From: Tomeu Vizoso Date: Mon, 21 Jul 2025 09:17:32 +0000 (+0200) Subject: accel/rocket: Add IOCTLs for synchronizing memory accesses X-Git-Url: https://www.infradead.org/git/?a=commitdiff_plain;h=525ad89dd90434d529b76a87b1c653a69fedc416;p=users%2Fhch%2Fmisc.git accel/rocket: Add IOCTLs for synchronizing memory accesses The NPU cores have their own access to the memory bus, and this isn't cache coherent with the CPUs. Add IOCTLs so userspace can mark when the caches need to be flushed, and also when a writer job needs to be waited for before the buffer can be accessed from the CPU. Initially based on the same IOCTLs from the Etnaviv driver. v2: - Don't break UABI by reordering the IOCTL IDs (Jeff Hugo) v3: - Check that padding fields in IOCTLs are zero (Jeff Hugo) v6: - Fix conversion logic to make sure we use DMA_BIDIRECTIONAL when needed (Lucas Stach) v8: - Always sync BOs in both directions (Robin Murphy) Reviewed-by: Jeff Hugo Tested-by: Heiko Stuebner Signed-off-by: Tomeu Vizoso Signed-off-by: Jeff Hugo Link: https://lore.kernel.org/r/20250721-6-10-rocket-v9-5-77ebd484941e@tomeuvizoso.net --- diff --git a/drivers/accel/rocket/rocket_drv.c b/drivers/accel/rocket/rocket_drv.c index a21aa9aa189b..5c0b63f0a8f0 100644 --- a/drivers/accel/rocket/rocket_drv.c +++ b/drivers/accel/rocket/rocket_drv.c @@ -134,6 +134,8 @@ static const struct drm_ioctl_desc rocket_drm_driver_ioctls[] = { ROCKET_IOCTL(CREATE_BO, create_bo), ROCKET_IOCTL(SUBMIT, submit), + ROCKET_IOCTL(PREP_BO, prep_bo), + ROCKET_IOCTL(FINI_BO, fini_bo), }; DEFINE_DRM_ACCEL_FOPS(rocket_accel_driver_fops); diff --git a/drivers/accel/rocket/rocket_gem.c b/drivers/accel/rocket/rocket_gem.c index 05cf46040865..0551e11cc184 100644 --- a/drivers/accel/rocket/rocket_gem.c +++ b/drivers/accel/rocket/rocket_gem.c @@ -123,3 +123,59 @@ err: return ret; } + +int rocket_ioctl_prep_bo(struct drm_device *dev, void *data, struct drm_file *file) +{ + struct drm_rocket_prep_bo *args = data; + unsigned long timeout = drm_timeout_abs_to_jiffies(args->timeout_ns); + struct drm_gem_object *gem_obj; + struct drm_gem_shmem_object *shmem_obj; + long ret = 0; + + if (args->reserved != 0) { + drm_dbg(dev, "Reserved field in drm_rocket_prep_bo struct should be 0.\n"); + return -EINVAL; + } + + gem_obj = drm_gem_object_lookup(file, args->handle); + if (!gem_obj) + return -ENOENT; + + ret = dma_resv_wait_timeout(gem_obj->resv, DMA_RESV_USAGE_WRITE, true, timeout); + if (!ret) + ret = timeout ? -ETIMEDOUT : -EBUSY; + + shmem_obj = &to_rocket_bo(gem_obj)->base; + + dma_sync_sgtable_for_cpu(dev->dev, shmem_obj->sgt, DMA_BIDIRECTIONAL); + + drm_gem_object_put(gem_obj); + + return ret; +} + +int rocket_ioctl_fini_bo(struct drm_device *dev, void *data, struct drm_file *file) +{ + struct drm_rocket_fini_bo *args = data; + struct drm_gem_shmem_object *shmem_obj; + struct rocket_gem_object *rkt_obj; + struct drm_gem_object *gem_obj; + + if (args->reserved != 0) { + drm_dbg(dev, "Reserved field in drm_rocket_fini_bo struct should be 0.\n"); + return -EINVAL; + } + + gem_obj = drm_gem_object_lookup(file, args->handle); + if (!gem_obj) + return -ENOENT; + + rkt_obj = to_rocket_bo(gem_obj); + shmem_obj = &rkt_obj->base; + + dma_sync_sgtable_for_device(dev->dev, shmem_obj->sgt, DMA_BIDIRECTIONAL); + + drm_gem_object_put(gem_obj); + + return 0; +} diff --git a/drivers/accel/rocket/rocket_gem.h b/drivers/accel/rocket/rocket_gem.h index 91a1fc09c56c..240430334509 100644 --- a/drivers/accel/rocket/rocket_gem.h +++ b/drivers/accel/rocket/rocket_gem.h @@ -21,6 +21,10 @@ struct drm_gem_object *rocket_gem_create_object(struct drm_device *dev, size_t s int rocket_ioctl_create_bo(struct drm_device *dev, void *data, struct drm_file *file); +int rocket_ioctl_prep_bo(struct drm_device *dev, void *data, struct drm_file *file); + +int rocket_ioctl_fini_bo(struct drm_device *dev, void *data, struct drm_file *file); + static inline struct rocket_gem_object *to_rocket_bo(struct drm_gem_object *obj) { diff --git a/include/uapi/drm/rocket_accel.h b/include/uapi/drm/rocket_accel.h index 374f8370ac9d..14b2e12b7c49 100644 --- a/include/uapi/drm/rocket_accel.h +++ b/include/uapi/drm/rocket_accel.h @@ -13,9 +13,13 @@ extern "C" { #define DRM_ROCKET_CREATE_BO 0x00 #define DRM_ROCKET_SUBMIT 0x01 +#define DRM_ROCKET_PREP_BO 0x02 +#define DRM_ROCKET_FINI_BO 0x03 #define DRM_IOCTL_ROCKET_CREATE_BO DRM_IOWR(DRM_COMMAND_BASE + DRM_ROCKET_CREATE_BO, struct drm_rocket_create_bo) #define DRM_IOCTL_ROCKET_SUBMIT DRM_IOW(DRM_COMMAND_BASE + DRM_ROCKET_SUBMIT, struct drm_rocket_submit) +#define DRM_IOCTL_ROCKET_PREP_BO DRM_IOW(DRM_COMMAND_BASE + DRM_ROCKET_PREP_BO, struct drm_rocket_prep_bo) +#define DRM_IOCTL_ROCKET_FINI_BO DRM_IOW(DRM_COMMAND_BASE + DRM_ROCKET_FINI_BO, struct drm_rocket_fini_bo) /** * struct drm_rocket_create_bo - ioctl argument for creating Rocket BOs. @@ -39,6 +43,36 @@ struct drm_rocket_create_bo { __u64 offset; }; +/** + * struct drm_rocket_prep_bo - ioctl argument for starting CPU ownership of the BO. + * + * Takes care of waiting for any NPU jobs that might still use the NPU and performs cache + * synchronization. + */ +struct drm_rocket_prep_bo { + /** Input: GEM handle of the buffer object. */ + __u32 handle; + + /** Reserved, must be zero. */ + __u32 reserved; + + /** Input: Amount of time to wait for NPU jobs. */ + __s64 timeout_ns; +}; + +/** + * struct drm_rocket_fini_bo - ioctl argument for finishing CPU ownership of the BO. + * + * Synchronize caches for NPU access. + */ +struct drm_rocket_fini_bo { + /** Input: GEM handle of the buffer object. */ + __u32 handle; + + /** Reserved, must be zero. */ + __u32 reserved; +}; + /** * struct drm_rocket_task - A task to be run on the NPU *