Batch Buffer

Batch Buffer — Batchbuffer and blitter support

Functions

struct intel_batchbuffer * intel_batchbuffer_alloc ()
void intel_batchbuffer_set_context ()
void intel_batchbuffer_free ()
void intel_batchbuffer_flush ()
void intel_batchbuffer_flush_on_ring ()
void intel_batchbuffer_flush_with_context ()
void intel_batchbuffer_reset ()
uint32_t intel_batchbuffer_copy_data ()
void intel_batchbuffer_emit_reloc ()
uint32_t intel_batchbuffer_align ()
void * intel_batchbuffer_subdata_alloc ()
uint32_t intel_batchbuffer_subdata_offset ()
unsigned int intel_batchbuffer_space ()
void intel_batchbuffer_emit_dword ()
void intel_batchbuffer_require_space ()
#define BEGIN_BATCH()
#define OUT_BATCH()
#define OUT_RELOC_FENCED()
#define OUT_RELOC()
#define ADVANCE_BATCH
#define BLIT_COPY_BATCH_START()
#define COLOR_BLIT_COPY_BATCH_START()
void intel_blt_copy ()
void intel_copy_bo ()
unsigned igt_buf_width ()
unsigned igt_buf_height ()
unsigned int igt_buf_intel_ccs_width ()
unsigned int igt_buf_intel_ccs_height ()
void igt_blitter_src_copy ()
void igt_blitter_fast_copy ()
void igt_blitter_fast_copy__raw ()
void (*igt_render_copyfunc_t) ()
igt_render_copyfunc_t igt_get_render_copyfunc ()
void (*igt_vebox_copyfunc_t) ()
igt_vebox_copyfunc_t igt_get_vebox_copyfunc ()
void (*igt_render_clearfunc_t) ()
igt_render_clearfunc_t igt_get_render_clearfunc ()
void (*igt_fillfunc_t) ()
igt_fillfunc_t igt_get_gpgpu_fillfunc ()
igt_fillfunc_t igt_get_media_fillfunc ()
void (*igt_vme_func_t) ()
igt_vme_func_t igt_get_media_vme_func ()
void (*igt_media_spinfunc_t) ()
igt_media_spinfunc_t igt_get_media_spinfunc ()
struct intel_bb * intel_bb_create_full ()
struct intel_bb * intel_bb_create_with_allocator ()
struct intel_bb * intel_bb_create ()
struct intel_bb * intel_bb_create_with_context ()
struct intel_bb * intel_bb_create_with_relocs ()
struct intel_bb * intel_bb_create_with_relocs_and_context ()
void intel_bb_destroy ()
void intel_bb_reset ()
int intel_bb_sync ()
void intel_bb_print ()
void intel_bb_dump ()
void intel_bb_set_debug ()
void intel_bb_set_dump_base64 ()
void intel_bb_set_pxp ()
struct drm_i915_gem_exec_object2 * intel_bb_add_object ()
bool intel_bb_remove_object ()
struct drm_i915_gem_exec_object2 * intel_bb_add_intel_buf ()
struct drm_i915_gem_exec_object2 * intel_bb_add_intel_buf_with_alignment ()
bool intel_bb_remove_intel_buf ()
void intel_bb_print_intel_bufs ()
struct drm_i915_gem_exec_object2 * intel_bb_find_object ()
bool intel_bb_object_set_flag ()
bool intel_bb_object_clear_flag ()
uint64_t intel_bb_emit_reloc ()
uint64_t intel_bb_emit_reloc_fenced ()
uint64_t intel_bb_offset_reloc ()
uint64_t intel_bb_offset_reloc_with_delta ()
uint64_t intel_bb_offset_reloc_to_object ()
void intel_bb_dump_cache ()
void intel_bb_exec ()
uint64_t intel_bb_get_object_offset ()
bool intel_bb_object_offset_to_buf ()
uint32_t intel_bb_emit_bbe ()
uint32_t intel_bb_emit_flush_common ()
void intel_bb_flush ()
void intel_bb_flush_render ()
void intel_bb_flush_blit ()
uint32_t intel_bb_copy_data ()
void intel_bb_blit_start ()
void intel_bb_emit_blt_copy ()
void intel_bb_blt_copy ()
void intel_bb_copy_intel_buf ()
void (*igt_huc_copyfunc_t) ()
igt_huc_copyfunc_t igt_get_huc_copyfunc ()

Types and Values

#define BATCH_SZ
#define BATCH_RESERVED
struct intel_batchbuffer
#define I915_TILING_Yf
#define I915_TILING_Ys
enum i915_compression
struct igt_buf
struct igt_pxp
struct intel_bb
uint32_t previous_offset
struct intel_buf

Includes

#include <igt.h>

Description

This library provides some basic support for batchbuffers and using the blitter engine based upon libdrm. A new batchbuffer is allocated with intel_batchbuffer_alloc() and for simple blitter commands submitted with intel_batchbuffer_flush().

It also provides some convenient macros to easily emit commands into batchbuffers. All those macros presume that a pointer to a intel_batchbuffer structure called batch is in scope. The basic macros are BEGIN_BATCH, OUT_BATCH, OUT_RELOC and ADVANCE_BATCH.

Note that this library's header pulls in the i-g-t core library as a dependency.

Functions

intel_batchbuffer_alloc ()

struct intel_batchbuffer *
intel_batchbuffer_alloc (drm_intel_bufmgr *bufmgr,
                         uint32_t devid);

Allocates a new batchbuffer object. devid must be supplied since libdrm doesn't expose it directly.

Parameters

bufmgr

libdrm buffer manager

 

devid

pci device id of the drm device

 

Returns

The allocated and initialized batchbuffer object.


intel_batchbuffer_set_context ()

void
intel_batchbuffer_set_context (struct intel_batchbuffer *batch,
                               drm_intel_context *ctx);

intel_batchbuffer_free ()

void
intel_batchbuffer_free (struct intel_batchbuffer *batch);

Releases all resource of the batchbuffer object batch .

Parameters

batch

batchbuffer object

 

intel_batchbuffer_flush ()

void
intel_batchbuffer_flush (struct intel_batchbuffer *batch);

Submits the batch for execution on the blitter engine, selecting the right ring depending upon the hardware platform.

Parameters

batch

batchbuffer object

 

intel_batchbuffer_flush_on_ring ()

void
intel_batchbuffer_flush_on_ring (struct intel_batchbuffer *batch,
                                 int ring);

Submits the batch for execution on ring .

Parameters

batch

batchbuffer object

 

ring

execbuf ring flag

 

intel_batchbuffer_flush_with_context ()

void
intel_batchbuffer_flush_with_context (struct intel_batchbuffer *batch,
                                      drm_intel_context *context);

Submits the batch for execution on the render engine with the supplied hardware context.

Parameters

batch

batchbuffer object

 

context

libdrm hardware context object

 

intel_batchbuffer_reset ()

void
intel_batchbuffer_reset (struct intel_batchbuffer *batch);

Resets batch by allocating a new gem buffer object as backing storage.

Parameters

batch

batchbuffer object

 

intel_batchbuffer_copy_data ()

uint32_t
intel_batchbuffer_copy_data (struct intel_batchbuffer *batch,
                             const void *data,
                             unsigned int bytes,
                             uint32_t align);

This transfers the given data into the batchbuffer. Note that the length must be DWORD aligned, i.e. multiples of 32bits. The caller must confirm that there is enough space in the batch for the data to be copied.

Parameters

batch

batchbuffer object

 

data

pointer to the data to write into the batchbuffer

 

bytes

number of bytes to write into the batchbuffer

 

align

value in bytes to which we want to align

 

Returns

Offset of copied data.


intel_batchbuffer_emit_reloc ()

void
intel_batchbuffer_emit_reloc (struct intel_batchbuffer *batch,
                              drm_intel_bo *buffer,
                              uint64_t delta,
                              uint32_t read_domains,
                              uint32_t write_domain,
                              int fenced);

Emits both a libdrm relocation entry pointing at buffer and the pre-computed DWORD of batch 's presumed gpu address plus the supplied delta into batch .

Note that fenced is only relevant if buffer is actually tiled.

This is the only way buffers get added to the validate list.

Parameters

batch

batchbuffer object

 

buffer

relocation target libdrm buffer object

 

delta

delta value to add to buffer 's gpu address

 

read_domains

gem domain bits for the relocation

 

write_domain

gem domain bit for the relocation

 

fenced

whether this gpu access requires fences

 

intel_batchbuffer_align ()

uint32_t
intel_batchbuffer_align (struct intel_batchbuffer *batch,
                         uint32_t align);

Aligns the current in-batch offset to the given value.

Parameters

batch

batchbuffer object

 

align

value in bytes to which we want to align

 

Returns

Batchbuffer offset aligned to the given value.


intel_batchbuffer_subdata_alloc ()

void *
intel_batchbuffer_subdata_alloc (struct intel_batchbuffer *batch,
                                 uint32_t size,
                                 uint32_t align);

Verify if sufficient size within batch is available to deny overflow. Then allocate size bytes within batch .

Parameters

batch

batchbuffer object

 

size

amount of bytes need to allocate

 

align

value in bytes to which we want to align

 

Returns

Offset within batch between allocated subdata and base of batch .


intel_batchbuffer_subdata_offset ()

uint32_t
intel_batchbuffer_subdata_offset (struct intel_batchbuffer *batch,
                                  void *ptr);

Parameters

batch

batchbuffer object

 

ptr

pointer to given data

 

Returns

Offset within batch between ptr and base of batch .


intel_batchbuffer_space ()

unsigned int
intel_batchbuffer_space (struct intel_batchbuffer *batch);

intel_batchbuffer_emit_dword ()

void
intel_batchbuffer_emit_dword (struct intel_batchbuffer *batch,
                              uint32_t dword);

intel_batchbuffer_require_space ()

void
intel_batchbuffer_require_space (struct intel_batchbuffer *batch,
                                 unsigned int sz);

BEGIN_BATCH()

#define             BEGIN_BATCH(n, r)

Prepares a batch to emit n DWORDS, flushing it if there's not enough space available.

This macro needs a pointer to an intel_batchbuffer structure called batch in scope.

Parameters

n

number of DWORDS to emit

 

r

number of RELOCS to emit

 

OUT_BATCH()

#define OUT_BATCH(d) intel_batchbuffer_emit_dword(batch, d)

Emits d into a batch.

This macro needs a pointer to an intel_batchbuffer structure called batch in scope.

Parameters

d

DWORD to emit

 

OUT_RELOC_FENCED()

#define             OUT_RELOC_FENCED(buf, read_domains, write_domain, delta)

Emits a fenced relocation into a batch.

This macro needs a pointer to an intel_batchbuffer structure called batch in scope.

Parameters

buf

relocation target libdrm buffer object

 

read_domains

gem domain bits for the relocation

 

write_domain

gem domain bit for the relocation

 

delta

delta value to add to buffer 's gpu address

 

OUT_RELOC()

#define             OUT_RELOC(buf, read_domains, write_domain, delta)

Emits a normal, unfenced relocation into a batch.

This macro needs a pointer to an intel_batchbuffer structure called batch in scope.

Parameters

buf

relocation target libdrm buffer object

 

read_domains

gem domain bits for the relocation

 

write_domain

gem domain bit for the relocation

 

delta

delta value to add to buffer 's gpu address

 

ADVANCE_BATCH

#define             ADVANCE_BATCH()

Completes the batch command emission sequence started with BEGIN_BATCH.

This macro needs a pointer to an intel_batchbuffer structure called batch in scope.


BLIT_COPY_BATCH_START()

#define             BLIT_COPY_BATCH_START(flags)

COLOR_BLIT_COPY_BATCH_START()

#define             COLOR_BLIT_COPY_BATCH_START(flags)

intel_blt_copy ()

void
intel_blt_copy (struct intel_batchbuffer *batch,
                drm_intel_bo *src_bo,
                int src_x1,
                int src_y1,
                int src_pitch,
                drm_intel_bo *dst_bo,
                int dst_x1,
                int dst_y1,
                int dst_pitch,
                int width,
                int height,
                int bpp);

This emits a 2D copy operation using blitter commands into the supplied batch buffer object.

Parameters

batch

batchbuffer object

 

src_bo

source libdrm buffer object

 

src_x1

source pixel x-coordination

 

src_y1

source pixel y-coordination

 

src_pitch

src_bo 's pitch in bytes

 

dst_bo

destination libdrm buffer object

 

dst_x1

destination pixel x-coordination

 

dst_y1

destination pixel y-coordination

 

dst_pitch

dst_bo 's pitch in bytes

 

width

width of the copied rectangle

 

height

height of the copied rectangle

 

bpp

bits per pixel

 

intel_copy_bo ()

void
intel_copy_bo (struct intel_batchbuffer *batch,
               drm_intel_bo *dst_bo,
               drm_intel_bo *src_bo,
               long int size);

This emits a copy operation using blitter commands into the supplied batch buffer object. A total of size bytes from the start of src_bo is copied over to dst_bo . Note that size must be page-aligned.

Parameters

batch

batchbuffer object

 

src_bo

source libdrm buffer object

 

dst_bo

destination libdrm buffer object

 

size

size of the copy range in bytes

 

igt_buf_width ()

unsigned
igt_buf_width (const struct igt_buf *buf);

Computes the width in 32-bit pixels of the given buffer.

Parameters

buf

the i-g-t buffer object

 

Returns

The width of the buffer.


igt_buf_height ()

unsigned
igt_buf_height (const struct igt_buf *buf);

Computes the height in 32-bit pixels of the given buffer.

Parameters

buf

the i-g-t buffer object

 

Returns

The height of the buffer.


igt_buf_intel_ccs_width ()

unsigned int
igt_buf_intel_ccs_width (unsigned int gen,
                         const struct igt_buf *buf);

Computes the width of ccs buffer when considered as Intel surface data.

Parameters

buf

the Intel i-g-t buffer object

 

gen

device generation

 

Returns

The width of the ccs buffer data.


igt_buf_intel_ccs_height ()

unsigned int
igt_buf_intel_ccs_height (unsigned int gen,
                          const struct igt_buf *buf);

Computes the height of ccs buffer when considered as Intel surface data.

Parameters

buf

the i-g-t buffer object

 

gen

device generation

 

Returns

The height of the ccs buffer data.


igt_blitter_src_copy ()

void
igt_blitter_src_copy (int fd,
                      uint64_t ahnd,
                      uint32_t ctx,
                      uint32_t src_handle,
                      uint32_t src_delta,
                      uint32_t src_stride,
                      uint32_t src_tiling,
                      uint32_t src_x,
                      uint32_t src_y,
                      uint64_t src_size,
                      uint32_t width,
                      uint32_t height,
                      uint32_t bpp,
                      uint32_t dst_handle,
                      uint32_t dst_delta,
                      uint32_t dst_stride,
                      uint32_t dst_tiling,
                      uint32_t dst_x,
                      uint32_t dst_y,
                      uint64_t dst_size);

Copy src into dst using the XY_SRC blit command.

Parameters

fd

file descriptor of the i915 driver

 

ahnd

handle to an allocator

 

ctx

context within which execute copy blit

 

src_handle

GEM handle of the source buffer

 

src_delta

offset into the source GEM bo, in bytes

 

src_stride

Stride (in bytes) of the source buffer

 

src_tiling

Tiling mode of the source buffer

 

src_x

X coordinate of the source region to copy

 

src_y

Y coordinate of the source region to copy

 

src_size

size of the src bo required for allocator and softpin

 

width

Width of the region to copy

 

height

Height of the region to copy

 

bpp

source and destination bits per pixel

 

dst_handle

GEM handle of the destination buffer

 

dst_delta

offset into the destination GEM bo, in bytes

 

dst_stride

Stride (in bytes) of the destination buffer

 

dst_tiling

Tiling mode of the destination buffer

 

dst_x

X coordinate of destination

 

dst_y

Y coordinate of destination

 

dst_size

size of the dst bo required for allocator and softpin

 

igt_blitter_fast_copy ()

void
igt_blitter_fast_copy (struct intel_batchbuffer *batch,
                       const struct igt_buf *src,
                       unsigned  src_delta,
                       unsigned  src_x,
                       unsigned  src_y,
                       unsigned  width,
                       unsigned  height,
                       int bpp,
                       const struct igt_buf *dst,
                       unsigned  dst_delta,
                       unsigned  dst_x,
                       unsigned  dst_y);

Copy src into dst using the gen9 fast copy blitter command.

The source and destination surfaces cannot overlap.

Parameters

batch

batchbuffer object

 

src

source i-g-t buffer object

 

src_delta

offset into the source i-g-t bo

 

src_x

source pixel x-coordination

 

src_y

source pixel y-coordination

 

width

width of the copied rectangle

 

height

height of the copied rectangle

 

dst

destination i-g-t buffer object

 

dst_delta

offset into the destination i-g-t bo

 

dst_x

destination pixel x-coordination

 

dst_y

destination pixel y-coordination

 

igt_blitter_fast_copy__raw ()

void
igt_blitter_fast_copy__raw (int fd,
                            uint64_t ahnd,
                            uint32_t ctx,
                            uint32_t src_handle,
                            unsigned int src_delta,
                            unsigned int src_stride,
                            unsigned int src_tiling,
                            unsigned int src_x,
                            unsigned  src_y,
                            uint64_t src_size,
                            unsigned int width,
                            unsigned int height,
                            int bpp,
                            uint32_t dst_handle,
                            unsigned int dst_delta,
                            unsigned int dst_stride,
                            unsigned int dst_tiling,
                            unsigned int dst_x,
                            unsigned  dst_y,
                            uint64_t dst_size);

Like igt_blitter_fast_copy(), but talking to the kernel directly.

Parameters

fd

file descriptor of the i915 driver

 

ahnd

handle to an allocator

 

ctx

context within which execute copy blit

 

src_handle

GEM handle of the source buffer

 

src_delta

offset into the source GEM bo, in bytes

 

src_stride

Stride (in bytes) of the source buffer

 

src_tiling

Tiling mode of the source buffer

 

src_x

X coordinate of the source region to copy

 

src_y

Y coordinate of the source region to copy

 

src_size

size of the src bo required for allocator and softpin

 

width

Width of the region to copy

 

height

Height of the region to copy

 

bpp

source and destination bits per pixel

 

dst_handle

GEM handle of the destination buffer

 

dst_delta

offset into the destination GEM bo, in bytes

 

dst_stride

Stride (in bytes) of the destination buffer

 

dst_tiling

Tiling mode of the destination buffer

 

dst_x

X coordinate of destination

 

dst_y

Y coordinate of destination

 

dst_size

size of the dst bo required for allocator and softpin

 

igt_render_copyfunc_t ()

void
(*igt_render_copyfunc_t) (struct intel_bb *ibb,
                          struct intel_buf *src,
                          uint32_t src_x,
                          uint32_t src_y,
                          uint32_t width,
                          uint32_t height,
                          struct intel_buf *dst,
                          uint32_t dst_x,
                          uint32_t dst_y);

This is the type of the per-platform render copy functions. The platform-specific implementation can be obtained by calling igt_get_render_copyfunc().

A render copy function will emit a batchbuffer to the kernel which executes the specified blit copy operation using the render engine. ctx is optional and can be 0.

Parameters

ibb

batchbuffer

 

ctx

context to use

 

src

intel_buf source object

 

src_x

source pixel x-coordination

 

src_y

source pixel y-coordination

 

width

width of the copied rectangle

 

height

height of the copied rectangle

 

dst

intel_buf destination object

 

dst_x

destination pixel x-coordination

 

dst_y

destination pixel y-coordination

 

igt_get_render_copyfunc ()

igt_render_copyfunc_t
igt_get_render_copyfunc (int devid);

Parameters

devid

pci device id

 

Returns

The platform-specific render copy function pointer for the device specified with devid . Will return NULL when no render copy function is implemented.


igt_vebox_copyfunc_t ()

void
(*igt_vebox_copyfunc_t) (struct intel_bb *ibb,
                         struct intel_buf *src,
                         unsigned int width,
                         unsigned int height,
                         struct intel_buf *dst);

This is the type of the per-platform vebox copy functions. The platform-specific implementation can be obtained by calling igt_get_vebox_copyfunc().

A vebox copy function will emit a batchbuffer to the kernel which executes the specified blit copy operation using the vebox engine.

Parameters

ibb

batchbuffer

 

src

intel_buf source object

 

width

width of the copied rectangle

 

height

height of the copied rectangle

 

dst

intel_buf destination object

 

igt_get_vebox_copyfunc ()

igt_vebox_copyfunc_t
igt_get_vebox_copyfunc (int devid);

igt_render_clearfunc_t ()

void
(*igt_render_clearfunc_t) (struct intel_bb *ibb,
                           struct intel_buf *dst,
                           unsigned int dst_x,
                           unsigned int dst_y,
                           unsigned int width,
                           unsigned int height,
                           const float cc_color[4]);

igt_get_render_clearfunc ()

igt_render_clearfunc_t
igt_get_render_clearfunc (int devid);

igt_fillfunc_t ()

void
(*igt_fillfunc_t) (int i915,
                   struct intel_buf *buf,
                   unsigned  x,
                   unsigned  y,
                   unsigned  width,
                   unsigned  height,
                   uint8_t color);

This is the type of the per-platform fill functions using media or gpgpu pipeline. The platform-specific implementation can be obtained by calling igt_get_media_fillfunc() or igt_get_gpgpu_fillfunc().

A fill function will emit a batchbuffer to the kernel which executes the specified blit fill operation using the media/gpgpu engine.

Parameters

i915

drm fd

 

buf

destination intel_buf object

 

x

destination pixel x-coordination

 

y

destination pixel y-coordination

 

width

width of the filled rectangle

 

height

height of the filled rectangle

 

color

fill color to use

 

igt_get_gpgpu_fillfunc ()

igt_fillfunc_t
igt_get_gpgpu_fillfunc (int devid);

Parameters

devid

pci device id

 

Returns

The platform-specific gpgpu fill function pointer for the device specified with devid . Will return NULL when no gpgpu fill function is implemented.


igt_get_media_fillfunc ()

igt_fillfunc_t
igt_get_media_fillfunc (int devid);

Parameters

devid

pci device id

 

Returns

The platform-specific media fill function pointer for the device specified with devid . Will return NULL when no media fill function is implemented.


igt_vme_func_t ()

void
(*igt_vme_func_t) (int i915,
                   uint32_t ctx,
                   struct intel_buf *src,
                   unsigned int width,
                   unsigned int height,
                   struct intel_buf *dst);

igt_get_media_vme_func ()

igt_vme_func_t
igt_get_media_vme_func (int devid);

igt_media_spinfunc_t ()

void
(*igt_media_spinfunc_t) (int i915,
                         struct intel_buf *buf,
                         uint32_t spins);

This is the type of the per-platform media spin functions. The platform-specific implementation can be obtained by calling igt_get_media_spinfunc().

The media spin function emits a batchbuffer for the render engine with the media pipeline selected. The workload consists of a single thread which spins in a tight loop the requested number of times. Each spin increments a counter whose final 32-bit value is written to the destination buffer on completion. This utility provides a simple way to keep the render engine busy for a set time for various tests.

Parameters

i915

drm fd

 

buf

destination buffer object

 

spins

number of loops to execute

 

igt_get_media_spinfunc ()

igt_media_spinfunc_t
igt_get_media_spinfunc (int devid);

Parameters

devid

pci device id

 

Returns

The platform-specific media spin function pointer for the device specified with devid . Will return NULL when no media spin function is implemented.


intel_bb_create_full ()

struct intel_bb *
intel_bb_create_full (int i915,
                      uint32_t ctx,
                      uint32_t size,
                      uint64_t start,
                      uint64_t end,
                      uint8_t allocator_type,
                      enum allocator_strategy strategy);

Creates bb with context passed in ctx , size in size and allocator type in allocator_type . Relocations are set to false because IGT allocator is used in that case. VM range is passed to allocator (start and end ) and allocation strategy (suggestion to allocator about address allocation preferences).

Parameters

i915

drm fd

 

ctx

context

 

size

size of the batchbuffer

 

start

allocator vm start address

 

end

allocator vm start address

 

allocator_type

allocator type, SIMPLE, RANDOM, ...

 

strategy

allocation strategy

 

Returns

Pointer the intel_bb, asserts on failure.


intel_bb_create_with_allocator ()

struct intel_bb *
intel_bb_create_with_allocator (int i915,
                                uint32_t ctx,
                                uint32_t size,
                                uint8_t allocator_type);

Creates bb with context passed in ctx , size in size and allocator type in allocator_type . Relocations are set to false because IGT allocator is used in that case.

Parameters

i915

drm fd

 

ctx

context

 

size

size of the batchbuffer

 

allocator_type

allocator type, SIMPLE, RANDOM, ...

 

Returns

Pointer the intel_bb, asserts on failure.


intel_bb_create ()

struct intel_bb *
intel_bb_create (int i915,
                 uint32_t size);

Creates bb with default context.

Parameters

i915

drm fd

 

size

size of the batchbuffer

 

Returns

Pointer the intel_bb, asserts on failure.

Notes:

intel_bb must not be created in igt_fixture. The reason is intel_bb "opens" connection to the allocator and when test completes it can leave the allocator in unknown state (mostly for failed tests). As igt_core was armed to reset the allocator infrastructure connection to it inside intel_bb is not valid anymore. Trying to use it leads to catastrofic errors.


intel_bb_create_with_context ()

struct intel_bb *
intel_bb_create_with_context (int i915,
                              uint32_t ctx,
                              uint32_t size);

Creates bb with context passed in ctx .

Parameters

i915

drm fd

 

ctx

context

 

size

size of the batchbuffer

 

Returns

Pointer the intel_bb, asserts on failure.


intel_bb_create_with_relocs ()

struct intel_bb *
intel_bb_create_with_relocs (int i915,
                             uint32_t size);

Creates bb which will disable passing addresses. This will lead to relocations when objects are not previously pinned.

Parameters

i915

drm fd

 

size

size of the batchbuffer

 

Returns

Pointer the intel_bb, asserts on failure.


intel_bb_create_with_relocs_and_context ()

struct intel_bb *
intel_bb_create_with_relocs_and_context
                               (int i915,
                                uint32_t ctx,
                                uint32_t size);

Creates bb with default context which will disable passing addresses. This will lead to relocations when objects are not previously pinned.

Parameters

i915

drm fd

 

ctx

context

 

size

size of the batchbuffer

 

Returns

Pointer the intel_bb, asserts on failure.


intel_bb_destroy ()

void
intel_bb_destroy (struct intel_bb *ibb);

Frees all relocations / objects allocated during filling the batch.

Parameters

ibb

pointer to intel_bb

 

intel_bb_reset ()

void
intel_bb_reset (struct intel_bb *ibb,
                bool purge_objects_cache);

intel_bb_sync ()

int
intel_bb_sync (struct intel_bb *ibb);

intel_bb_print ()

void
intel_bb_print (struct intel_bb *ibb);

intel_bb_dump ()

void
intel_bb_dump (struct intel_bb *ibb,
               const char *filename);

intel_bb_set_debug ()

void
intel_bb_set_debug (struct intel_bb *ibb,
                    bool debug);

Sets debug to true / false. Execbuf is then called synchronously and object/reloc arrays are printed after execution.

Parameters

ibb

pointer to intel_bb

 

debug

true / false

 

intel_bb_set_dump_base64 ()

void
intel_bb_set_dump_base64 (struct intel_bb *ibb,
                          bool dump);

Do bb dump as base64 string before execbuf call.

Parameters

ibb

pointer to intel_bb

 

dump

true / false

 

intel_bb_set_pxp ()

void
intel_bb_set_pxp (struct intel_bb *ibb,
                  bool new_state,
                  uint32_t apptype,
                  uint32_t appid);

intel_bb_add_object ()

struct drm_i915_gem_exec_object2 *
intel_bb_add_object (struct intel_bb *ibb,
                     uint32_t handle,
                     uint64_t size,
                     uint64_t offset,
                     uint64_t alignment,
                     bool write);

Function adds or updates execobj slot in bb objects array and in the object tree. When object is a render target it has to be marked with EXEC_OBJECT_WRITE flag.

Parameters

ibb

pointer to intel_bb

 

handle

which handle to add to objects array

 

size

object size

 

offset

presumed offset of the object when no relocation is enforced

 

alignment

alignment of the object, if 0 it will be set to page size

 

write

does a handle is a render target

 

intel_bb_remove_object ()

bool
intel_bb_remove_object (struct intel_bb *ibb,
                        uint32_t handle,
                        uint64_t offset,
                        uint64_t size);

intel_bb_add_intel_buf ()

struct drm_i915_gem_exec_object2 *
intel_bb_add_intel_buf (struct intel_bb *ibb,
                        struct intel_buf *buf,
                        bool write);

intel_bb_add_intel_buf_with_alignment ()

struct drm_i915_gem_exec_object2 *
intel_bb_add_intel_buf_with_alignment (struct intel_bb *ibb,
                                       struct intel_buf *buf,
                                       uint64_t alignment,
                                       bool write);

intel_bb_remove_intel_buf ()

bool
intel_bb_remove_intel_buf (struct intel_bb *ibb,
                           struct intel_buf *buf);

intel_bb_print_intel_bufs ()

void
intel_bb_print_intel_bufs (struct intel_bb *ibb);

intel_bb_find_object ()

struct drm_i915_gem_exec_object2 *
intel_bb_find_object (struct intel_bb *ibb,
                      uint32_t handle);

intel_bb_object_set_flag ()

bool
intel_bb_object_set_flag (struct intel_bb *ibb,
                          uint32_t handle,
                          uint64_t flag);

intel_bb_object_clear_flag ()

bool
intel_bb_object_clear_flag (struct intel_bb *ibb,
                            uint32_t handle,
                            uint64_t flag);

intel_bb_emit_reloc ()

uint64_t
intel_bb_emit_reloc (struct intel_bb *ibb,
                     uint32_t handle,
                     uint32_t read_domains,
                     uint32_t write_domain,
                     uint64_t delta,
                     uint64_t presumed_offset);

Function prepares relocation (execobj if required + reloc) and emits offset in bb. For I915_EXEC_NO_RELOC presumed_offset is a hint we already have object in valid place and relocation step can be skipped in this case.

Note: delta is value added to address, mostly used when some instructions require modify-bit set to apply change. Which delta is valid depends on instruction (see instruction specification).

Parameters

ibb

pointer to intel_bb

 

handle

object handle which address will be taken to patch the bb

 

read_domains

gem domain bits for the relocation

 

write_domain

gem domain bit for the relocation

 

delta

delta value to add to buffer 's gpu address

 

presumed_offset

address of the object in address space. If -1 is passed then final offset of the object will be randomized (for no-reloc bb) or 0 (for reloc bb, in that case reloc.presumed_offset will be -1). In case address is known it should passed in presumed_offset (for no-reloc).

 

write

does a handle is a render target

 

intel_bb_emit_reloc_fenced ()

uint64_t
intel_bb_emit_reloc_fenced (struct intel_bb *ibb,
                            uint32_t handle,
                            uint32_t read_domains,
                            uint32_t write_domain,
                            uint64_t delta,
                            uint64_t presumed_offset);

intel_bb_offset_reloc ()

uint64_t
intel_bb_offset_reloc (struct intel_bb *ibb,
                       uint32_t handle,
                       uint32_t read_domains,
                       uint32_t write_domain,
                       uint32_t offset,
                       uint64_t presumed_offset);

Function prepares relocation (execobj if required + reloc). It it used for editing batchbuffer via modifying structures. It means when we're preparing batchbuffer it is more descriptive to edit the structure than emitting dwords. But it require for some fields to point the relocation. For that case offset is passed by the user and it points to the offset in bb where the relocation will be applied.

Parameters

ibb

pointer to intel_bb

 

handle

object handle which address will be taken to patch the bb

 

read_domains

gem domain bits for the relocation

 

write_domain

gem domain bit for the relocation

 

offset

offset within bb to be patched

 

presumed_offset

address of the object in address space. If -1 is passed then final offset of the object will be randomized (for no-reloc bb) or 0 (for reloc bb, in that case reloc.presumed_offset will be -1). In case address is known it should passed in presumed_offset (for no-reloc).

 

intel_bb_offset_reloc_with_delta ()

uint64_t
intel_bb_offset_reloc_with_delta (struct intel_bb *ibb,
                                  uint32_t handle,
                                  uint32_t read_domains,
                                  uint32_t write_domain,
                                  uint32_t delta,
                                  uint32_t offset,
                                  uint64_t presumed_offset);

intel_bb_offset_reloc_to_object ()

uint64_t
intel_bb_offset_reloc_to_object (struct intel_bb *ibb,
                                 uint32_t handle,
                                 uint32_t to_handle,
                                 uint32_t read_domains,
                                 uint32_t write_domain,
                                 uint32_t delta,
                                 uint32_t offset,
                                 uint64_t presumed_offset);

intel_bb_dump_cache ()

void
intel_bb_dump_cache (struct intel_bb *ibb);

intel_bb_exec ()

void
intel_bb_exec (struct intel_bb *ibb,
               uint32_t end_offset,
               uint64_t flags,
               bool sync);

Do execbuf on context selected during bb creation. Asserts on failure.

Parameters

ibb

pointer to intel_bb

 

end_offset

offset of the last instruction in the bb

 

flags

flags passed directly to execbuf

 

sync

if true wait for execbuf completion, otherwise caller is responsible to wait for completion

 

intel_bb_get_object_offset ()

uint64_t
intel_bb_get_object_offset (struct intel_bb *ibb,
                            uint32_t handle);

intel_bb_object_offset_to_buf ()

bool
intel_bb_object_offset_to_buf (struct intel_bb *ibb,
                               struct intel_buf *buf);

intel_bb_emit_bbe ()

uint32_t
intel_bb_emit_bbe (struct intel_bb *ibb);

intel_bb_emit_flush_common ()

uint32_t
intel_bb_emit_flush_common (struct intel_bb *ibb);

intel_bb_flush ()

void
intel_bb_flush (struct intel_bb *ibb,
                uint32_t ring);

intel_bb_flush_render ()

void
intel_bb_flush_render (struct intel_bb *ibb);

intel_bb_flush_blit ()

void
intel_bb_flush_blit (struct intel_bb *ibb);

intel_bb_copy_data ()

uint32_t
intel_bb_copy_data (struct intel_bb *ibb,
                    const void *data,
                    unsigned int bytes,
                    uint32_t align);

intel_bb_blit_start ()

void
intel_bb_blit_start (struct intel_bb *ibb,
                     uint32_t flags);

intel_bb_emit_blt_copy ()

void
intel_bb_emit_blt_copy (struct intel_bb *ibb,
                        struct intel_buf *src,
                        int src_x1,
                        int src_y1,
                        int src_pitch,
                        struct intel_buf *dst,
                        int dst_x1,
                        int dst_y1,
                        int dst_pitch,
                        int width,
                        int height,
                        int bpp);

intel_bb_blt_copy ()

void
intel_bb_blt_copy (struct intel_bb *ibb,
                   struct intel_buf *src,
                   int src_x1,
                   int src_y1,
                   int src_pitch,
                   struct intel_buf *dst,
                   int dst_x1,
                   int dst_y1,
                   int dst_pitch,
                   int width,
                   int height,
                   int bpp);

intel_bb_copy_intel_buf ()

void
intel_bb_copy_intel_buf (struct intel_bb *ibb,
                         struct intel_buf *dst,
                         struct intel_buf *src,
                         long int size);

Emits a copy operation using blitter commands into the supplied batch. A total of size bytes from the start of src is copied over to dst . Note that size must be page-aligned.

Parameters

batch

batchbuffer object

 

src

source buffer (intel_buf)

 

dst

destination libdrm buffer object

 

size

size of the copy range in bytes

 

igt_huc_copyfunc_t ()

void
(*igt_huc_copyfunc_t) (int fd,
                       uint64_t ahnd,
                       struct drm_i915_gem_exec_object2 *obj,
                       uint64_t *objsize);

This is the type of the per-platform huc copy functions.

The huc copy function emits a batchbuffer to the VDBOX engine to invoke the HuC Copy kernel to copy 4K bytes from the source buffer to the destination buffer.

Parameters

fd

drm fd

 

ahnd

allocator handle, if it is equal to 0 we use relocations

 

obj

drm_i915_gem_exec_object2 buffer array obj[0] is source buffer obj[1] is destination buffer obj[2] is execution buffer

 

objsize

corresponding buffer sizes to obj

 

igt_get_huc_copyfunc ()

igt_huc_copyfunc_t
igt_get_huc_copyfunc (int devid);

Parameters

devid

pci device id

 

Returns

The platform-specific huc copy function pointer for the device specified with devid . Will return NULL when no media spin function is implemented.

Types and Values

BATCH_SZ

#define BATCH_SZ 4096

BATCH_RESERVED

#define BATCH_RESERVED 16

struct intel_batchbuffer

struct intel_batchbuffer {
	drm_intel_bufmgr *bufmgr;
	uint32_t devid;
	unsigned int gen;

	drm_intel_context *ctx;
	drm_intel_bo *bo;

	uint8_t buffer[BATCH_SZ];
	uint8_t *ptr, *end;
};

I915_TILING_Yf

#define I915_TILING_Yf 3

I915_TILING_Ys

#define I915_TILING_Ys 4

enum i915_compression

Members

I915_COMPRESSION_NONE

   

I915_COMPRESSION_RENDER

   

I915_COMPRESSION_MEDIA

   

struct igt_buf

struct igt_buf {
	drm_intel_bo *bo;
	uint32_t tiling;
	enum i915_compression compression;
	uint32_t bpp;
	uint32_t yuv_semiplanar_bpp;
	uint32_t *data;
	bool format_is_yuv:1;
	bool format_is_yuv_semiplanar:1;
	struct {
		uint32_t offset;
		uint32_t stride;
		uint32_t size;
	} surface[2];
	struct {
		uint32_t offset;
		uint32_t stride;
	} ccs[2];
	struct {
		uint32_t offset;
	} cc;
};

This is a i-g-t buffer object wrapper structure which augments the baseline libdrm buffer object with suitable data needed by the render/vebox copy and the fill functions.

Members

drm_intel_bo *bo;

underlying libdrm buffer object

 

uint32_t tiling;

tiling mode bits

 

enum i915_compression compression;

memory compression mode

 

uint32_t bpp;

bits per pixel, 8, 16 or 32.

 

uint32_t yuv_semiplanar_bpp;

   

uint32_t *data;

pointer to the memory mapping of the buffer

 

bool format_is_yuv :1;

   

bool format_is_yuv_semiplanar :1;

   

struct igt_pxp

struct igt_pxp {
	bool     enabled;
	uint32_t apptype;
	uint32_t appid;
};

struct intel_bb

struct intel_bb {
	uint64_t allocator_handle;
	uint8_t allocator_type;
	enum allocator_strategy allocator_strategy;

	int i915;
	unsigned int gen;
	bool debug;
	bool dump_base64;
	bool enforce_relocs;
	uint32_t devid;
	uint32_t handle;
	uint32_t size;
	uint32_t *batch;
	uint32_t *ptr;
	uint64_t alignment;
	int fence;

	uint64_t gtt_size;
	bool supports_48b_address;
	bool uses_full_ppgtt;
	bool allows_obj_alignment;

	struct igt_pxp pxp;
	uint32_t ctx;
	uint32_t vm_id;

	/* Cache */
	void *root;

	/* Current objects for execbuf */
	void *current;

	/* Objects for current execbuf */
	struct drm_i915_gem_exec_object2 **objects;
	uint32_t num_objects;
	uint32_t allocated_objects;
	uint64_t batch_offset;

	struct drm_i915_gem_relocation_entry *relocs;
	uint32_t num_relocs;
	uint32_t allocated_relocs;

	/* Tracked intel_bufs */
	struct igt_list_head intel_bufs;

	/*
	 * BO recreate in reset path only when refcount == 0
	 * Currently we don't need to use atomics because intel_bb
	 * is not thread-safe.
	 */
	int32_t refcount;
};

previous_offset

	uint32_t previous_offset = intel_bb_offset(ibb);

struct intel_buf

struct intel_buf {
	struct buf_ops *bops;

	bool is_owner;
	uint32_t handle;
	uint64_t size;
	uint32_t tiling;
	uint32_t bpp;
	uint32_t compression;
	uint32_t swizzle_mode;
	uint32_t yuv_semiplanar_bpp;
	bool format_is_yuv;
	bool format_is_yuv_semiplanar;
	struct {
		uint32_t offset;
		uint32_t stride;
		uint64_t size;
	} surface[2];
	struct {
		uint32_t offset;
		uint32_t stride;
	} ccs[2];
	struct {
		uint32_t offset;
	} cc;
	struct {
		uint64_t offset;
		uint32_t ctx;
	} addr;

	uint64_t bo_size;

	/* Tracking */
	struct intel_bb *ibb;
	struct igt_list_head link;

	/* CPU mapping */
	uint32_t *ptr;
	bool cpu_write;

	/* Content Protection*/
	bool is_protected;

	/* For debugging purposes */
	char name[INTEL_BUF_NAME_MAXSIZE + 1];
};