tiler_features, - ptdev->gpu_info.mem_features, - ptdev->gpu_info.mmu_features, - ptdev->gpu_info.as_present); - - drm_info(&ptdev->base, - "shader_present=0x%0llx l2_present=0x%0llx tiler_present=0x%0llx", - ptdev->gpu_info.shader_present, ptdev->gpu_info.l2_present, - ptdev->gpu_info.tiler_present); -} - static void panthor_gpu_irq_handler(struct panthor_device *ptdev, u32 status) { gpu_write(ptdev, GPU_INT_CLEAR, status); @@ -204,8 +113,8 @@ int panthor_gpu_init(struct panthor_device *ptdev) spin_lock_init(&gpu->reqs_lock); init_waitqueue_head(&gpu->reqs_acked); + mutex_init(&gpu->cache_flush_lock); ptdev->gpu = gpu; - panthor_gpu_init_info(ptdev); dma_set_max_seg_size(ptdev->base.dev, UINT_MAX); pa_bits = GPU_MMU_FEATURES_PA_BITS(ptdev->gpu_info.mmu_features); @@ -353,6 +262,9 @@ int panthor_gpu_flush_caches(struct panthor_device *ptdev, bool timedout = false; unsigned long flags; + /* Serialize cache flush operations. */ + guard(mutex)(&ptdev->gpu->cache_flush_lock); + spin_lock_irqsave(&ptdev->gpu->reqs_lock, flags); if (!drm_WARN_ON(&ptdev->base, ptdev->gpu->pending_reqs & GPU_IRQ_CLEAN_CACHES_COMPLETED)) { diff --git a/drivers/gpu/drm/panthor/panthor_hw.c b/drivers/gpu/drm/panthor/panthor_hw.c new file mode 100644 index 000000000000..4f2858114e5e --- /dev/null +++ b/drivers/gpu/drm/panthor/panthor_hw.c @@ -0,0 +1,125 @@ +// SPDX-License-Identifier: GPL-2.0 or MIT +/* Copyright 2025 ARM Limited. All rights reserved. */ + +#include "panthor_device.h" +#include "panthor_hw.h" +#include "panthor_regs.h" + +#define GPU_PROD_ID_MAKE(arch_major, prod_major) \ + (((arch_major) << 24) | (prod_major)) + +static char *get_gpu_model_name(struct panthor_device *ptdev) +{ + const u32 gpu_id = ptdev->gpu_info.gpu_id; + const u32 product_id = GPU_PROD_ID_MAKE(GPU_ARCH_MAJOR(gpu_id), + GPU_PROD_MAJOR(gpu_id)); + const bool ray_intersection = !!(ptdev->gpu_info.gpu_features & + GPU_FEATURES_RAY_INTERSECTION); + const u8 shader_core_count = hweight64(ptdev->gpu_info.shader_present); + + switch (product_id) { + case GPU_PROD_ID_MAKE(10, 2): + return "Mali-G710"; + case GPU_PROD_ID_MAKE(10, 3): + return "Mali-G510"; + case GPU_PROD_ID_MAKE(10, 4): + return "Mali-G310"; + case GPU_PROD_ID_MAKE(10, 7): + return "Mali-G610"; + case GPU_PROD_ID_MAKE(11, 2): + if (shader_core_count > 10 && ray_intersection) + return "Mali-G715-Immortalis"; + else if (shader_core_count >= 7) + return "Mali-G715"; + + fallthrough; + case GPU_PROD_ID_MAKE(11, 3): + return "Mali-G615"; + case GPU_PROD_ID_MAKE(12, 0): + if (shader_core_count >= 10 && ray_intersection) + return "Mali-G720-Immortalis"; + else if (shader_core_count >= 6) + return "Mali-G720"; + + fallthrough; + case GPU_PROD_ID_MAKE(12, 1): + return "Mali-G620"; + case GPU_PROD_ID_MAKE(13, 0): + if (shader_core_count >= 10 && ray_intersection) + return "Mali-G925-Immortalis"; + else if (shader_core_count >= 6) + return "Mali-G725"; + + fallthrough; + case GPU_PROD_ID_MAKE(13, 1): + return "Mali-G625"; + } + + return "(Unknown Mali GPU)"; +} + +static void panthor_gpu_info_init(struct panthor_device *ptdev) +{ + unsigned int i; + + ptdev->gpu_info.gpu_id = gpu_read(ptdev, GPU_ID); + ptdev->gpu_info.csf_id = gpu_read(ptdev, GPU_CSF_ID); + ptdev->gpu_info.gpu_rev = gpu_read(ptdev, GPU_REVID); + ptdev->gpu_info.core_features = gpu_read(ptdev, GPU_CORE_FEATURES); + ptdev->gpu_info.l2_features = gpu_read(ptdev, GPU_L2_FEATURES); + ptdev->gpu_info.tiler_features = gpu_read(ptdev, GPU_TILER_FEATURES); + ptdev->gpu_info.mem_features = gpu_read(ptdev, GPU_MEM_FEATURES); + ptdev->gpu_info.mmu_features = gpu_read(ptdev, GPU_MMU_FEATURES); + ptdev->gpu_info.thread_features = gpu_read(ptdev, GPU_THREAD_FEATURES); + ptdev->gpu_info.max_threads = gpu_read(ptdev, GPU_THREAD_MAX_THREADS); + ptdev->gpu_info.thread_max_workgroup_size = gpu_read(ptdev, GPU_THREAD_MAX_WORKGROUP_SIZE); + ptdev->gpu_info.thread_max_barrier_size = gpu_read(ptdev, GPU_THREAD_MAX_BARRIER_SIZE); + ptdev->gpu_info.coherency_features = gpu_read(ptdev, GPU_COHERENCY_FEATURES); + for (i = 0; i < 4; i++) + ptdev->gpu_info.texture_features[i] = gpu_read(ptdev, GPU_TEXTURE_FEATURES(i)); + + ptdev->gpu_info.as_present = gpu_read(ptdev, GPU_AS_PRESENT); + + ptdev->gpu_info.shader_present = gpu_read64(ptdev, GPU_SHADER_PRESENT); + ptdev->gpu_info.tiler_present = gpu_read64(ptdev, GPU_TILER_PRESENT); + ptdev->gpu_info.l2_present = gpu_read64(ptdev, GPU_L2_PRESENT); + + /* Introduced in arch 11.x */ + ptdev->gpu_info.gpu_features = gpu_read64(ptdev, GPU_FEATURES); +} + +static void panthor_hw_info_init(struct panthor_device *ptdev) +{ + u32 major, minor, status; + + panthor_gpu_info_init(ptdev); + + major = GPU_VER_MAJOR(ptdev->gpu_info.gpu_id); + minor = GPU_VER_MINOR(ptdev->gpu_info.gpu_id); + status = GPU_VER_STATUS(ptdev->gpu_info.gpu_id); + + drm_info(&ptdev->base, + "%s id 0x%x major 0x%x minor 0x%x status 0x%x", + get_gpu_model_name(ptdev), ptdev->gpu_info.gpu_id >> 16, + major, minor, status); + + drm_info(&ptdev->base, + "Features: L2:%#x Tiler:%#x Mem:%#x MMU:%#x AS:%#x", + ptdev->gpu_info.l2_features, + ptdev->gpu_info.tiler_features, + ptdev->gpu_info.mem_features, + ptdev->gpu_info.mmu_features, + ptdev->gpu_info.as_present); + + drm_info(&ptdev->base, + "shader_present=0x%0llx l2_present=0x%0llx tiler_present=0x%0llx", + ptdev->gpu_info.shader_present, ptdev->gpu_info.l2_present, + ptdev->gpu_info.tiler_present); +} + +int panthor_hw_init(struct panthor_device *ptdev) +{ + panthor_hw_info_init(ptdev); + + return 0; +} diff --git a/drivers/gpu/drm/panthor/panthor_hw.h b/drivers/gpu/drm/panthor/panthor_hw.h new file mode 100644 index 000000000000..0af6acc6aa6a --- /dev/null +++ b/drivers/gpu/drm/panthor/panthor_hw.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 or MIT */ +/* Copyright 2025 ARM Limited. All rights reserved. */ + +#ifndef __PANTHOR_HW_H__ +#define __PANTHOR_HW_H__ + +struct panthor_device; + +int panthor_hw_init(struct panthor_device *ptdev); + +#endif /* __PANTHOR_HW_H__ */ diff --git a/drivers/gpu/drm/panthor/panthor_mmu.c b/drivers/gpu/drm/panthor/panthor_mmu.c index 4140f697ba5a..6dec4354e378 100644 --- a/drivers/gpu/drm/panthor/panthor_mmu.c +++ b/drivers/gpu/drm/panthor/panthor_mmu.c @@ -29,6 +29,7 @@ #include "panthor_device.h" #include "panthor_gem.h" +#include "panthor_gpu.h" #include "panthor_heap.h" #include "panthor_mmu.h" #include "panthor_regs.h" @@ -571,8 +572,24 @@ static void lock_region(struct panthor_device *ptdev, u32 as_nr, static int mmu_hw_do_operation_locked(struct panthor_device *ptdev, int as_nr, u64 iova, u64 size, u32 op) { + const u32 l2_flush_op = CACHE_CLEAN | CACHE_INV; + u32 lsc_flush_op; + int ret; + lockdep_assert_held(&ptdev->mmu->as.slots_lock); + switch (op) { + case AS_COMMAND_FLUSH_MEM: + lsc_flush_op = CACHE_CLEAN | CACHE_INV; + break; + case AS_COMMAND_FLUSH_PT: + lsc_flush_op = 0; + break; + default: + drm_WARN(&ptdev->base, 1, "Unexpected AS_COMMAND: %d", op); + return -EINVAL; + } + if (as_nr < 0) return 0; @@ -582,13 +599,24 @@ static int mmu_hw_do_operation_locked(struct panthor_device *ptdev, int as_nr, * power it up */ - if (op != AS_COMMAND_UNLOCK) - lock_region(ptdev, as_nr, iova, size); + lock_region(ptdev, as_nr, iova, size); - /* Run the MMU operation */ - write_cmd(ptdev, as_nr, op); + ret = wait_ready(ptdev, as_nr); + if (ret) + return ret; - /* Wait for the flush to complete */ + ret = panthor_gpu_flush_caches(ptdev, l2_flush_op, lsc_flush_op, 0); + if (ret) + return ret; + + /* + * Explicitly unlock the region as the AS is not unlocked automatically + * at the end of the GPU_CONTROL cache flush command, unlike + * AS_COMMAND_FLUSH_MEM or AS_COMMAND_FLUSH_PT. + */ + write_cmd(ptdev, as_nr, AS_COMMAND_UNLOCK); + + /* Wait for the unlock command to complete */ return wait_ready(ptdev, as_nr); } @@ -1074,9 +1102,9 @@ static void panthor_vm_bo_put(struct drm_gpuvm_bo *vm_bo) * GEM vm_bo list. */ dma_resv_lock(drm_gpuvm_resv(vm), NULL); - mutex_lock(&bo->gpuva_list_lock); + mutex_lock(&bo->base.base.gpuva.lock); unpin = drm_gpuvm_bo_put(vm_bo); - mutex_unlock(&bo->gpuva_list_lock); + mutex_unlock(&bo->base.base.gpuva.lock); dma_resv_unlock(drm_gpuvm_resv(vm)); /* If the vm_bo object was destroyed, release the pin reference that @@ -1194,7 +1222,7 @@ static int panthor_vm_prepare_map_op_ctx(struct panthor_vm_op_ctx *op_ctx, (flags & DRM_PANTHOR_VM_BIND_OP_TYPE_MASK) != DRM_PANTHOR_VM_BIND_OP_TYPE_MAP) return -EINVAL; - /* Make sure the VA and size are aligned and in-bounds. */ + /* Make sure the VA and size are in-bounds. */ if (size > bo->base.base.size || offset > bo->base.base.size - size) return -EINVAL; @@ -1249,9 +1277,9 @@ static int panthor_vm_prepare_map_op_ctx(struct panthor_vm_op_ctx *op_ctx, * calling this function. */ dma_resv_lock(panthor_vm_resv(vm), NULL); - mutex_lock(&bo->gpuva_list_lock); + mutex_lock(&bo->base.base.gpuva.lock); op_ctx->map.vm_bo = drm_gpuvm_bo_obtain_prealloc(preallocated_vm_bo); - mutex_unlock(&bo->gpuva_list_lock); + mutex_unlock(&bo->base.base.gpuva.lock); dma_resv_unlock(panthor_vm_resv(vm)); /* If the a vm_bo for this <VM,BO> combination exists, it already @@ -2003,10 +2031,10 @@ static void panthor_vma_link(struct panthor_vm *vm, { struct panthor_gem_object *bo = to_panthor_bo(vma->base.gem.obj); - mutex_lock(&bo->gpuva_list_lock); + mutex_lock(&bo->base.base.gpuva.lock); drm_gpuva_link(&vma->base, vm_bo); drm_WARN_ON(&vm->ptdev->base, drm_gpuvm_bo_put(vm_bo)); - mutex_unlock(&bo->gpuva_list_lock); + mutex_unlock(&bo->base.base.gpuva.lock); } static void panthor_vma_unlink(struct panthor_vm *vm, @@ -2015,9 +2043,9 @@ static void panthor_vma_unlink(struct panthor_vm *vm, struct panthor_gem_object *bo = to_panthor_bo(vma->base.gem.obj); struct drm_gpuvm_bo *vm_bo = drm_gpuvm_bo_get(vma->base.vm_bo); - mutex_lock(&bo->gpuva_list_lock); + mutex_lock(&bo->base.base.gpuva.lock); drm_gpuva_unlink(&vma->base); - mutex_unlock(&bo->gpuva_list_lock); + mutex_unlock(&bo->base.base.gpuva.lock); /* drm_gpuva_unlink() release the vm_bo, but we manually retained it * when entering this function, so we can implement deferred VMA @@ -2169,15 +2197,22 @@ panthor_vm_exec_op(struct panthor_vm *vm, struct panthor_vm_op_ctx *op, mutex_lock(&vm->op_lock); vm->op_ctx = op; switch (op_type) { - case DRM_PANTHOR_VM_BIND_OP_TYPE_MAP: + case DRM_PANTHOR_VM_BIND_OP_TYPE_MAP: { + const struct drm_gpuvm_map_req map_req = { + .map.va.addr = op->va.addr, + .map.va.range = op->va.range, + .map.gem.obj = op->map.vm_bo->obj, + .map.gem.offset = op->map.bo_offset, + }; + if (vm->unusable) { ret = -EINVAL; break; } - ret = drm_gpuvm_sm_map(&vm->base, vm, op->va.addr, op->va.range, - op->map.vm_bo->obj, op->map.bo_offset); + ret = drm_gpuvm_sm_map(&vm->base, vm, &map_req); break; + } case DRM_PANTHOR_VM_BIND_OP_TYPE_UNMAP: ret = drm_gpuvm_sm_unmap(&vm->base, vm, op->va.addr, op->va.range); @@ -2380,8 +2415,9 @@ panthor_vm_create(struct panthor_device *ptdev, bool for_mcu, * to be handled the same way user VMAs are. */ drm_gpuvm_init(&vm->base, for_mcu ? "panthor-MCU-VM" : "panthor-GPU-VM", - DRM_GPUVM_RESV_PROTECTED, &ptdev->base, dummy_gem, - min_va, va_range, 0, 0, &panthor_gpuvm_ops); + DRM_GPUVM_RESV_PROTECTED | DRM_GPUVM_IMMEDIATE_MODE, + &ptdev->base, dummy_gem, min_va, va_range, 0, 0, + &panthor_gpuvm_ops); drm_gem_object_put(dummy_gem); return vm; @@ -2411,7 +2447,7 @@ panthor_vm_bind_prepare_op_ctx(struct drm_file *file, int ret; /* Aligned on page size. */ - if (!IS_ALIGNED(op->va | op->size, vm_pgsz)) + if (!IS_ALIGNED(op->va | op->size | op->bo_offset, vm_pgsz)) return -EINVAL; switch (op->flags & DRM_PANTHOR_VM_BIND_OP_TYPE_MASK) { diff --git a/drivers/gpu/drm/panthor/panthor_regs.h b/drivers/gpu/drm/panthor/panthor_regs.h index 48bbfd40138c..8bee76d01bf8 100644 --- a/drivers/gpu/drm/panthor/panthor_regs.h +++ b/drivers/gpu/drm/panthor/panthor_regs.h @@ -70,6 +70,9 @@ #define GPU_PWR_OVERRIDE0 0x54 #define GPU_PWR_OVERRIDE1 0x58 +#define GPU_FEATURES 0x60 +#define GPU_FEATURES_RAY_INTERSECTION BIT(2) + #define GPU_TIMESTAMP_OFFSET 0x88 #define GPU_CYCLE_COUNT 0x90 #define GPU_TIMESTAMP 0x98 diff --git a/drivers/gpu/drm/panthor/panthor_sched.c b/drivers/gpu/drm/panthor/panthor_sched.c index df76653e649a..3d1f57e3990f 100644 --- a/drivers/gpu/drm/panthor/panthor_sched.c +++ b/drivers/gpu/drm/panthor/panthor_sched.c @@ -641,6 +641,15 @@ struct panthor_group { size_t kbo_sizes; } fdinfo; + /** @task_info: Info of current->group_leader that created the group. */ + struct { + /** @task_info.pid: pid of current->group_leader */ + pid_t pid; + + /** @task_info.comm: comm of current->group_leader */ + char comm[TASK_COMM_LEN]; + } task_info; + /** @state: Group state. */ enum panthor_group_state state; @@ -1354,8 +1363,12 @@ cs_slot_process_fatal_event_locked(struct panthor_device *ptdev, fatal = cs_iface->output->fatal; info = cs_iface->output->fatal_info; - if (group) + if (group) { + drm_warn(&ptdev->base, "CS_FATAL: pid=%d, comm=%s\n", + group->task_info.pid, group->task_info.comm); + group->fatal_queues |= BIT(cs_id); + } if (CS_EXCEPTION_TYPE(fatal) == DRM_PANTHOR_EXCEPTION_CS_UNRECOVERABLE) { /* If this exception is unrecoverable, queue a reset, and make @@ -1415,6 +1428,11 @@ cs_slot_process_fault_event_locked(struct panthor_device *ptdev, spin_unlock(&queue->fence_ctx.lock); } + if (group) { + drm_warn(&ptdev->base, "CS_FAULT: pid=%d, comm=%s\n", + group->task_info.pid, group->task_info.comm); + } + drm_warn(&ptdev->base, "CSG slot %d CS slot: %d\n" "CS_FAULT.EXCEPTION_TYPE: 0x%x (%s)\n" @@ -1631,11 +1649,15 @@ csg_slot_process_progress_timer_event_locked(struct panthor_device *ptdev, u32 c lockdep_assert_held(&sched->lock); - drm_warn(&ptdev->base, "CSG slot %d progress timeout\n", csg_id); - group = csg_slot->group; - if (!drm_WARN_ON(&ptdev->base, !group)) + if (!drm_WARN_ON(&ptdev->base, !group)) { + drm_warn(&ptdev->base, "CSG_PROGRESS_TIMER_EVENT: pid=%d, comm=%s\n", + group->task_info.pid, group->task_info.comm); + group->timedout = true; + } + + drm_warn(&ptdev->base, "CSG slot %d progress timeout\n", csg_id); sched_queue_delayed_work(sched, tick, 0); } @@ -3217,7 +3239,8 @@ queue_timedout_job(struct drm_sched_job *sched_job) struct panthor_scheduler *sched = ptdev->scheduler; struct panthor_queue *queue = group->queues[job->queue_idx]; - drm_warn(&ptdev->base, "job timeout\n"); + drm_warn(&ptdev->base, "job timeout: pid=%d, comm=%s, seqno=%llu\n", + group->task_info.pid, group->task_info.comm, job->done_fence->seqno); drm_WARN_ON(&ptdev->base, atomic_read(&sched->reset.in_progress)); @@ -3388,6 +3411,14 @@ err_free_queue: return ERR_PTR(ret); } +static void group_init_task_info(struct panthor_group *group) +{ + struct task_struct *task = current->group_leader; + + group->task_info.pid = task->pid; + get_task_comm(group->task_info.comm, task); +} + static void add_group_kbo_sizes(struct panthor_device *ptdev, struct panthor_group *group) { @@ -3539,6 +3570,8 @@ int panthor_group_create(struct panthor_file *pfile, add_group_kbo_sizes(group->ptdev, group); spin_lock_init(&group->fdinfo.lock); + group_init_task_info(group); + return gid; err_put_group: |