From: Marek Olšák <marek.olsak@xxxxxxx>
v2: update amdgpu-symbol-check
---
amdgpu/amdgpu-symbol-check | 1 +
amdgpu/amdgpu.h | 14 ++++++++++++++
amdgpu/amdgpu_cs.c | 22 ++++++++++++++++++++++
include/drm/amdgpu_drm.h | 21 +++++++++++++++++++++
4 files changed, 58 insertions(+)
diff --git a/amdgpu/amdgpu-symbol-check b/amdgpu/amdgpu-symbol-check
index 7ecfc98..d9f89ef 100755
--- a/amdgpu/amdgpu-symbol-check
+++ b/amdgpu/amdgpu-symbol-check
@@ -27,20 +27,21 @@ amdgpu_bo_wait_for_idle
amdgpu_create_bo_from_user_mem
amdgpu_cs_chunk_fence_info_to_data
amdgpu_cs_chunk_fence_to_dep
amdgpu_cs_create_semaphore
amdgpu_cs_create_syncobj
amdgpu_cs_ctx_create
amdgpu_cs_ctx_free
amdgpu_cs_destroy_semaphore
amdgpu_cs_destroy_syncobj
amdgpu_cs_export_syncobj
+amdgpu_cs_fence_to_handle
amdgpu_cs_import_syncobj
amdgpu_cs_query_fence_status
amdgpu_cs_query_reset_state
amdgpu_cs_signal_semaphore
amdgpu_cs_submit
amdgpu_cs_submit_raw
amdgpu_cs_syncobj_export_sync_file
amdgpu_cs_syncobj_import_sync_file
amdgpu_cs_syncobj_wait
amdgpu_cs_wait_fences
diff --git a/amdgpu/amdgpu.h b/amdgpu/amdgpu.h
index 979acfc..23cde10 100644
--- a/amdgpu/amdgpu.h
+++ b/amdgpu/amdgpu.h
@@ -1426,20 +1426,34 @@ int amdgpu_cs_syncobj_export_sync_file(amdgpu_device_handle dev,
*
* \return 0 on success\n
* <0 - Negative POSIX Error code
*
*/
int amdgpu_cs_syncobj_import_sync_file(amdgpu_device_handle dev,
uint32_t syncobj,
int sync_file_fd);
/**
+ * Export an amdgpu fence as a handle (syncobj or fd).
+ *
+ * \param what AMDGPU_FENCE_TO_HANDLE_GET_{SYNCOBJ, FD}
+ * \param out_handle returned handle
+ *
+ * \return 0 on success\n
+ * <0 - Negative POSIX Error code
+ */
+int amdgpu_cs_fence_to_handle(amdgpu_device_handle dev,
+ struct amdgpu_cs_fence *fence,
+ uint32_t what,
+ uint32_t *out_handle);
+
+/**
* Submit raw command submission to kernel
*
* \param dev - \c [in] device handle
* \param context - \c [in] context handle for context id
* \param bo_list_handle - \c [in] request bo list handle (0 for none)
* \param num_chunks - \c [in] number of CS chunks to submit
* \param chunks - \c [in] array of CS chunks
* \param seq_no - \c [out] output sequence number for submission.
*
* \return 0 on success\n
diff --git a/amdgpu/amdgpu_cs.c b/amdgpu/amdgpu_cs.c
index 2cde7bf..9577d5c 100644
--- a/amdgpu/amdgpu_cs.c
+++ b/amdgpu/amdgpu_cs.c
@@ -706,10 +706,32 @@ void amdgpu_cs_chunk_fence_info_to_data(struct amdgpu_cs_fence_info *fence_info,
void amdgpu_cs_chunk_fence_to_dep(struct amdgpu_cs_fence *fence,
struct drm_amdgpu_cs_chunk_dep *dep)
{
dep->ip_type = fence->ip_type;
dep->ip_instance = fence->ip_instance;
dep->ring = fence->ring;
dep->ctx_id = fence->context->id;
dep->handle = fence->fence;
}
+
+int amdgpu_cs_fence_to_handle(amdgpu_device_handle dev,
+ struct amdgpu_cs_fence *fence,
+ uint32_t what,
+ uint32_t *out_handle)
+{
+ union drm_amdgpu_fence_to_handle fth = {0};
+ int r;
+
+ fth.in.fence.ctx_id = fence->context->id;
+ fth.in.fence.ip_type = fence->ip_type;
+ fth.in.fence.ip_instance = fence->ip_instance;
+ fth.in.fence.ring = fence->ring;
+ fth.in.fence.seq_no = fence->fence;
+ fth.in.what = what;
+
+ r = drmCommandWriteRead(dev->fd, DRM_AMDGPU_FENCE_TO_HANDLE,
+ &fth, sizeof(fth));
+ if (r == 0)
+ *out_handle = fth.out.handle;
+ return r;
+}
diff --git a/include/drm/amdgpu_drm.h b/include/drm/amdgpu_drm.h
index d9aa4a3..00f1b81 100644
--- a/include/drm/amdgpu_drm.h
+++ b/include/drm/amdgpu_drm.h
@@ -45,55 +45,59 @@ extern "C" {
#define DRM_AMDGPU_CS 0x04
#define DRM_AMDGPU_INFO 0x05
#define DRM_AMDGPU_GEM_METADATA 0x06
#define DRM_AMDGPU_GEM_WAIT_IDLE 0x07
#define DRM_AMDGPU_GEM_VA 0x08
#define DRM_AMDGPU_WAIT_CS 0x09
#define DRM_AMDGPU_GEM_OP 0x10
#define DRM_AMDGPU_GEM_USERPTR 0x11
#define DRM_AMDGPU_WAIT_FENCES 0x12
#define DRM_AMDGPU_VM 0x13
+#define DRM_AMDGPU_FENCE_TO_HANDLE 0x15
#define DRM_IOCTL_AMDGPU_GEM_CREATE DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_CREATE, union drm_amdgpu_gem_create)
#define DRM_IOCTL_AMDGPU_GEM_MMAP DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_MMAP, union drm_amdgpu_gem_mmap)
#define DRM_IOCTL_AMDGPU_CTX DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_CTX, union drm_amdgpu_ctx)
#define DRM_IOCTL_AMDGPU_BO_LIST DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_BO_LIST, union drm_amdgpu_bo_list)
#define DRM_IOCTL_AMDGPU_CS DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_CS, union drm_amdgpu_cs)
#define DRM_IOCTL_AMDGPU_INFO DRM_IOW(DRM_COMMAND_BASE + DRM_AMDGPU_INFO, struct drm_amdgpu_info)
#define DRM_IOCTL_AMDGPU_GEM_METADATA DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_METADATA, struct drm_amdgpu_gem_metadata)
#define DRM_IOCTL_AMDGPU_GEM_WAIT_IDLE DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_WAIT_IDLE, union drm_amdgpu_gem_wait_idle)
#define DRM_IOCTL_AMDGPU_GEM_VA DRM_IOW(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_VA, struct drm_amdgpu_gem_va)
#define DRM_IOCTL_AMDGPU_WAIT_CS DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_WAIT_CS, union drm_amdgpu_wait_cs)
#define DRM_IOCTL_AMDGPU_GEM_OP DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_OP, struct drm_amdgpu_gem_op)
#define DRM_IOCTL_AMDGPU_GEM_USERPTR DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_USERPTR, struct drm_amdgpu_gem_userptr)
#define DRM_IOCTL_AMDGPU_WAIT_FENCES DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_WAIT_FENCES, union drm_amdgpu_wait_fences)
#define DRM_IOCTL_AMDGPU_VM DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_VM, union drm_amdgpu_vm)
+#define DRM_IOCTL_AMDGPU_FENCE_TO_HANDLE DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_FENCE_TO_HANDLE, union drm_amdgpu_fence_to_handle)
#define AMDGPU_GEM_DOMAIN_CPU 0x1
#define AMDGPU_GEM_DOMAIN_GTT 0x2
#define AMDGPU_GEM_DOMAIN_VRAM 0x4
#define AMDGPU_GEM_DOMAIN_GDS 0x8
#define AMDGPU_GEM_DOMAIN_GWS 0x10
#define AMDGPU_GEM_DOMAIN_OA 0x20
/* Flag that CPU access will be required for the case of VRAM domain */
#define AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED (1 << 0)
/* Flag that CPU access will not work, this VRAM domain is invisible */
#define AMDGPU_GEM_CREATE_NO_CPU_ACCESS (1 << 1)
/* Flag that USWC attributes should be used for GTT */
#define AMDGPU_GEM_CREATE_CPU_GTT_USWC (1 << 2)
/* Flag that the memory should be in VRAM and cleared */
#define AMDGPU_GEM_CREATE_VRAM_CLEARED (1 << 3)
/* Flag that create shadow bo(GTT) while allocating vram bo */
#define AMDGPU_GEM_CREATE_SHADOW (1 << 4)
/* Flag that allocating the BO should use linear VRAM */
#define AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS (1 << 5)
+/* Flag that BO is always valid in this VM */
+#define AMDGPU_GEM_CREATE_VM_ALWAYS_VALID (1 << 6)
struct drm_amdgpu_gem_create_in {
/** the requested memory size */
__u64 bo_size;
/** physical start_addr alignment in bytes for some HW requirements */
__u64 alignment;
/** the requested memory domains */
__u64 domains;
/** allocation flags */
__u64 domain_flags;
@@ -506,20 +510,34 @@ struct drm_amdgpu_cs_chunk_dep {
struct drm_amdgpu_cs_chunk_fence {
__u32 handle;
__u32 offset;
};
struct drm_amdgpu_cs_chunk_sem {
__u32 handle;
};
+#define AMDGPU_FENCE_TO_HANDLE_GET_SYNCOBJ 0
+#define AMDGPU_FENCE_TO_HANDLE_GET_SYNCOBJ_FD 1
+#define AMDGPU_FENCE_TO_HANDLE_GET_SYNC_FILE_FD 2
+
+union drm_amdgpu_fence_to_handle {
+ struct {
+ struct drm_amdgpu_fence fence;
+ __u32 what;
+ } in;
+ struct {
+ __u32 handle;
+ } out;
+};
+
struct drm_amdgpu_cs_chunk_data {
union {
struct drm_amdgpu_cs_chunk_ib ib_data;
struct drm_amdgpu_cs_chunk_fence fence_data;
};
};
/**
* Query h/w info: Flag that this is integrated (a.h.a. fusion) GPU
*
@@ -757,20 +775,21 @@ struct drm_amdgpu_info_device {
__u32 pci_rev;
__u32 family;
__u32 num_shader_engines;
__u32 num_shader_arrays_per_engine;
/* in KHz */
__u32 gpu_counter_freq;
__u64 max_engine_clock;
__u64 max_memory_clock;
/* cu information */
__u32 cu_active_number;
+ /* NOTE: cu_ao_mask is INVALID, DON'T use it */
__u32 cu_ao_mask;
__u32 cu_bitmap[4][4];
/** Render backend pipe mask. One render backend is CB+DB. */
__u32 enabled_rb_pipes_mask;
__u32 num_rb_pipes;
__u32 num_hw_gfx_contexts;
__u32 _pad;
__u64 ids_flags;
/** Starting virtual address for UMDs. */
__u64 virtual_address_offset;
@@ -811,20 +830,22 @@ struct drm_amdgpu_info_device {
__u32 num_cu_per_sh;
/* number of tcc blocks*/
__u32 num_tcc_blocks;
/* gs vgt table depth*/
__u32 gs_vgt_table_depth;
/* gs primitive buffer depth*/
__u32 gs_prim_buffer_depth;
/* max gs wavefront per vgt*/
__u32 max_gs_waves_per_vgt;
__u32 _pad1;
+ /* always on cu bitmap */
+ __u32 cu_ao_bitmap[4][4];
};
struct drm_amdgpu_info_hw_ip {
/** Version of h/w IP */
__u32 hw_ip_version_major;
__u32 hw_ip_version_minor;
/** Capabilities */
__u64 capabilities_flags;
/** command buffer address start alignment*/
__u32 ib_start_alignment;
--
2.7.4
