From 5ec7e02854b3b9b55936c3b44b8acfb85e333f49 Mon Sep 17 00:00:00 2001 From: Felix Kuehling Date: Thu, 15 Mar 2018 17:27:51 -0400 Subject: [PATCH] drm/amdkfd: Add ioctls for GPUVM memory management MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit v2: * Fix error handling after kfd_bind_process_to_device in kfd_ioctl_map_memory_to_gpu v3: * Add ioctl to acquire VM from a DRM FD v4: * Return number of successful map/unmap operations in failure cases * Facilitate partial retry after failed map/unmap * Added comments with parameter descriptions to new APIs * Defined AMDKFD_IOC_FREE_MEMORY_OF_GPU write-only Signed-off-by: Felix Kuehling Acked-by: Christian König Signed-off-by: Oded Gabbay --- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 377 ++++++++++++++++++ drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 8 + .../gpu/drm/amd/include/kgd_kfd_interface.h | 2 + include/uapi/linux/kfd_ioctl.h | 97 ++++- 4 files changed, 483 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 7d4009418ec3..a563ff2ca7dd 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include @@ -1046,6 +1047,366 @@ static int kfd_ioctl_get_tile_config(struct file *filep, return 0; } +static int kfd_ioctl_acquire_vm(struct file *filep, struct kfd_process *p, + void *data) +{ + struct kfd_ioctl_acquire_vm_args *args = data; + struct kfd_process_device *pdd; + struct kfd_dev *dev; + struct file *drm_file; + int ret; + + dev = kfd_device_by_id(args->gpu_id); + if (!dev) + return -EINVAL; + + drm_file = fget(args->drm_fd); + if (!drm_file) + return -EINVAL; + + mutex_lock(&p->mutex); + + pdd = kfd_get_process_device_data(dev, p); + if (!pdd) { + ret = -EINVAL; + goto err_unlock; + } + + if (pdd->drm_file) { + ret = pdd->drm_file == drm_file ? 0 : -EBUSY; + goto err_unlock; + } + + ret = kfd_process_device_init_vm(pdd, drm_file); + if (ret) + goto err_unlock; + /* On success, the PDD keeps the drm_file reference */ + mutex_unlock(&p->mutex); + + return 0; + +err_unlock: + mutex_unlock(&p->mutex); + fput(drm_file); + return ret; +} + +bool kfd_dev_is_large_bar(struct kfd_dev *dev) +{ + struct kfd_local_mem_info mem_info; + + if (dev->device_info->needs_iommu_device) + return false; + + dev->kfd2kgd->get_local_mem_info(dev->kgd, &mem_info); + if (mem_info.local_mem_size_private == 0 && + mem_info.local_mem_size_public > 0) + return true; + return false; +} + +static int kfd_ioctl_alloc_memory_of_gpu(struct file *filep, + struct kfd_process *p, void *data) +{ + struct kfd_ioctl_alloc_memory_of_gpu_args *args = data; + struct kfd_process_device *pdd; + void *mem; + struct kfd_dev *dev; + int idr_handle; + long err; + uint64_t offset = args->mmap_offset; + uint32_t flags = args->flags; + + if (args->size == 0) + return -EINVAL; + + dev = kfd_device_by_id(args->gpu_id); + if (!dev) + return -EINVAL; + + if ((flags & KFD_IOC_ALLOC_MEM_FLAGS_PUBLIC) && + (flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) && + !kfd_dev_is_large_bar(dev)) { + pr_err("Alloc host visible vram on small bar is not allowed\n"); + return -EINVAL; + } + + mutex_lock(&p->mutex); + + pdd = kfd_bind_process_to_device(dev, p); + if (IS_ERR(pdd)) { + err = PTR_ERR(pdd); + goto err_unlock; + } + + err = dev->kfd2kgd->alloc_memory_of_gpu( + dev->kgd, args->va_addr, args->size, + pdd->vm, (struct kgd_mem **) &mem, &offset, + flags); + + if (err) + goto err_unlock; + + idr_handle = kfd_process_device_create_obj_handle(pdd, mem); + if (idr_handle < 0) { + err = -EFAULT; + goto err_free; + } + + mutex_unlock(&p->mutex); + + args->handle = MAKE_HANDLE(args->gpu_id, idr_handle); + args->mmap_offset = offset; + + return 0; + +err_free: + dev->kfd2kgd->free_memory_of_gpu(dev->kgd, (struct kgd_mem *)mem); +err_unlock: + mutex_unlock(&p->mutex); + return err; +} + +static int kfd_ioctl_free_memory_of_gpu(struct file *filep, + struct kfd_process *p, void *data) +{ + struct kfd_ioctl_free_memory_of_gpu_args *args = data; + struct kfd_process_device *pdd; + void *mem; + struct kfd_dev *dev; + int ret; + + dev = kfd_device_by_id(GET_GPU_ID(args->handle)); + if (!dev) + return -EINVAL; + + mutex_lock(&p->mutex); + + pdd = kfd_get_process_device_data(dev, p); + if (!pdd) { + pr_err("Process device data doesn't exist\n"); + ret = -EINVAL; + goto err_unlock; + } + + mem = kfd_process_device_translate_handle( + pdd, GET_IDR_HANDLE(args->handle)); + if (!mem) { + ret = -EINVAL; + goto err_unlock; + } + + ret = dev->kfd2kgd->free_memory_of_gpu(dev->kgd, (struct kgd_mem *)mem); + + /* If freeing the buffer failed, leave the handle in place for + * clean-up during process tear-down. + */ + if (!ret) + kfd_process_device_remove_obj_handle( + pdd, GET_IDR_HANDLE(args->handle)); + +err_unlock: + mutex_unlock(&p->mutex); + return ret; +} + +static int kfd_ioctl_map_memory_to_gpu(struct file *filep, + struct kfd_process *p, void *data) +{ + struct kfd_ioctl_map_memory_to_gpu_args *args = data; + struct kfd_process_device *pdd, *peer_pdd; + void *mem; + struct kfd_dev *dev, *peer; + long err = 0; + int i; + uint32_t *devices_arr = NULL; + + dev = kfd_device_by_id(GET_GPU_ID(args->handle)); + if (!dev) + return -EINVAL; + + if (!args->n_devices) { + pr_debug("Device IDs array empty\n"); + return -EINVAL; + } + if (args->n_success > args->n_devices) { + pr_debug("n_success exceeds n_devices\n"); + return -EINVAL; + } + + devices_arr = kmalloc(args->n_devices * sizeof(*devices_arr), + GFP_KERNEL); + if (!devices_arr) + return -ENOMEM; + + err = copy_from_user(devices_arr, + (void __user *)args->device_ids_array_ptr, + args->n_devices * sizeof(*devices_arr)); + if (err != 0) { + err = -EFAULT; + goto copy_from_user_failed; + } + + mutex_lock(&p->mutex); + + pdd = kfd_bind_process_to_device(dev, p); + if (IS_ERR(pdd)) { + err = PTR_ERR(pdd); + goto bind_process_to_device_failed; + } + + mem = kfd_process_device_translate_handle(pdd, + GET_IDR_HANDLE(args->handle)); + if (!mem) { + err = -ENOMEM; + goto get_mem_obj_from_handle_failed; + } + + for (i = args->n_success; i < args->n_devices; i++) { + peer = kfd_device_by_id(devices_arr[i]); + if (!peer) { + pr_debug("Getting device by id failed for 0x%x\n", + devices_arr[i]); + err = -EINVAL; + goto get_mem_obj_from_handle_failed; + } + + peer_pdd = kfd_bind_process_to_device(peer, p); + if (IS_ERR(peer_pdd)) { + err = PTR_ERR(peer_pdd); + goto get_mem_obj_from_handle_failed; + } + err = peer->kfd2kgd->map_memory_to_gpu( + peer->kgd, (struct kgd_mem *)mem, peer_pdd->vm); + if (err) { + pr_err("Failed to map to gpu %d/%d\n", + i, args->n_devices); + goto map_memory_to_gpu_failed; + } + args->n_success = i+1; + } + + mutex_unlock(&p->mutex); + + err = dev->kfd2kgd->sync_memory(dev->kgd, (struct kgd_mem *) mem, true); + if (err) { + pr_debug("Sync memory failed, wait interrupted by user signal\n"); + goto sync_memory_failed; + } + + /* Flush TLBs after waiting for the page table updates to complete */ + for (i = 0; i < args->n_devices; i++) { + peer = kfd_device_by_id(devices_arr[i]); + if (WARN_ON_ONCE(!peer)) + continue; + peer_pdd = kfd_get_process_device_data(peer, p); + if (WARN_ON_ONCE(!peer_pdd)) + continue; + kfd_flush_tlb(peer_pdd); + } + + kfree(devices_arr); + + return err; + +bind_process_to_device_failed: +get_mem_obj_from_handle_failed: +map_memory_to_gpu_failed: + mutex_unlock(&p->mutex); +copy_from_user_failed: +sync_memory_failed: + kfree(devices_arr); + + return err; +} + +static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep, + struct kfd_process *p, void *data) +{ + struct kfd_ioctl_unmap_memory_from_gpu_args *args = data; + struct kfd_process_device *pdd, *peer_pdd; + void *mem; + struct kfd_dev *dev, *peer; + long err = 0; + uint32_t *devices_arr = NULL, i; + + dev = kfd_device_by_id(GET_GPU_ID(args->handle)); + if (!dev) + return -EINVAL; + + if (!args->n_devices) { + pr_debug("Device IDs array empty\n"); + return -EINVAL; + } + if (args->n_success > args->n_devices) { + pr_debug("n_success exceeds n_devices\n"); + return -EINVAL; + } + + devices_arr = kmalloc(args->n_devices * sizeof(*devices_arr), + GFP_KERNEL); + if (!devices_arr) + return -ENOMEM; + + err = copy_from_user(devices_arr, + (void __user *)args->device_ids_array_ptr, + args->n_devices * sizeof(*devices_arr)); + if (err != 0) { + err = -EFAULT; + goto copy_from_user_failed; + } + + mutex_lock(&p->mutex); + + pdd = kfd_get_process_device_data(dev, p); + if (!pdd) { + err = PTR_ERR(pdd); + goto bind_process_to_device_failed; + } + + mem = kfd_process_device_translate_handle(pdd, + GET_IDR_HANDLE(args->handle)); + if (!mem) { + err = -ENOMEM; + goto get_mem_obj_from_handle_failed; + } + + for (i = args->n_success; i < args->n_devices; i++) { + peer = kfd_device_by_id(devices_arr[i]); + if (!peer) { + err = -EINVAL; + goto get_mem_obj_from_handle_failed; + } + + peer_pdd = kfd_get_process_device_data(peer, p); + if (!peer_pdd) { + err = -ENODEV; + goto get_mem_obj_from_handle_failed; + } + err = dev->kfd2kgd->unmap_memory_to_gpu( + peer->kgd, (struct kgd_mem *)mem, peer_pdd->vm); + if (err) { + pr_err("Failed to unmap from gpu %d/%d\n", + i, args->n_devices); + goto unmap_memory_from_gpu_failed; + } + args->n_success = i+1; + } + kfree(devices_arr); + + mutex_unlock(&p->mutex); + + return 0; + +bind_process_to_device_failed: +get_mem_obj_from_handle_failed: +unmap_memory_from_gpu_failed: + mutex_unlock(&p->mutex); +copy_from_user_failed: + kfree(devices_arr); + return err; +} + #define AMDKFD_IOCTL_DEF(ioctl, _func, _flags) \ [_IOC_NR(ioctl)] = {.cmd = ioctl, .func = _func, .flags = _flags, \ .cmd_drv = 0, .name = #ioctl} @@ -1111,6 +1472,22 @@ static const struct amdkfd_ioctl_desc amdkfd_ioctls[] = { AMDKFD_IOCTL_DEF(AMDKFD_IOC_GET_PROCESS_APERTURES_NEW, kfd_ioctl_get_process_apertures_new, 0), + + AMDKFD_IOCTL_DEF(AMDKFD_IOC_ACQUIRE_VM, + kfd_ioctl_acquire_vm, 0), + + AMDKFD_IOCTL_DEF(AMDKFD_IOC_ALLOC_MEMORY_OF_GPU, + kfd_ioctl_alloc_memory_of_gpu, 0), + + AMDKFD_IOCTL_DEF(AMDKFD_IOC_FREE_MEMORY_OF_GPU, + kfd_ioctl_free_memory_of_gpu, 0), + + AMDKFD_IOCTL_DEF(AMDKFD_IOC_MAP_MEMORY_TO_GPU, + kfd_ioctl_map_memory_to_gpu, 0), + + AMDKFD_IOCTL_DEF(AMDKFD_IOC_UNMAP_MEMORY_FROM_GPU, + kfd_ioctl_unmap_memory_from_gpu, 0), + }; #define AMDKFD_CORE_IOCTL_COUNT ARRAY_SIZE(amdkfd_ioctls) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index aaed005ce1f5..1542807373d7 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -509,6 +509,14 @@ struct qcm_process_device { int kgd2kfd_schedule_evict_and_restore_process(struct mm_struct *mm, struct dma_fence *fence); +/* 8 byte handle containing GPU ID in the most significant 4 bytes and + * idr_handle in the least significant 4 bytes + */ +#define MAKE_HANDLE(gpu_id, idr_handle) \ + (((uint64_t)(gpu_id) << 32) + idr_handle) +#define GET_GPU_ID(handle) (handle >> 32) +#define GET_IDR_HANDLE(handle) (handle & 0xFFFFFFFF) + enum kfd_pdd_bound { PDD_UNBOUND = 0, PDD_BOUND, diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h index b1f35c8be2cf..237289a72bb7 100644 --- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h +++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h @@ -130,6 +130,7 @@ struct tile_config { /* * Allocation flag domains + * NOTE: This must match the corresponding definitions in kfd_ioctl.h. */ #define ALLOC_MEM_FLAGS_VRAM (1 << 0) #define ALLOC_MEM_FLAGS_GTT (1 << 1) @@ -138,6 +139,7 @@ struct tile_config { /* * Allocation flags attributes/access options. + * NOTE: This must match the corresponding definitions in kfd_ioctl.h. */ #define ALLOC_MEM_FLAGS_WRITABLE (1 << 31) #define ALLOC_MEM_FLAGS_EXECUTABLE (1 << 30) diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 52014370e2e5..b4f5073dbac2 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -286,6 +286,86 @@ struct kfd_ioctl_set_trap_handler_args { __u32 pad; }; +struct kfd_ioctl_acquire_vm_args { + __u32 drm_fd; /* to KFD */ + __u32 gpu_id; /* to KFD */ +}; + +/* Allocation flags: memory types */ +#define KFD_IOC_ALLOC_MEM_FLAGS_VRAM (1 << 0) +#define KFD_IOC_ALLOC_MEM_FLAGS_GTT (1 << 1) +#define KFD_IOC_ALLOC_MEM_FLAGS_USERPTR (1 << 2) +#define KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL (1 << 3) +/* Allocation flags: attributes/access options */ +#define KFD_IOC_ALLOC_MEM_FLAGS_WRITABLE (1 << 31) +#define KFD_IOC_ALLOC_MEM_FLAGS_EXECUTABLE (1 << 30) +#define KFD_IOC_ALLOC_MEM_FLAGS_PUBLIC (1 << 29) +#define KFD_IOC_ALLOC_MEM_FLAGS_NO_SUBSTITUTE (1 << 28) +#define KFD_IOC_ALLOC_MEM_FLAGS_AQL_QUEUE_MEM (1 << 27) +#define KFD_IOC_ALLOC_MEM_FLAGS_COHERENT (1 << 26) + +/* Allocate memory for later SVM (shared virtual memory) mapping. + * + * @va_addr: virtual address of the memory to be allocated + * all later mappings on all GPUs will use this address + * @size: size in bytes + * @handle: buffer handle returned to user mode, used to refer to + * this allocation for mapping, unmapping and freeing + * @mmap_offset: for CPU-mapping the allocation by mmapping a render node + * for userptrs this is overloaded to specify the CPU address + * @gpu_id: device identifier + * @flags: memory type and attributes. See KFD_IOC_ALLOC_MEM_FLAGS above + */ +struct kfd_ioctl_alloc_memory_of_gpu_args { + __u64 va_addr; /* to KFD */ + __u64 size; /* to KFD */ + __u64 handle; /* from KFD */ + __u64 mmap_offset; /* to KFD (userptr), from KFD (mmap offset) */ + __u32 gpu_id; /* to KFD */ + __u32 flags; +}; + +/* Free memory allocated with kfd_ioctl_alloc_memory_of_gpu + * + * @handle: memory handle returned by alloc + */ +struct kfd_ioctl_free_memory_of_gpu_args { + __u64 handle; /* to KFD */ +}; + +/* Map memory to one or more GPUs + * + * @handle: memory handle returned by alloc + * @device_ids_array_ptr: array of gpu_ids (__u32 per device) + * @n_devices: number of devices in the array + * @n_success: number of devices mapped successfully + * + * @n_success returns information to the caller how many devices from + * the start of the array have mapped the buffer successfully. It can + * be passed into a subsequent retry call to skip those devices. For + * the first call the caller should initialize it to 0. + * + * If the ioctl completes with return code 0 (success), n_success == + * n_devices. + */ +struct kfd_ioctl_map_memory_to_gpu_args { + __u64 handle; /* to KFD */ + __u64 device_ids_array_ptr; /* to KFD */ + __u32 n_devices; /* to KFD */ + __u32 n_success; /* to/from KFD */ +}; + +/* Unmap memory from one or more GPUs + * + * same arguments as for mapping + */ +struct kfd_ioctl_unmap_memory_from_gpu_args { + __u64 handle; /* to KFD */ + __u64 device_ids_array_ptr; /* to KFD */ + __u32 n_devices; /* to KFD */ + __u32 n_success; /* to/from KFD */ +}; + #define AMDKFD_IOCTL_BASE 'K' #define AMDKFD_IO(nr) _IO(AMDKFD_IOCTL_BASE, nr) #define AMDKFD_IOR(nr, type) _IOR(AMDKFD_IOCTL_BASE, nr, type) @@ -353,7 +433,22 @@ struct kfd_ioctl_set_trap_handler_args { AMDKFD_IOWR(0x14, \ struct kfd_ioctl_get_process_apertures_new_args) +#define AMDKFD_IOC_ACQUIRE_VM \ + AMDKFD_IOW(0x15, struct kfd_ioctl_acquire_vm_args) + +#define AMDKFD_IOC_ALLOC_MEMORY_OF_GPU \ + AMDKFD_IOWR(0x16, struct kfd_ioctl_alloc_memory_of_gpu_args) + +#define AMDKFD_IOC_FREE_MEMORY_OF_GPU \ + AMDKFD_IOW(0x17, struct kfd_ioctl_free_memory_of_gpu_args) + +#define AMDKFD_IOC_MAP_MEMORY_TO_GPU \ + AMDKFD_IOWR(0x18, struct kfd_ioctl_map_memory_to_gpu_args) + +#define AMDKFD_IOC_UNMAP_MEMORY_FROM_GPU \ + AMDKFD_IOWR(0x19, struct kfd_ioctl_unmap_memory_from_gpu_args) + #define AMDKFD_COMMAND_START 0x01 -#define AMDKFD_COMMAND_END 0x15 +#define AMDKFD_COMMAND_END 0x1A #endif -- 2.30.2