The NVIDIA Deep Learning Accelerator (NVDLA) is an open source IP
which is integrated into NVIDIA Jetson AGX Xavier,
so add UAPI of this driver.
Signed-off-by: Cai Huoqing <[email protected]>
---
v1->v2:
*Rename nvdla_drm.[ch] to nvdla_drv.[ch] and rename nvdla_ioctl.h to nvdla_drm.h,
move it to uapi.
comments link: https://lore.kernel.org/lkml/[email protected]/
include/uapi/drm/nvdla_drm.h | 99 ++++++++++++++++++++++++++++++++++++
1 file changed, 99 insertions(+)
create mode 100644 include/uapi/drm/nvdla_drm.h
diff --git a/include/uapi/drm/nvdla_drm.h b/include/uapi/drm/nvdla_drm.h
new file mode 100644
index 000000000000..984635285525
--- /dev/null
+++ b/include/uapi/drm/nvdla_drm.h
@@ -0,0 +1,99 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2017-2018 NVIDIA CORPORATION.
+ * Copyright (C) 2022 Cai Huoqing
+ */
+
+#ifndef __LINUX_NVDLA_IOCTL_H
+#define __LINUX_NVDLA_IOCTL_H
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+#if !defined(__KERNEL__)
+#define __user
+#endif
+
+/**
+ * struct nvdla_mem_handle structure for memory handles
+ *
+ * @handle handle to DMA buffer allocated in userspace
+ * @reserved Reserved for padding
+ * @offset offset in bytes from start address of buffer
+ *
+ */
+struct nvdla_mem_handle {
+ __u32 handle;
+ __u32 reserved;
+ __u64 offset;
+};
+
+/**
+ * struct nvdla_ioctl_submit_task structure for single task information
+ *
+ * @num_addresses total number of entries in address_list
+ * @reserved Reserved for padding
+ * @address_list pointer to array of struct nvdla_mem_handle
+ *
+ */
+struct nvdla_ioctl_submit_task {
+#define NVDLA_MAX_BUFFERS_PER_TASK (6144)
+ __u32 num_addresses;
+#define NVDLA_NO_TIMEOUT (0xffffffff)
+ __u32 timeout;
+ __u64 address_list;
+};
+
+/**
+ * struct nvdla_submit_args structure for task submit
+ *
+ * @tasks pointer to array of struct nvdla_ioctl_submit_task
+ * @num_tasks number of entries in tasks
+ * @flags flags for task submit, no flags defined yet
+ * @version version of task structure
+ *
+ */
+struct nvdla_submit_args {
+ __u64 tasks;
+ __u16 num_tasks;
+#define NVDLA_MAX_TASKS_PER_SUBMIT 24
+#define NVDLA_SUBMIT_FLAGS_ATOMIC (1 << 0)
+ __u16 flags;
+ __u32 version;
+};
+
+/**
+ * struct nvdla_gem_create_args for allocating DMA buffer through GEM
+ *
+ * @handle handle updated by kernel after allocation
+ * @flags implementation specific flags
+ * @size size of buffer to allocate
+ */
+struct nvdla_gem_create_args {
+ __u32 handle;
+ __u32 flags;
+ __u64 size;
+};
+
+/**
+ * struct nvdla_gem_map_offset_args for mapping DMA buffer
+ *
+ * @handle handle of the buffer
+ * @reserved reserved for padding
+ * @offset offset updated by kernel after mapping
+ */
+struct nvdla_gem_map_offset_args {
+ __u32 handle;
+ __u32 reserved;
+ __u64 offset;
+};
+
+#define DRM_NVDLA_SUBMIT 0x00
+#define DRM_NVDLA_GEM_CREATE 0x01
+#define DRM_NVDLA_GEM_MMAP 0x02
+
+#define DRM_IOCTL_NVDLA_SUBMIT DRM_IOWR(DRM_COMMAND_BASE + DRM_NVDLA_SUBMIT, struct nvdla_submit_args)
+#define DRM_IOCTL_NVDLA_GEM_CREATE DRM_IOWR(DRM_COMMAND_BASE + DRM_NVDLA_GEM_CREATE, struct nvdla_gem_create_args)
+#define DRM_IOCTL_NVDLA_GEM_MMAP DRM_IOWR(DRM_COMMAND_BASE + DRM_NVDLA_GEM_MMAP, struct nvdla_gem_map_offset_args)
+
+#endif
--
2.25.1
Hi Cai,
I love your patch! Yet something to improve:
[auto build test ERROR on drm/drm-next]
[also build test ERROR on linus/master linux/master v5.18-rc4 next-20220422]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]
url: https://github.com/intel-lab-lkp/linux/commits/Cai-Huoqing/drm-nvdla-Add-driver-support-for-NVDLA/20220426-141148
base: git://anongit.freedesktop.org/drm/drm drm-next
config: ia64-randconfig-r021-20220425 (https://download.01.org/0day-ci/archive/20220426/[email protected]/config)
compiler: ia64-linux-gcc (GCC) 11.3.0
reproduce (this is a W=1 build):
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# https://github.com/intel-lab-lkp/linux/commit/a54587f7637b8ee11ad624794af3b409e6306e07
git remote add linux-review https://github.com/intel-lab-lkp/linux
git fetch --no-tags linux-review Cai-Huoqing/drm-nvdla-Add-driver-support-for-NVDLA/20220426-141148
git checkout a54587f7637b8ee11ad624794af3b409e6306e07
# save the config file
mkdir build_dir && cp config build_dir/.config
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-11.3.0 make.cross W=1 O=build_dir ARCH=ia64 prepare
If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <[email protected]>
All errors (new ones prefixed by >>):
>> error: include/uapi/drm/nvdla_drm.h: missing "WITH Linux-syscall-note" for SPDX-License-Identifier
make[2]: *** [scripts/Makefile.headersinst:63: usr/include/drm/nvdla_drm.h] Error 1
make[2]: Target '__headers' not remade because of errors.
make[1]: *** [Makefile:1280: headers] Error 2
arch/ia64/kernel/asm-offsets.c:23:6: warning: no previous prototype for 'foo' [-Wmissing-prototypes]
23 | void foo(void)
| ^~~
<stdin>:1517:2: warning: #warning syscall clone3 not implemented [-Wcpp]
make[1]: Target 'prepare' not remade because of errors.
make: *** [Makefile:219: __sub-make] Error 2
make: Target 'prepare' not remade because of errors.
--
0-DAY CI Kernel Test Service
https://01.org/lkp
Hi Cai,
I love your patch! Yet something to improve:
[auto build test ERROR on drm/drm-next]
[also build test ERROR on linus/master linux/master v5.18-rc4 next-20220422]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]
url: https://github.com/intel-lab-lkp/linux/commits/Cai-Huoqing/drm-nvdla-Add-driver-support-for-NVDLA/20220426-141148
base: git://anongit.freedesktop.org/drm/drm drm-next
config: i386-randconfig-a003-20220425 (https://download.01.org/0day-ci/archive/20220426/[email protected]/config)
compiler: clang version 15.0.0 (https://github.com/llvm/llvm-project 1cddcfdc3c683b393df1a5c9063252eb60e52818)
reproduce (this is a W=1 build):
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# https://github.com/intel-lab-lkp/linux/commit/a54587f7637b8ee11ad624794af3b409e6306e07
git remote add linux-review https://github.com/intel-lab-lkp/linux
git fetch --no-tags linux-review Cai-Huoqing/drm-nvdla-Add-driver-support-for-NVDLA/20220426-141148
git checkout a54587f7637b8ee11ad624794af3b409e6306e07
# save the config file
mkdir build_dir && cp config build_dir/.config
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross W=1 O=build_dir ARCH=i386 prepare
If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <[email protected]>
All errors (new ones prefixed by >>):
>> error: include/uapi/drm/nvdla_drm.h: missing "WITH Linux-syscall-note" for SPDX-License-Identifier
make[2]: *** [scripts/Makefile.headersinst:63: usr/include/drm/nvdla_drm.h] Error 1
make[2]: Target '__headers' not remade because of errors.
make[1]: *** [Makefile:1280: headers] Error 2
make[1]: Target 'prepare' not remade because of errors.
make: *** [Makefile:219: __sub-make] Error 2
make: Target 'prepare' not remade because of errors.
--
0-DAY CI Kernel Test Service
https://01.org/lkp
On Tue, Apr 26, 2022 at 02:08:01PM +0800, Cai Huoqing wrote:
> The NVIDIA Deep Learning Accelerator (NVDLA) is an open source IP
> which is integrated into NVIDIA Jetson AGX Xavier,
> so add UAPI of this driver.
>
> Signed-off-by: Cai Huoqing <[email protected]>
> ---
> v1->v2:
> *Rename nvdla_drm.[ch] to nvdla_drv.[ch] and rename nvdla_ioctl.h to nvdla_drm.h,
> move it to uapi.
> comments link: https://lore.kernel.org/lkml/[email protected]/
>
> include/uapi/drm/nvdla_drm.h | 99 ++++++++++++++++++++++++++++++++++++
> 1 file changed, 99 insertions(+)
> create mode 100644 include/uapi/drm/nvdla_drm.h
>
> diff --git a/include/uapi/drm/nvdla_drm.h b/include/uapi/drm/nvdla_drm.h
> new file mode 100644
> index 000000000000..984635285525
> --- /dev/null
> +++ b/include/uapi/drm/nvdla_drm.h
> @@ -0,0 +1,99 @@
> +/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
> +/*
> + * Copyright (C) 2017-2018 NVIDIA CORPORATION.
> + * Copyright (C) 2022 Cai Huoqing
> + */
> +
> +#ifndef __LINUX_NVDLA_IOCTL_H
> +#define __LINUX_NVDLA_IOCTL_H
> +
> +#include <linux/ioctl.h>
> +#include <linux/types.h>
> +
> +#if !defined(__KERNEL__)
> +#define __user
> +#endif
> +
> +/**
> + * struct nvdla_mem_handle structure for memory handles
> + *
> + * @handle handle to DMA buffer allocated in userspace
> + * @reserved Reserved for padding
> + * @offset offset in bytes from start address of buffer
> + *
> + */
> +struct nvdla_mem_handle {
> + __u32 handle;
> + __u32 reserved;
> + __u64 offset;
> +};
> +
> +/**
> + * struct nvdla_ioctl_submit_task structure for single task information
> + *
> + * @num_addresses total number of entries in address_list
> + * @reserved Reserved for padding
> + * @address_list pointer to array of struct nvdla_mem_handle
> + *
> + */
> +struct nvdla_ioctl_submit_task {
> +#define NVDLA_MAX_BUFFERS_PER_TASK (6144)
This is an odd number. Can you clarify where this limitation comes from?
I say "limitation" here because, again, I'm no expert on DLA and I don't
know what a typical workload would look like. 6144 is a lot of buffers,
but are these tasks typically using a few large buffers or many small
buffers?
> + __u32 num_addresses;
> +#define NVDLA_NO_TIMEOUT (0xffffffff)
> + __u32 timeout;
> + __u64 address_list;
> +};
So if a task is basically just a collection of DMA buffers, is the
userspace supposed to fill some of those buffers with metadata to
determine what the task is about? If so, is this something that the
DLA firmware/hardware knows how to parse?
> +/**
> + * struct nvdla_submit_args structure for task submit
> + *
> + * @tasks pointer to array of struct nvdla_ioctl_submit_task
> + * @num_tasks number of entries in tasks
> + * @flags flags for task submit, no flags defined yet
> + * @version version of task structure
> + *
> + */
> +struct nvdla_submit_args {
> + __u64 tasks;
> + __u16 num_tasks;
> +#define NVDLA_MAX_TASKS_PER_SUBMIT 24
Perhaps worth clarifying if this is a hardware restriction or an
arbitrary software limit. Is this perhaps worth parameterizing somehow
if this can potentially change in newer versions of DLA?
> +#define NVDLA_SUBMIT_FLAGS_ATOMIC (1 << 0)
What exactly does atomicity imply here? Should this be described in a
comment?
Thierry
> + __u16 flags;
> + __u32 version;
> +};
> +
> +/**
> + * struct nvdla_gem_create_args for allocating DMA buffer through GEM
> + *
> + * @handle handle updated by kernel after allocation
> + * @flags implementation specific flags
> + * @size size of buffer to allocate
> + */
> +struct nvdla_gem_create_args {
> + __u32 handle;
> + __u32 flags;
> + __u64 size;
> +};
> +
> +/**
> + * struct nvdla_gem_map_offset_args for mapping DMA buffer
> + *
> + * @handle handle of the buffer
> + * @reserved reserved for padding
> + * @offset offset updated by kernel after mapping
> + */
> +struct nvdla_gem_map_offset_args {
> + __u32 handle;
> + __u32 reserved;
> + __u64 offset;
> +};
> +
> +#define DRM_NVDLA_SUBMIT 0x00
> +#define DRM_NVDLA_GEM_CREATE 0x01
> +#define DRM_NVDLA_GEM_MMAP 0x02
> +
> +#define DRM_IOCTL_NVDLA_SUBMIT DRM_IOWR(DRM_COMMAND_BASE + DRM_NVDLA_SUBMIT, struct nvdla_submit_args)
> +#define DRM_IOCTL_NVDLA_GEM_CREATE DRM_IOWR(DRM_COMMAND_BASE + DRM_NVDLA_GEM_CREATE, struct nvdla_gem_create_args)
> +#define DRM_IOCTL_NVDLA_GEM_MMAP DRM_IOWR(DRM_COMMAND_BASE + DRM_NVDLA_GEM_MMAP, struct nvdla_gem_map_offset_args)
> +
> +#endif
> --
> 2.25.1
>