* [igt-dev] [PATCH i-g-t,v5 0/5] Add testing for CCS @ 2021-12-19 13:14 apoorva1.singh 2021-12-19 13:14 ` [igt-dev] [PATCH i-g-t, v5 1/5] lib/i915: Introduce library intel_mocs apoorva1.singh ` (6 more replies) 0 siblings, 7 replies; 11+ messages in thread From: apoorva1.singh @ 2021-12-19 13:14 UTC (permalink / raw) To: apoorva1.singh, igt-dev, ramalingam.c, zbigniew.kempczynski, arjun.melkaveri From: Apoorva Singh <apoorva1.singh@intel.com> - Add new library intel_mocs for mocs settings. - Add new library i915_blt for various blt commands. - Add a new platform flag, has_flat_ccs, for platforms supporting Flat CCS. - Only use the main copy engines for XY_BLOCK_COPY. XY_BLOCK_COPY blt command is used to transfer the ccs data. So, we can only run the tests on those engines which have support for the "block_copy" capability. - Add gem_ccs test for CCS testing. Commands are constructed with XY_BLOCK_COPY_BLT and XY_CTRL_SURF_COPY_BLT instructions. Apoorva Singh (3): lib/i915: Introduce library intel_mocs lib/i915: Introduce library i915_blt lib/intel_chipset.h: Add has_flat_ccs flag CQ Tang (1): i915/gem_ccs: Add testing for CCS Chris Wilson (1): i915/gem_engine_topology: Only use the main copy engines for XY_BLOCK_COPY lib/i915/gem_engine_topology.c | 38 +++ lib/i915/gem_engine_topology.h | 5 + lib/i915/i915_blt.c | 393 +++++++++++++++++++++++++++++++ lib/i915/i915_blt.h | 72 ++++++ lib/i915/intel_mocs.c | 51 ++++ lib/i915/intel_mocs.h | 23 ++ lib/intel_chipset.h | 3 + lib/meson.build | 2 + tests/i915/gem_ccs.c | 413 +++++++++++++++++++++++++++++++++ tests/meson.build | 1 + 10 files changed, 1001 insertions(+) create mode 100644 lib/i915/i915_blt.c create mode 100644 lib/i915/i915_blt.h create mode 100644 lib/i915/intel_mocs.c create mode 100644 lib/i915/intel_mocs.h create mode 100644 tests/i915/gem_ccs.c -- 2.25.1 ^ permalink raw reply [flat|nested] 11+ messages in thread
* [igt-dev] [PATCH i-g-t, v5 1/5] lib/i915: Introduce library intel_mocs 2021-12-19 13:14 [igt-dev] [PATCH i-g-t,v5 0/5] Add testing for CCS apoorva1.singh @ 2021-12-19 13:14 ` apoorva1.singh 2021-12-20 12:36 ` Zbigniew Kempczyński 2021-12-19 13:14 ` [igt-dev] [PATCH i-g-t, v5 2/5] lib/i915: Introduce library i915_blt apoorva1.singh ` (5 subsequent siblings) 6 siblings, 1 reply; 11+ messages in thread From: apoorva1.singh @ 2021-12-19 13:14 UTC (permalink / raw) To: apoorva1.singh, igt-dev, ramalingam.c, zbigniew.kempczynski, arjun.melkaveri From: Apoorva Singh <apoorva1.singh@intel.com> Add new library intel_mocs for mocs settings. Signed-off-by: Apoorva Singh <apoorva1.singh@intel.com> Cc: Zbigniew Kempczyński <zbigniew.kempczynski@intel.com> Cc: Melkaveri, Arjun <arjun.melkaveri@intel.com> --- lib/i915/intel_mocs.c | 51 +++++++++++++++++++++++++++++++++++++++++++ lib/i915/intel_mocs.h | 23 +++++++++++++++++++ lib/meson.build | 1 + 3 files changed, 75 insertions(+) create mode 100644 lib/i915/intel_mocs.c create mode 100644 lib/i915/intel_mocs.h diff --git a/lib/i915/intel_mocs.c b/lib/i915/intel_mocs.c new file mode 100644 index 00000000..021aef03 --- /dev/null +++ b/lib/i915/intel_mocs.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2021 Intel Corporation + */ + +#include "igt.h" +#include "i915/gem.h" +#include "intel_mocs.h" + +static void get_mocs_index(int fd, struct drm_i915_mocs_index *mocs) +{ + uint16_t devid = intel_get_drm_devid(fd); + + /* + * Gen >= 12 onwards don't have a setting for PTE, + * so using I915_MOCS_PTE as mocs index may leads to + * some undefined MOCS behavior. + * This helper function is providing current UC as well + * as WB MOCS index based on platform. + */ + if (IS_DG1(devid)) { + mocs->uc_index = DG1_MOCS_UC_IDX; + mocs->wb_index = DG1_MOCS_WB_IDX; + } else if (IS_GEN12(devid)) { + mocs->uc_index = GEN12_MOCS_UC_IDX; + mocs->wb_index = GEN12_MOCS_WB_IDX; + } else { + mocs->uc_index = I915_MOCS_PTE; + mocs->wb_index = I915_MOCS_CACHED; + } +} + +/* BitField [6:1] represents index to MOCS Tables + * BitField [0] represents Encryption/Decryption + */ + +uint8_t intel_get_wb_mocs(int fd) +{ + struct drm_i915_mocs_index mocs; + + get_mocs_index(fd, &mocs); + return mocs.wb_index << 1; +} + +uint8_t intel_get_uc_mocs(int fd) +{ + struct drm_i915_mocs_index mocs; + + get_mocs_index(fd, &mocs); + return mocs.uc_index << 1; +} diff --git a/lib/i915/intel_mocs.h b/lib/i915/intel_mocs.h new file mode 100644 index 00000000..92d0d920 --- /dev/null +++ b/lib/i915/intel_mocs.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2019 Intel Corporation + */ + +#ifndef _INTEL_MOCS_H +#define _INTEL_MOCS_H + +#define DG1_MOCS_UC_IDX 1 +#define DG1_MOCS_WB_IDX 5 +#define GEN12_MOCS_UC_IDX 3 +#define GEN12_MOCS_WB_IDX 2 +#define XY_BLOCK_COPY_BLT_MOCS_SHIFT 21 +#define XY_CTRL_SURF_COPY_BLT_MOCS_SHIFT 25 + +struct drm_i915_mocs_index { + uint8_t uc_index; + uint8_t wb_index; +}; + +uint8_t intel_get_wb_mocs(int fd); +uint8_t intel_get_uc_mocs(int fd); +#endif /* _INTEL_MOCS_H */ diff --git a/lib/meson.build b/lib/meson.build index b9568a71..f500f0f1 100644 --- a/lib/meson.build +++ b/lib/meson.build @@ -11,6 +11,7 @@ lib_sources = [ 'i915/gem_mman.c', 'i915/gem_vm.c', 'i915/intel_memory_region.c', + 'i915/intel_mocs.c', 'igt_collection.c', 'igt_color_encoding.c', 'igt_debugfs.c', -- 2.25.1 ^ permalink raw reply related [flat|nested] 11+ messages in thread
* Re: [igt-dev] [PATCH i-g-t, v5 1/5] lib/i915: Introduce library intel_mocs 2021-12-19 13:14 ` [igt-dev] [PATCH i-g-t, v5 1/5] lib/i915: Introduce library intel_mocs apoorva1.singh @ 2021-12-20 12:36 ` Zbigniew Kempczyński 0 siblings, 0 replies; 11+ messages in thread From: Zbigniew Kempczyński @ 2021-12-20 12:36 UTC (permalink / raw) To: apoorva1.singh; +Cc: igt-dev On Sun, Dec 19, 2021 at 06:44:39PM +0530, apoorva1.singh@intel.com wrote: > From: Apoorva Singh <apoorva1.singh@intel.com> > > Add new library intel_mocs for mocs settings. > > Signed-off-by: Apoorva Singh <apoorva1.singh@intel.com> > Cc: Zbigniew Kempczyński <zbigniew.kempczynski@intel.com> > Cc: Melkaveri, Arjun <arjun.melkaveri@intel.com> > --- > lib/i915/intel_mocs.c | 51 +++++++++++++++++++++++++++++++++++++++++++ > lib/i915/intel_mocs.h | 23 +++++++++++++++++++ > lib/meson.build | 1 + > 3 files changed, 75 insertions(+) > create mode 100644 lib/i915/intel_mocs.c > create mode 100644 lib/i915/intel_mocs.h > > diff --git a/lib/i915/intel_mocs.c b/lib/i915/intel_mocs.c > new file mode 100644 > index 00000000..021aef03 > --- /dev/null > +++ b/lib/i915/intel_mocs.c > @@ -0,0 +1,51 @@ > +// SPDX-License-Identifier: MIT > +/* > + * Copyright © 2021 Intel Corporation > + */ > + > +#include "igt.h" > +#include "i915/gem.h" > +#include "intel_mocs.h" > + > +static void get_mocs_index(int fd, struct drm_i915_mocs_index *mocs) > +{ > + uint16_t devid = intel_get_drm_devid(fd); > + > + /* > + * Gen >= 12 onwards don't have a setting for PTE, > + * so using I915_MOCS_PTE as mocs index may leads to > + * some undefined MOCS behavior. > + * This helper function is providing current UC as well > + * as WB MOCS index based on platform. > + */ > + if (IS_DG1(devid)) { > + mocs->uc_index = DG1_MOCS_UC_IDX; > + mocs->wb_index = DG1_MOCS_WB_IDX; > + } else if (IS_GEN12(devid)) { > + mocs->uc_index = GEN12_MOCS_UC_IDX; > + mocs->wb_index = GEN12_MOCS_WB_IDX; > + } else { > + mocs->uc_index = I915_MOCS_PTE; > + mocs->wb_index = I915_MOCS_CACHED; > + } > +} Ok, this looks better for me right now. Reviewed-by: Zbigniew Kempczyński <zbigniew.kempczynski@intel.com> -- Zbigniew > + > +/* BitField [6:1] represents index to MOCS Tables > + * BitField [0] represents Encryption/Decryption > + */ > + > +uint8_t intel_get_wb_mocs(int fd) > +{ > + struct drm_i915_mocs_index mocs; > + > + get_mocs_index(fd, &mocs); > + return mocs.wb_index << 1; > +} > + > +uint8_t intel_get_uc_mocs(int fd) > +{ > + struct drm_i915_mocs_index mocs; > + > + get_mocs_index(fd, &mocs); > + return mocs.uc_index << 1; > +} > diff --git a/lib/i915/intel_mocs.h b/lib/i915/intel_mocs.h > new file mode 100644 > index 00000000..92d0d920 > --- /dev/null > +++ b/lib/i915/intel_mocs.h > @@ -0,0 +1,23 @@ > +/* SPDX-License-Identifier: MIT */ > +/* > + * Copyright © 2019 Intel Corporation > + */ > + > +#ifndef _INTEL_MOCS_H > +#define _INTEL_MOCS_H > + > +#define DG1_MOCS_UC_IDX 1 > +#define DG1_MOCS_WB_IDX 5 > +#define GEN12_MOCS_UC_IDX 3 > +#define GEN12_MOCS_WB_IDX 2 > +#define XY_BLOCK_COPY_BLT_MOCS_SHIFT 21 > +#define XY_CTRL_SURF_COPY_BLT_MOCS_SHIFT 25 > + > +struct drm_i915_mocs_index { > + uint8_t uc_index; > + uint8_t wb_index; > +}; > + > +uint8_t intel_get_wb_mocs(int fd); > +uint8_t intel_get_uc_mocs(int fd); > +#endif /* _INTEL_MOCS_H */ > diff --git a/lib/meson.build b/lib/meson.build > index b9568a71..f500f0f1 100644 > --- a/lib/meson.build > +++ b/lib/meson.build > @@ -11,6 +11,7 @@ lib_sources = [ > 'i915/gem_mman.c', > 'i915/gem_vm.c', > 'i915/intel_memory_region.c', > + 'i915/intel_mocs.c', > 'igt_collection.c', > 'igt_color_encoding.c', > 'igt_debugfs.c', > -- > 2.25.1 > ^ permalink raw reply [flat|nested] 11+ messages in thread
* [igt-dev] [PATCH i-g-t, v5 2/5] lib/i915: Introduce library i915_blt 2021-12-19 13:14 [igt-dev] [PATCH i-g-t,v5 0/5] Add testing for CCS apoorva1.singh 2021-12-19 13:14 ` [igt-dev] [PATCH i-g-t, v5 1/5] lib/i915: Introduce library intel_mocs apoorva1.singh @ 2021-12-19 13:14 ` apoorva1.singh 2021-12-20 13:06 ` Zbigniew Kempczyński 2021-12-20 13:49 ` Petri Latvala 2021-12-19 13:14 ` [igt-dev] [PATCH i-g-t, v5 3/5] lib/intel_chipset.h: Add has_flat_ccs flag apoorva1.singh ` (4 subsequent siblings) 6 siblings, 2 replies; 11+ messages in thread From: apoorva1.singh @ 2021-12-19 13:14 UTC (permalink / raw) To: apoorva1.singh, igt-dev, ramalingam.c, zbigniew.kempczynski, arjun.melkaveri From: Apoorva Singh <apoorva1.singh@intel.com> Add new library 'i915_blt' for various blt commands. Signed-off-by: Apoorva Singh <apoorva1.singh@intel.com> Signed-off-by: Ayaz A Siddiqui <ayaz.siddiqui@intel.com> Cc: Zbigniew Kempczyński <zbigniew.kempczynski@intel.com> Cc: Melkaveri, Arjun <arjun.melkaveri@intel.com> --- lib/i915/i915_blt.c | 393 ++++++++++++++++++++++++++++++++++++++++++++ lib/i915/i915_blt.h | 72 ++++++++ lib/meson.build | 1 + 3 files changed, 466 insertions(+) create mode 100644 lib/i915/i915_blt.c create mode 100644 lib/i915/i915_blt.h diff --git a/lib/i915/i915_blt.c b/lib/i915/i915_blt.c new file mode 100644 index 00000000..5d6d53e1 --- /dev/null +++ b/lib/i915/i915_blt.c @@ -0,0 +1,393 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2021 Intel Corporation + */ + +#include <errno.h> +#include <sys/ioctl.h> +#include <sys/time.h> +#include <malloc.h> +#include "drm.h" +#include "igt.h" +#include "i915_blt.h" +#include "i915/intel_mocs.h" + +/* + * make_block_copy_batch: + * @fd: open i915 drm file descriptor + * @batch_buf: the batch buffer to populate with the command + * @src: handle of the source BO + * @dst: handle of the destination BO + * @length: size of the src and dest BOs + * @reloc: pointer to the relocation entry for this command + * @offset_src: source address offset + * @offset_dst: destination address offset + * @copy_mode: different modes of copy + * @enable_compression: flag to enable compression + * @return: length of batch buffer created + */ +static int make_block_copy_batch(int fd, uint32_t *batch_buf, + uint32_t src, uint32_t dst, uint32_t length, + struct drm_i915_gem_relocation_entry *reloc, + uint64_t offset_src, uint64_t offset_dst, + enum copy_mode mode, bool enable_compression) +{ + uint32_t *b = batch_buf; + uint32_t devid; + uint8_t src_mocs = intel_get_uc_mocs(fd); + uint8_t dst_mocs = src_mocs; + int src_mem_type, dst_mem_type; + int dst_compression, src_compression; + int resolve; + + devid = intel_get_drm_devid(fd); + + igt_assert(AT_LEAST_GEN(devid, 12)); + + switch (mode) { + case SYS_TO_SYS: /* copy from smem to smem */ + src_mem_type = MEM_TYPE_SYS; + dst_mem_type = MEM_TYPE_SYS; + src_compression = 0; + dst_compression = 0; + resolve = NO_RESOLVE; + break; + case SYS_TO_LOCAL: /* copy from smem to lmem */ + src_mem_type = MEM_TYPE_SYS; + dst_mem_type = MEM_TYPE_LOCAL; + src_compression = 0; + dst_compression = enable_compression ? (COMPRESSION_ENABLE | AUX_CCS_E) : 0; + resolve = NO_RESOLVE; + break; + case LOCAL_TO_SYS: /* copy from lmem to smem */ + src_mem_type = MEM_TYPE_LOCAL; + dst_mem_type = MEM_TYPE_SYS; + src_compression = enable_compression ? (COMPRESSION_ENABLE | AUX_CCS_E) : 0; + dst_compression = 0; + resolve = NO_RESOLVE; + break; + case LOCAL_TO_LOCAL: /* copy from lmem to lmem */ + src_mem_type = MEM_TYPE_LOCAL; + dst_mem_type = MEM_TYPE_LOCAL; + src_compression = enable_compression ? (COMPRESSION_ENABLE | AUX_CCS_E) : 0; + dst_compression = enable_compression ? (COMPRESSION_ENABLE | AUX_CCS_E) : 0; + resolve = (src == dst) ? FULL_RESOLVE : NO_RESOLVE; + break; + } + + /* BG 0 */ + b[0] = BLOCK_COPY_BLT_CMD | (resolve << 12); + + /* BG 1 + * + * Using Tile 4 dimensions. Height = 32 rows + * Width = 128 bytes + */ + b[1] = dst_compression | TILE_4_FORMAT | TILE_4_WIDTH_DWORD | + dst_mocs << XY_BLOCK_COPY_BLT_MOCS_SHIFT; + + /* BG 3 + * + * X2 = TILE_4_WIDTH + * Y2 = (length / TILE_4_WIDTH) << 16: + */ + b[3] = TILE_4_WIDTH | (length >> 7) << DEST_Y2_COORDINATE_SHIFT; + + b[4] = offset_dst; + b[5] = offset_dst >> 32; + + /* relocate address in b[4] and b[5] */ + reloc->offset = 4 * (sizeof(uint32_t)); + reloc->delta = 0; + reloc->target_handle = dst; + reloc->read_domains = I915_GEM_DOMAIN_RENDER; + reloc->write_domain = I915_GEM_DOMAIN_RENDER; + reloc->presumed_offset = 0; + reloc++; + + /* BG 6 */ + b[6] = dst_mem_type << DEST_MEM_TYPE_SHIFT; + + /* BG 8 */ + b[8] = src_compression | TILE_4_WIDTH_DWORD | TILE_4_FORMAT | + src_mocs << XY_BLOCK_COPY_BLT_MOCS_SHIFT; + + b[9] = offset_src; + b[10] = offset_src >> 32; + + /* relocate address in b[9] and b[10] */ + reloc->offset = 9 * sizeof(uint32_t); + reloc->delta = 0; + reloc->target_handle = src; + reloc->read_domains = I915_GEM_DOMAIN_RENDER; + reloc->write_domain = 0; + reloc->presumed_offset = 0; + reloc++; + + /* BG 11 */ + b[11] = src_mem_type << SRC_MEM_TYPE_SHIFT; + + /* BG 16 */ + b[16] = SURFACE_TYPE_2D | + ((TILE_4_WIDTH - 1) << DEST_SURF_WIDTH_SHIFT) | + (TILE_4_HEIGHT - 1); + + /* BG 19 */ + b[19] = SURFACE_TYPE_2D | + ((TILE_4_WIDTH - 1) << SRC_SURF_WIDTH_SHIFT) | + (TILE_4_HEIGHT - 1); + + b += XY_BLOCK_COPY_BLT_LEN_DWORD; + + b[0] = MI_FLUSH_DW | MI_FLUSH_LLC | MI_INVALIDATE_TLB; + reloc->offset = 23 * sizeof(uint32_t); + reloc->delta = 0; + reloc->target_handle = dst_compression > 0 ? dst : src; + reloc->read_domains = 0; + reloc->write_domain = 0; + reloc->presumed_offset = 0; + reloc++; + b[3] = 0; + + b[4] = MI_FLUSH_DW | MI_FLUSH_CCS; + reloc->offset = 27 * sizeof(uint32_t); + reloc->delta = 0; + reloc->target_handle = dst_compression > 0 ? dst : src; + reloc->read_domains = 0; + reloc->write_domain = 0; + reloc->presumed_offset = 0; + reloc++; + b[7] = 0; + + b[8] = MI_BATCH_BUFFER_END; + b[9] = 0; + + b += 10; + + return (b - batch_buf) * sizeof(uint32_t); +} + +void xy_block_copy_blt(int fd, uint32_t bb_region, uint32_t src, uint32_t dst, + uint64_t src_size, uint64_t dst_size, uint64_t ahnd, + uint32_t length, enum copy_mode mode, bool enable_compression, + uint32_t ctx, struct intel_execution_engine2 *e) +{ + struct drm_i915_gem_relocation_entry reloc[4]; + struct drm_i915_gem_exec_object2 exec[3]; + struct drm_i915_gem_execbuffer2 execbuf; + int len; + uint32_t cmd, batch_buf[BATCH_SIZE / sizeof(uint32_t)] = {}; + uint64_t offset_src, offset_dst, offset_bb, bb_size, ret; + + bb_size = BATCH_SIZE; + ret = __gem_create_in_memory_regions(fd, &cmd, &bb_size, bb_region); + igt_assert_eq(ret, 0); + + offset_src = get_offset(ahnd, src, src_size, 0); + offset_dst = get_offset(ahnd, dst, dst_size, 0); + offset_bb = get_offset(ahnd, cmd, bb_size, 0); + + /* construct the batch buffer */ + memset(reloc, 0, sizeof(reloc)); + len = make_block_copy_batch(fd, batch_buf, src, dst, length, reloc, + offset_src, offset_dst, mode, + enable_compression); + + /* write batch buffer to 'cmd' BO */ + gem_write(fd, cmd, 0, batch_buf, len); + + /* Execute the batch buffer */ + memset(exec, 0, sizeof(exec)); + exec[0].handle = src; + exec[1].handle = dst; + exec[2].handle = cmd; + exec[2].relocation_count = !ahnd ? 4 : 0; + exec[2].relocs_ptr = to_user_pointer(reloc); + if (ahnd) { + exec[0].offset = offset_src; + exec[0].flags |= EXEC_OBJECT_PINNED | EXEC_OBJECT_SUPPORTS_48B_ADDRESS; + exec[1].offset = offset_dst; + exec[1].flags |= EXEC_OBJECT_PINNED | EXEC_OBJECT_WRITE | + EXEC_OBJECT_SUPPORTS_48B_ADDRESS; + exec[2].offset = offset_bb; + exec[2].flags |= EXEC_OBJECT_PINNED | EXEC_OBJECT_SUPPORTS_48B_ADDRESS; + } + + memset(&execbuf, 0, sizeof(execbuf)); + execbuf.buffers_ptr = to_user_pointer(exec); + execbuf.buffer_count = 3; + execbuf.batch_len = len; + execbuf.flags = e ? e->flags : I915_EXEC_BLT; + if (ctx) + execbuf.rsvd1 = ctx; + + gem_execbuf(fd, &execbuf); + gem_close(fd, cmd); + put_offset(ahnd, src); + put_offset(ahnd, dst); + put_offset(ahnd, cmd); +} + +/* + * make_ctrl_surf_batch: + * @fd: open i915 drm file descriptor + * @batch_buf: the batch buffer to populate with the command + * @src: handle of the source BO + * @dst: handle of the destination BO + * @length: size of the ctrl surf in bytes + * @reloc: pointer to the relocation entyr for this command + * @offset_src: source address offset + * @offset_dst: destination address offset + * @writetodev: flag to enable direct access of the address + * @return: length of batch buffer created + */ +static int make_ctrl_surf_batch(int fd, uint32_t *batch_buf, + uint32_t src, uint32_t dst, uint32_t length, + struct drm_i915_gem_relocation_entry *reloc, + uint64_t offset_src, uint64_t offset_dst, + bool writetodev) +{ + int num_ccs_blocks, src_mem_access, dst_mem_access; + uint32_t *b = batch_buf; + uint8_t src_mocs = intel_get_uc_mocs(fd); + uint8_t dst_mocs = src_mocs; + + num_ccs_blocks = length / CCS_RATIO; + if (num_ccs_blocks < 1) + num_ccs_blocks = 1; + if (num_ccs_blocks > NUM_CCS_BLKS_PER_XFER) + return 0; + + if (writetodev) { + src_mem_access = DIRECT_ACCESS; + dst_mem_access = INDIRECT_ACCESS; + } else { + src_mem_access = INDIRECT_ACCESS; + dst_mem_access = DIRECT_ACCESS; + } + + /* + * We use logical AND with 1023 since the size field + * takes values which is in the range of 0 - 1023 + */ + b[0] = ((XY_CTRL_SURF_COPY_BLT) | + (src_mem_access << SRC_ACCESS_TYPE_SHIFT) | + (dst_mem_access << DST_ACCESS_TYPE_SHIFT) | + (((num_ccs_blocks - 1) & 1023) << CCS_SIZE_SHIFT)); + + b[1] = offset_src; + b[2] = offset_src >> 32 | src_mocs << XY_CTRL_SURF_COPY_BLT_MOCS_SHIFT; + + /* relocate address in b[1] and b[2] */ + reloc->offset = 1 * sizeof(uint32_t); + reloc->delta = 0; + reloc->target_handle = src; + reloc->read_domains = I915_GEM_DOMAIN_RENDER; + reloc->write_domain = 0; + reloc->presumed_offset = 0; + reloc++; + + b[3] = offset_dst; + b[4] = offset_dst >> 32 | dst_mocs << XY_CTRL_SURF_COPY_BLT_MOCS_SHIFT; + + /* relocate address in b[3] and b[4] */ + reloc->offset = 3 * (sizeof(uint32_t)); + reloc->delta = 0; + reloc->target_handle = dst; + reloc->read_domains = I915_GEM_DOMAIN_RENDER; + reloc->write_domain = I915_GEM_DOMAIN_RENDER; + reloc->presumed_offset = 0; + reloc++; + + b[5] = 0; + + b[6] = MI_FLUSH_DW | MI_FLUSH_LLC | MI_INVALIDATE_TLB; + + reloc->offset = 7 * sizeof(uint32_t); + reloc->delta = 0; + reloc->target_handle = + dst_mem_access == INDIRECT_ACCESS ? dst : src; + reloc->read_domains = 0; + reloc->write_domain = 0; + reloc->presumed_offset = 0; + reloc++; + b[9] = 0; + + b[10] = MI_FLUSH_DW | MI_FLUSH_CCS; + reloc->offset = 11 * sizeof(uint32_t); + reloc->delta = 0; + reloc->target_handle = + dst_mem_access == INDIRECT_ACCESS ? dst : src; + reloc->read_domains = 0; + reloc->write_domain = 0; + reloc->presumed_offset = 0; + reloc++; + b[13] = 0; + + b[14] = MI_BATCH_BUFFER_END; + b[15] = 0; + + b += 16; + + return (b - batch_buf) * sizeof(uint32_t); +} + +void xy_ctrl_surf_copy_blt(int fd, uint32_t bb_region, uint32_t src, + uint32_t dst, uint64_t src_size, uint64_t dst_size, + uint64_t ahnd, uint32_t length, bool writetodev, + uint32_t ctx, struct intel_execution_engine2 *e) +{ + struct drm_i915_gem_relocation_entry reloc[4]; + struct drm_i915_gem_exec_object2 exec[3]; + struct drm_i915_gem_execbuffer2 execbuf; + int len; + uint32_t cmd, batch_buf[BATCH_SIZE / sizeof(uint32_t)] = {}; + uint64_t offset_src, offset_dst, offset_bb, bb_size, ret; + + bb_size = BATCH_SIZE; + ret = __gem_create_in_memory_regions(fd, &cmd, &bb_size, bb_region); + igt_assert_eq(ret, 0); + + offset_src = get_offset(ahnd, src, src_size, 0); + offset_dst = get_offset(ahnd, dst, dst_size, 0); + offset_bb = get_offset(ahnd, cmd, bb_size, 0); + + /* construct batch command buffer */ + memset(reloc, 0, sizeof(reloc)); + len = make_ctrl_surf_batch(fd, batch_buf, src, dst, length, reloc, + offset_src, offset_dst, writetodev); + + /* Copy the batch buff to BO cmd */ + gem_write(fd, cmd, 0, batch_buf, len); + + /* Execute the batch buffer */ + memset(exec, 0, sizeof(exec)); + exec[0].handle = src; + exec[1].handle = dst; + exec[2].handle = cmd; + exec[2].relocation_count = !ahnd ? 4 : 0; + exec[2].relocs_ptr = to_user_pointer(reloc); + if (ahnd) { + exec[0].offset = offset_src; + exec[0].flags |= EXEC_OBJECT_PINNED | EXEC_OBJECT_SUPPORTS_48B_ADDRESS; + exec[1].offset = offset_dst; + exec[1].flags |= EXEC_OBJECT_PINNED | EXEC_OBJECT_WRITE | + EXEC_OBJECT_SUPPORTS_48B_ADDRESS; + exec[2].offset = offset_bb; + exec[2].flags |= EXEC_OBJECT_PINNED | EXEC_OBJECT_SUPPORTS_48B_ADDRESS; + } + + memset(&execbuf, 0, sizeof(execbuf)); + execbuf.buffers_ptr = to_user_pointer(exec); + execbuf.buffer_count = 3; + execbuf.batch_len = len; + execbuf.flags = e ? e->flags : I915_EXEC_BLT; + if (ctx) + execbuf.rsvd1 = ctx; + + gem_execbuf(fd, &execbuf); + gem_close(fd, cmd); + put_offset(ahnd, src); + put_offset(ahnd, dst); + put_offset(ahnd, cmd); +} diff --git a/lib/i915/i915_blt.h b/lib/i915/i915_blt.h new file mode 100644 index 00000000..ff3eee7f --- /dev/null +++ b/lib/i915/i915_blt.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ + +#include <errno.h> +#include <sys/ioctl.h> +#include <sys/time.h> +#include <malloc.h> +#include "drm.h" +#include "igt.h" + +#define MI_FLUSH_DW_LEN_DWORD 4 +#define MI_FLUSH_DW (0x26 << 23 | 1) +#define MI_FLUSH_CCS BIT(16) +#define MI_FLUSH_LLC BIT(9) +#define MI_INVALIDATE_TLB BIT(18) + +/* XY_BLOCK_COPY_BLT instruction has 22 bit groups 1 DWORD each */ +#define XY_BLOCK_COPY_BLT_LEN_DWORD 22 +#define BLOCK_COPY_BLT_CMD (2 << 29 | 0x41 << 22 | 0x14) +#define COMPRESSION_ENABLE BIT(29) +#define AUX_CCS_E (5 << 18) +#define NO_RESOLVE 0 +#define FULL_RESOLVE 1 +#define PARTIAL_RESOLVE 2 +#define TILE_4_FORMAT (2 << 30) +#define TILE_4_WIDTH (128) +#define TILE_4_WIDTH_DWORD ((128 >> 2) - 1) +#define TILE_4_HEIGHT (32) +#define SURFACE_TYPE_2D BIT(29) + +#define DEST_Y2_COORDINATE_SHIFT (16) +#define DEST_MEM_TYPE_SHIFT (31) +#define SRC_MEM_TYPE_SHIFT (31) +#define DEST_SURF_WIDTH_SHIFT (14) +#define SRC_SURF_WIDTH_SHIFT (14) + +#define XY_CTRL_SURF_COPY_BLT (2 << 29 | 0x48 << 22 | 3) +#define SRC_ACCESS_TYPE_SHIFT 21 +#define DST_ACCESS_TYPE_SHIFT 20 +#define CCS_SIZE_SHIFT 8 +#define MI_INSTR(opcode, flags) (((opcode) << 23) | (flags)) +#define MI_ARB_CHECK MI_INSTR(0x05, 0) +#define NUM_CCS_BLKS_PER_XFER 1024 +#define INDIRECT_ACCESS 0 +#define DIRECT_ACCESS 1 + +#define BATCH_SIZE 4096 +#define BOSIZE_MIN (4 * 1024) +#define BOSIZE_MAX (4 * 1024 * 1024) +#define CCS_RATIO 256 + +#define MEM_TYPE_SYS 1 +#define MEM_TYPE_LOCAL 0 + +enum copy_mode { + SYS_TO_SYS = 0, + SYS_TO_LOCAL, + LOCAL_TO_SYS, + LOCAL_TO_LOCAL, +}; + +void xy_block_copy_blt(int fd, uint32_t bb_region, uint32_t src, uint32_t dst, + uint64_t src_size, uint64_t dst_size, uint64_t ahnd, + uint32_t length, enum copy_mode mode, bool enable_compression, + uint32_t ctx, struct intel_execution_engine2 *e); + +void xy_ctrl_surf_copy_blt(int fd, uint32_t bb_region, uint32_t src, uint32_t dst, + uint64_t src_size, uint64_t dst_size, uint64_t ahnd, + uint32_t length, bool writetodev, uint32_t ctx, + struct intel_execution_engine2 *e); diff --git a/lib/meson.build b/lib/meson.build index f500f0f1..f2924541 100644 --- a/lib/meson.build +++ b/lib/meson.build @@ -12,6 +12,7 @@ lib_sources = [ 'i915/gem_vm.c', 'i915/intel_memory_region.c', 'i915/intel_mocs.c', + 'i915/i915_blt.c', 'igt_collection.c', 'igt_color_encoding.c', 'igt_debugfs.c', -- 2.25.1 ^ permalink raw reply related [flat|nested] 11+ messages in thread
* Re: [igt-dev] [PATCH i-g-t, v5 2/5] lib/i915: Introduce library i915_blt 2021-12-19 13:14 ` [igt-dev] [PATCH i-g-t, v5 2/5] lib/i915: Introduce library i915_blt apoorva1.singh @ 2021-12-20 13:06 ` Zbigniew Kempczyński 2021-12-20 13:49 ` Petri Latvala 1 sibling, 0 replies; 11+ messages in thread From: Zbigniew Kempczyński @ 2021-12-20 13:06 UTC (permalink / raw) To: apoorva1.singh; +Cc: igt-dev On Sun, Dec 19, 2021 at 06:44:40PM +0530, apoorva1.singh@intel.com wrote: > From: Apoorva Singh <apoorva1.singh@intel.com> > > Add new library 'i915_blt' for various blt commands. > > Signed-off-by: Apoorva Singh <apoorva1.singh@intel.com> > Signed-off-by: Ayaz A Siddiqui <ayaz.siddiqui@intel.com> > Cc: Zbigniew Kempczyński <zbigniew.kempczynski@intel.com> > Cc: Melkaveri, Arjun <arjun.melkaveri@intel.com> > --- > lib/i915/i915_blt.c | 393 ++++++++++++++++++++++++++++++++++++++++++++ > lib/i915/i915_blt.h | 72 ++++++++ > lib/meson.build | 1 + > 3 files changed, 466 insertions(+) > create mode 100644 lib/i915/i915_blt.c > create mode 100644 lib/i915/i915_blt.h > > diff --git a/lib/i915/i915_blt.c b/lib/i915/i915_blt.c > new file mode 100644 > index 00000000..5d6d53e1 > --- /dev/null > +++ b/lib/i915/i915_blt.c > @@ -0,0 +1,393 @@ > +// SPDX-License-Identifier: MIT > +/* > + * Copyright © 2021 Intel Corporation > + */ > + > +#include <errno.h> > +#include <sys/ioctl.h> > +#include <sys/time.h> > +#include <malloc.h> > +#include "drm.h" > +#include "igt.h" > +#include "i915_blt.h" > +#include "i915/intel_mocs.h" > + > +/* > + * make_block_copy_batch: > + * @fd: open i915 drm file descriptor > + * @batch_buf: the batch buffer to populate with the command > + * @src: handle of the source BO > + * @dst: handle of the destination BO > + * @length: size of the src and dest BOs > + * @reloc: pointer to the relocation entry for this command > + * @offset_src: source address offset > + * @offset_dst: destination address offset > + * @copy_mode: different modes of copy > + * @enable_compression: flag to enable compression > + * @return: length of batch buffer created > + */ > +static int make_block_copy_batch(int fd, uint32_t *batch_buf, > + uint32_t src, uint32_t dst, uint32_t length, > + struct drm_i915_gem_relocation_entry *reloc, > + uint64_t offset_src, uint64_t offset_dst, > + enum copy_mode mode, bool enable_compression) > +{ > + uint32_t *b = batch_buf; > + uint32_t devid; > + uint8_t src_mocs = intel_get_uc_mocs(fd); > + uint8_t dst_mocs = src_mocs; > + int src_mem_type, dst_mem_type; > + int dst_compression, src_compression; > + int resolve; > + > + devid = intel_get_drm_devid(fd); > + > + igt_assert(AT_LEAST_GEN(devid, 12)); > + > + switch (mode) { > + case SYS_TO_SYS: /* copy from smem to smem */ > + src_mem_type = MEM_TYPE_SYS; > + dst_mem_type = MEM_TYPE_SYS; > + src_compression = 0; > + dst_compression = 0; > + resolve = NO_RESOLVE; > + break; > + case SYS_TO_LOCAL: /* copy from smem to lmem */ > + src_mem_type = MEM_TYPE_SYS; > + dst_mem_type = MEM_TYPE_LOCAL; > + src_compression = 0; > + dst_compression = enable_compression ? (COMPRESSION_ENABLE | AUX_CCS_E) : 0; > + resolve = NO_RESOLVE; > + break; > + case LOCAL_TO_SYS: /* copy from lmem to smem */ > + src_mem_type = MEM_TYPE_LOCAL; > + dst_mem_type = MEM_TYPE_SYS; > + src_compression = enable_compression ? (COMPRESSION_ENABLE | AUX_CCS_E) : 0; > + dst_compression = 0; > + resolve = NO_RESOLVE; > + break; > + case LOCAL_TO_LOCAL: /* copy from lmem to lmem */ > + src_mem_type = MEM_TYPE_LOCAL; > + dst_mem_type = MEM_TYPE_LOCAL; > + src_compression = enable_compression ? (COMPRESSION_ENABLE | AUX_CCS_E) : 0; > + dst_compression = enable_compression ? (COMPRESSION_ENABLE | AUX_CCS_E) : 0; > + resolve = (src == dst) ? FULL_RESOLVE : NO_RESOLVE; > + break; > + } > + > + /* BG 0 */ > + b[0] = BLOCK_COPY_BLT_CMD | (resolve << 12); > + > + /* BG 1 > + * > + * Using Tile 4 dimensions. Height = 32 rows > + * Width = 128 bytes > + */ > + b[1] = dst_compression | TILE_4_FORMAT | TILE_4_WIDTH_DWORD | > + dst_mocs << XY_BLOCK_COPY_BLT_MOCS_SHIFT; > + > + /* BG 3 > + * > + * X2 = TILE_4_WIDTH > + * Y2 = (length / TILE_4_WIDTH) << 16: > + */ > + b[3] = TILE_4_WIDTH | (length >> 7) << DEST_Y2_COORDINATE_SHIFT; > + > + b[4] = offset_dst; > + b[5] = offset_dst >> 32; > + > + /* relocate address in b[4] and b[5] */ > + reloc->offset = 4 * (sizeof(uint32_t)); > + reloc->delta = 0; > + reloc->target_handle = dst; > + reloc->read_domains = I915_GEM_DOMAIN_RENDER; > + reloc->write_domain = I915_GEM_DOMAIN_RENDER; > + reloc->presumed_offset = 0; Set to -1 to enforce relocation could occur (TGL only). > + reloc++; > + > + /* BG 6 */ > + b[6] = dst_mem_type << DEST_MEM_TYPE_SHIFT; > + > + /* BG 8 */ > + b[8] = src_compression | TILE_4_WIDTH_DWORD | TILE_4_FORMAT | > + src_mocs << XY_BLOCK_COPY_BLT_MOCS_SHIFT; > + > + b[9] = offset_src; > + b[10] = offset_src >> 32; > + > + /* relocate address in b[9] and b[10] */ > + reloc->offset = 9 * sizeof(uint32_t); > + reloc->delta = 0; > + reloc->target_handle = src; > + reloc->read_domains = I915_GEM_DOMAIN_RENDER; > + reloc->write_domain = 0; > + reloc->presumed_offset = 0; Same. > + reloc++; > + > + /* BG 11 */ > + b[11] = src_mem_type << SRC_MEM_TYPE_SHIFT; > + > + /* BG 16 */ > + b[16] = SURFACE_TYPE_2D | > + ((TILE_4_WIDTH - 1) << DEST_SURF_WIDTH_SHIFT) | > + (TILE_4_HEIGHT - 1); > + > + /* BG 19 */ > + b[19] = SURFACE_TYPE_2D | > + ((TILE_4_WIDTH - 1) << SRC_SURF_WIDTH_SHIFT) | > + (TILE_4_HEIGHT - 1); > + > + b += XY_BLOCK_COPY_BLT_LEN_DWORD; > + > + b[0] = MI_FLUSH_DW | MI_FLUSH_LLC | MI_INVALIDATE_TLB; > + reloc->offset = 23 * sizeof(uint32_t); > + reloc->delta = 0; > + reloc->target_handle = dst_compression > 0 ? dst : src; > + reloc->read_domains = 0; > + reloc->write_domain = 0; > + reloc->presumed_offset = 0; Same. > + reloc++; > + b[3] = 0; > + > + b[4] = MI_FLUSH_DW | MI_FLUSH_CCS; > + reloc->offset = 27 * sizeof(uint32_t); > + reloc->delta = 0; > + reloc->target_handle = dst_compression > 0 ? dst : src; > + reloc->read_domains = 0; > + reloc->write_domain = 0; > + reloc->presumed_offset = 0; Same. > + reloc++; > + b[7] = 0; > + > + b[8] = MI_BATCH_BUFFER_END; > + b[9] = 0; > + > + b += 10; > + > + return (b - batch_buf) * sizeof(uint32_t); > +} > + > +void xy_block_copy_blt(int fd, uint32_t bb_region, uint32_t src, uint32_t dst, > + uint64_t src_size, uint64_t dst_size, uint64_t ahnd, > + uint32_t length, enum copy_mode mode, bool enable_compression, > + uint32_t ctx, struct intel_execution_engine2 *e) > +{ > + struct drm_i915_gem_relocation_entry reloc[4]; > + struct drm_i915_gem_exec_object2 exec[3]; > + struct drm_i915_gem_execbuffer2 execbuf; > + int len; > + uint32_t cmd, batch_buf[BATCH_SIZE / sizeof(uint32_t)] = {}; > + uint64_t offset_src, offset_dst, offset_bb, bb_size, ret; > + > + bb_size = BATCH_SIZE; > + ret = __gem_create_in_memory_regions(fd, &cmd, &bb_size, bb_region); > + igt_assert_eq(ret, 0); > + > + offset_src = get_offset(ahnd, src, src_size, 0); > + offset_dst = get_offset(ahnd, dst, dst_size, 0); > + offset_bb = get_offset(ahnd, cmd, bb_size, 0); > + > + /* construct the batch buffer */ > + memset(reloc, 0, sizeof(reloc)); > + len = make_block_copy_batch(fd, batch_buf, src, dst, length, reloc, > + offset_src, offset_dst, mode, > + enable_compression); > + > + /* write batch buffer to 'cmd' BO */ > + gem_write(fd, cmd, 0, batch_buf, len); > + > + /* Execute the batch buffer */ > + memset(exec, 0, sizeof(exec)); > + exec[0].handle = src; > + exec[1].handle = dst; > + exec[2].handle = cmd; > + exec[2].relocation_count = !ahnd ? 4 : 0; > + exec[2].relocs_ptr = to_user_pointer(reloc); > + if (ahnd) { > + exec[0].offset = offset_src; > + exec[0].flags |= EXEC_OBJECT_PINNED | EXEC_OBJECT_SUPPORTS_48B_ADDRESS; > + exec[1].offset = offset_dst; > + exec[1].flags |= EXEC_OBJECT_PINNED | EXEC_OBJECT_WRITE | > + EXEC_OBJECT_SUPPORTS_48B_ADDRESS; > + exec[2].offset = offset_bb; > + exec[2].flags |= EXEC_OBJECT_PINNED | EXEC_OBJECT_SUPPORTS_48B_ADDRESS; > + } > + > + memset(&execbuf, 0, sizeof(execbuf)); > + execbuf.buffers_ptr = to_user_pointer(exec); > + execbuf.buffer_count = 3; > + execbuf.batch_len = len; > + execbuf.flags = e ? e->flags : I915_EXEC_BLT; > + if (ctx) > + execbuf.rsvd1 = ctx; Conditional is not necessary, just: execbuf.rsvd1 = ctx; is ok (you need to provide ctx anyway). > + > + gem_execbuf(fd, &execbuf); > + gem_close(fd, cmd); > + put_offset(ahnd, src); > + put_offset(ahnd, dst); > + put_offset(ahnd, cmd); > +} > + > +/* > + * make_ctrl_surf_batch: > + * @fd: open i915 drm file descriptor > + * @batch_buf: the batch buffer to populate with the command > + * @src: handle of the source BO > + * @dst: handle of the destination BO > + * @length: size of the ctrl surf in bytes > + * @reloc: pointer to the relocation entyr for this command > + * @offset_src: source address offset > + * @offset_dst: destination address offset > + * @writetodev: flag to enable direct access of the address > + * @return: length of batch buffer created > + */ > +static int make_ctrl_surf_batch(int fd, uint32_t *batch_buf, > + uint32_t src, uint32_t dst, uint32_t length, > + struct drm_i915_gem_relocation_entry *reloc, > + uint64_t offset_src, uint64_t offset_dst, > + bool writetodev) > +{ > + int num_ccs_blocks, src_mem_access, dst_mem_access; > + uint32_t *b = batch_buf; > + uint8_t src_mocs = intel_get_uc_mocs(fd); > + uint8_t dst_mocs = src_mocs; > + > + num_ccs_blocks = length / CCS_RATIO; > + if (num_ccs_blocks < 1) > + num_ccs_blocks = 1; > + if (num_ccs_blocks > NUM_CCS_BLKS_PER_XFER) > + return 0; > + > + if (writetodev) { > + src_mem_access = DIRECT_ACCESS; > + dst_mem_access = INDIRECT_ACCESS; > + } else { > + src_mem_access = INDIRECT_ACCESS; > + dst_mem_access = DIRECT_ACCESS; > + } > + > + /* > + * We use logical AND with 1023 since the size field > + * takes values which is in the range of 0 - 1023 > + */ > + b[0] = ((XY_CTRL_SURF_COPY_BLT) | > + (src_mem_access << SRC_ACCESS_TYPE_SHIFT) | > + (dst_mem_access << DST_ACCESS_TYPE_SHIFT) | > + (((num_ccs_blocks - 1) & 1023) << CCS_SIZE_SHIFT)); > + > + b[1] = offset_src; > + b[2] = offset_src >> 32 | src_mocs << XY_CTRL_SURF_COPY_BLT_MOCS_SHIFT; > + > + /* relocate address in b[1] and b[2] */ > + reloc->offset = 1 * sizeof(uint32_t); > + reloc->delta = 0; > + reloc->target_handle = src; > + reloc->read_domains = I915_GEM_DOMAIN_RENDER; > + reloc->write_domain = 0; > + reloc->presumed_offset = 0; Same as above, set to -1. Applies below too. > + reloc++; > + > + b[3] = offset_dst; > + b[4] = offset_dst >> 32 | dst_mocs << XY_CTRL_SURF_COPY_BLT_MOCS_SHIFT; > + > + /* relocate address in b[3] and b[4] */ > + reloc->offset = 3 * (sizeof(uint32_t)); > + reloc->delta = 0; > + reloc->target_handle = dst; > + reloc->read_domains = I915_GEM_DOMAIN_RENDER; > + reloc->write_domain = I915_GEM_DOMAIN_RENDER; > + reloc->presumed_offset = 0; > + reloc++; > + > + b[5] = 0; > + > + b[6] = MI_FLUSH_DW | MI_FLUSH_LLC | MI_INVALIDATE_TLB; > + > + reloc->offset = 7 * sizeof(uint32_t); > + reloc->delta = 0; > + reloc->target_handle = > + dst_mem_access == INDIRECT_ACCESS ? dst : src; > + reloc->read_domains = 0; > + reloc->write_domain = 0; > + reloc->presumed_offset = 0; > + reloc++; > + b[9] = 0; > + > + b[10] = MI_FLUSH_DW | MI_FLUSH_CCS; > + reloc->offset = 11 * sizeof(uint32_t); > + reloc->delta = 0; > + reloc->target_handle = > + dst_mem_access == INDIRECT_ACCESS ? dst : src; > + reloc->read_domains = 0; > + reloc->write_domain = 0; > + reloc->presumed_offset = 0; > + reloc++; > + b[13] = 0; > + > + b[14] = MI_BATCH_BUFFER_END; > + b[15] = 0; > + > + b += 16; > + > + return (b - batch_buf) * sizeof(uint32_t); > +} > + > +void xy_ctrl_surf_copy_blt(int fd, uint32_t bb_region, uint32_t src, > + uint32_t dst, uint64_t src_size, uint64_t dst_size, > + uint64_t ahnd, uint32_t length, bool writetodev, > + uint32_t ctx, struct intel_execution_engine2 *e) > +{ > + struct drm_i915_gem_relocation_entry reloc[4]; > + struct drm_i915_gem_exec_object2 exec[3]; > + struct drm_i915_gem_execbuffer2 execbuf; > + int len; > + uint32_t cmd, batch_buf[BATCH_SIZE / sizeof(uint32_t)] = {}; > + uint64_t offset_src, offset_dst, offset_bb, bb_size, ret; > + > + bb_size = BATCH_SIZE; > + ret = __gem_create_in_memory_regions(fd, &cmd, &bb_size, bb_region); > + igt_assert_eq(ret, 0); > + > + offset_src = get_offset(ahnd, src, src_size, 0); > + offset_dst = get_offset(ahnd, dst, dst_size, 0); > + offset_bb = get_offset(ahnd, cmd, bb_size, 0); > + > + /* construct batch command buffer */ > + memset(reloc, 0, sizeof(reloc)); > + len = make_ctrl_surf_batch(fd, batch_buf, src, dst, length, reloc, > + offset_src, offset_dst, writetodev); > + > + /* Copy the batch buff to BO cmd */ > + gem_write(fd, cmd, 0, batch_buf, len); > + > + /* Execute the batch buffer */ > + memset(exec, 0, sizeof(exec)); > + exec[0].handle = src; > + exec[1].handle = dst; > + exec[2].handle = cmd; > + exec[2].relocation_count = !ahnd ? 4 : 0; > + exec[2].relocs_ptr = to_user_pointer(reloc); > + if (ahnd) { > + exec[0].offset = offset_src; > + exec[0].flags |= EXEC_OBJECT_PINNED | EXEC_OBJECT_SUPPORTS_48B_ADDRESS; > + exec[1].offset = offset_dst; > + exec[1].flags |= EXEC_OBJECT_PINNED | EXEC_OBJECT_WRITE | > + EXEC_OBJECT_SUPPORTS_48B_ADDRESS; > + exec[2].offset = offset_bb; > + exec[2].flags |= EXEC_OBJECT_PINNED | EXEC_OBJECT_SUPPORTS_48B_ADDRESS; > + } > + > + memset(&execbuf, 0, sizeof(execbuf)); > + execbuf.buffers_ptr = to_user_pointer(exec); > + execbuf.buffer_count = 3; > + execbuf.batch_len = len; > + execbuf.flags = e ? e->flags : I915_EXEC_BLT; > + if (ctx) > + execbuf.rsvd1 = ctx; Remove conditionals. > + > + gem_execbuf(fd, &execbuf); > + gem_close(fd, cmd); > + put_offset(ahnd, src); > + put_offset(ahnd, dst); > + put_offset(ahnd, cmd); > +} > diff --git a/lib/i915/i915_blt.h b/lib/i915/i915_blt.h > new file mode 100644 > index 00000000..ff3eee7f > --- /dev/null > +++ b/lib/i915/i915_blt.h > @@ -0,0 +1,72 @@ > +/* SPDX-License-Identifier: MIT */ > +/* > + * Copyright © 2021 Intel Corporation > + */ > + > +#include <errno.h> > +#include <sys/ioctl.h> > +#include <sys/time.h> > +#include <malloc.h> > +#include "drm.h" > +#include "igt.h" > + > +#define MI_FLUSH_DW_LEN_DWORD 4 > +#define MI_FLUSH_DW (0x26 << 23 | 1) > +#define MI_FLUSH_CCS BIT(16) > +#define MI_FLUSH_LLC BIT(9) > +#define MI_INVALIDATE_TLB BIT(18) > + > +/* XY_BLOCK_COPY_BLT instruction has 22 bit groups 1 DWORD each */ > +#define XY_BLOCK_COPY_BLT_LEN_DWORD 22 > +#define BLOCK_COPY_BLT_CMD (2 << 29 | 0x41 << 22 | 0x14) > +#define COMPRESSION_ENABLE BIT(29) > +#define AUX_CCS_E (5 << 18) > +#define NO_RESOLVE 0 > +#define FULL_RESOLVE 1 > +#define PARTIAL_RESOLVE 2 > +#define TILE_4_FORMAT (2 << 30) > +#define TILE_4_WIDTH (128) > +#define TILE_4_WIDTH_DWORD ((128 >> 2) - 1) > +#define TILE_4_HEIGHT (32) > +#define SURFACE_TYPE_2D BIT(29) > + > +#define DEST_Y2_COORDINATE_SHIFT (16) > +#define DEST_MEM_TYPE_SHIFT (31) > +#define SRC_MEM_TYPE_SHIFT (31) > +#define DEST_SURF_WIDTH_SHIFT (14) > +#define SRC_SURF_WIDTH_SHIFT (14) > + > +#define XY_CTRL_SURF_COPY_BLT (2 << 29 | 0x48 << 22 | 3) > +#define SRC_ACCESS_TYPE_SHIFT 21 > +#define DST_ACCESS_TYPE_SHIFT 20 > +#define CCS_SIZE_SHIFT 8 > +#define MI_INSTR(opcode, flags) (((opcode) << 23) | (flags)) > +#define MI_ARB_CHECK MI_INSTR(0x05, 0) > +#define NUM_CCS_BLKS_PER_XFER 1024 > +#define INDIRECT_ACCESS 0 > +#define DIRECT_ACCESS 1 > + > +#define BATCH_SIZE 4096 > +#define BOSIZE_MIN (4 * 1024) > +#define BOSIZE_MAX (4 * 1024 * 1024) > +#define CCS_RATIO 256 > + > +#define MEM_TYPE_SYS 1 > +#define MEM_TYPE_LOCAL 0 > + > +enum copy_mode { > + SYS_TO_SYS = 0, > + SYS_TO_LOCAL, > + LOCAL_TO_SYS, > + LOCAL_TO_LOCAL, > +}; > + Those functions should be documented as they are public. Don't forget about adding this to xml for processing. -- Zbigniew > +void xy_block_copy_blt(int fd, uint32_t bb_region, uint32_t src, uint32_t dst, > + uint64_t src_size, uint64_t dst_size, uint64_t ahnd, > + uint32_t length, enum copy_mode mode, bool enable_compression, > + uint32_t ctx, struct intel_execution_engine2 *e); > + > +void xy_ctrl_surf_copy_blt(int fd, uint32_t bb_region, uint32_t src, uint32_t dst, > + uint64_t src_size, uint64_t dst_size, uint64_t ahnd, > + uint32_t length, bool writetodev, uint32_t ctx, > + struct intel_execution_engine2 *e); > diff --git a/lib/meson.build b/lib/meson.build > index f500f0f1..f2924541 100644 > --- a/lib/meson.build > +++ b/lib/meson.build > @@ -12,6 +12,7 @@ lib_sources = [ > 'i915/gem_vm.c', > 'i915/intel_memory_region.c', > 'i915/intel_mocs.c', > + 'i915/i915_blt.c', > 'igt_collection.c', > 'igt_color_encoding.c', > 'igt_debugfs.c', > -- > 2.25.1 > ^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [igt-dev] [PATCH i-g-t, v5 2/5] lib/i915: Introduce library i915_blt 2021-12-19 13:14 ` [igt-dev] [PATCH i-g-t, v5 2/5] lib/i915: Introduce library i915_blt apoorva1.singh 2021-12-20 13:06 ` Zbigniew Kempczyński @ 2021-12-20 13:49 ` Petri Latvala 1 sibling, 0 replies; 11+ messages in thread From: Petri Latvala @ 2021-12-20 13:49 UTC (permalink / raw) To: apoorva1.singh; +Cc: igt-dev On Sun, Dec 19, 2021 at 06:44:40PM +0530, apoorva1.singh@intel.com wrote: > From: Apoorva Singh <apoorva1.singh@intel.com> > > Add new library 'i915_blt' for various blt commands. > > Signed-off-by: Apoorva Singh <apoorva1.singh@intel.com> > Signed-off-by: Ayaz A Siddiqui <ayaz.siddiqui@intel.com> > Cc: Zbigniew Kempczyński <zbigniew.kempczynski@intel.com> > Cc: Melkaveri, Arjun <arjun.melkaveri@intel.com> > --- > lib/i915/i915_blt.c | 393 ++++++++++++++++++++++++++++++++++++++++++++ > lib/i915/i915_blt.h | 72 ++++++++ > lib/meson.build | 1 + > 3 files changed, 466 insertions(+) > create mode 100644 lib/i915/i915_blt.c > create mode 100644 lib/i915/i915_blt.h > > diff --git a/lib/i915/i915_blt.c b/lib/i915/i915_blt.c > new file mode 100644 > index 00000000..5d6d53e1 > --- /dev/null > +++ b/lib/i915/i915_blt.c > @@ -0,0 +1,393 @@ > +// SPDX-License-Identifier: MIT > +/* > + * Copyright © 2021 Intel Corporation > + */ > + > +#include <errno.h> > +#include <sys/ioctl.h> > +#include <sys/time.h> > +#include <malloc.h> > +#include "drm.h" > +#include "igt.h" > +#include "i915_blt.h" > +#include "i915/intel_mocs.h" > + > +/* > + * make_block_copy_batch: > + * @fd: open i915 drm file descriptor > + * @batch_buf: the batch buffer to populate with the command > + * @src: handle of the source BO > + * @dst: handle of the destination BO > + * @length: size of the src and dest BOs > + * @reloc: pointer to the relocation entry for this command > + * @offset_src: source address offset > + * @offset_dst: destination address offset > + * @copy_mode: different modes of copy > + * @enable_compression: flag to enable compression > + * @return: length of batch buffer created > + */ > +static int make_block_copy_batch(int fd, uint32_t *batch_buf, > + uint32_t src, uint32_t dst, uint32_t length, > + struct drm_i915_gem_relocation_entry *reloc, > + uint64_t offset_src, uint64_t offset_dst, > + enum copy_mode mode, bool enable_compression) > +{ > + uint32_t *b = batch_buf; > + uint32_t devid; > + uint8_t src_mocs = intel_get_uc_mocs(fd); > + uint8_t dst_mocs = src_mocs; > + int src_mem_type, dst_mem_type; > + int dst_compression, src_compression; > + int resolve; > + > + devid = intel_get_drm_devid(fd); > + > + igt_assert(AT_LEAST_GEN(devid, 12)); > + > + switch (mode) { > + case SYS_TO_SYS: /* copy from smem to smem */ > + src_mem_type = MEM_TYPE_SYS; > + dst_mem_type = MEM_TYPE_SYS; > + src_compression = 0; > + dst_compression = 0; > + resolve = NO_RESOLVE; > + break; > + case SYS_TO_LOCAL: /* copy from smem to lmem */ > + src_mem_type = MEM_TYPE_SYS; > + dst_mem_type = MEM_TYPE_LOCAL; > + src_compression = 0; > + dst_compression = enable_compression ? (COMPRESSION_ENABLE | AUX_CCS_E) : 0; > + resolve = NO_RESOLVE; > + break; > + case LOCAL_TO_SYS: /* copy from lmem to smem */ > + src_mem_type = MEM_TYPE_LOCAL; > + dst_mem_type = MEM_TYPE_SYS; > + src_compression = enable_compression ? (COMPRESSION_ENABLE | AUX_CCS_E) : 0; > + dst_compression = 0; > + resolve = NO_RESOLVE; > + break; > + case LOCAL_TO_LOCAL: /* copy from lmem to lmem */ > + src_mem_type = MEM_TYPE_LOCAL; > + dst_mem_type = MEM_TYPE_LOCAL; > + src_compression = enable_compression ? (COMPRESSION_ENABLE | AUX_CCS_E) : 0; > + dst_compression = enable_compression ? (COMPRESSION_ENABLE | AUX_CCS_E) : 0; > + resolve = (src == dst) ? FULL_RESOLVE : NO_RESOLVE; > + break; > + } > + > + /* BG 0 */ > + b[0] = BLOCK_COPY_BLT_CMD | (resolve << 12); > + > + /* BG 1 > + * > + * Using Tile 4 dimensions. Height = 32 rows > + * Width = 128 bytes > + */ > + b[1] = dst_compression | TILE_4_FORMAT | TILE_4_WIDTH_DWORD | > + dst_mocs << XY_BLOCK_COPY_BLT_MOCS_SHIFT; > + > + /* BG 3 > + * > + * X2 = TILE_4_WIDTH > + * Y2 = (length / TILE_4_WIDTH) << 16: > + */ > + b[3] = TILE_4_WIDTH | (length >> 7) << DEST_Y2_COORDINATE_SHIFT; > + > + b[4] = offset_dst; > + b[5] = offset_dst >> 32; > + > + /* relocate address in b[4] and b[5] */ > + reloc->offset = 4 * (sizeof(uint32_t)); > + reloc->delta = 0; > + reloc->target_handle = dst; > + reloc->read_domains = I915_GEM_DOMAIN_RENDER; > + reloc->write_domain = I915_GEM_DOMAIN_RENDER; > + reloc->presumed_offset = 0; > + reloc++; > + > + /* BG 6 */ > + b[6] = dst_mem_type << DEST_MEM_TYPE_SHIFT; > + > + /* BG 8 */ > + b[8] = src_compression | TILE_4_WIDTH_DWORD | TILE_4_FORMAT | > + src_mocs << XY_BLOCK_COPY_BLT_MOCS_SHIFT; > + > + b[9] = offset_src; > + b[10] = offset_src >> 32; > + > + /* relocate address in b[9] and b[10] */ > + reloc->offset = 9 * sizeof(uint32_t); > + reloc->delta = 0; > + reloc->target_handle = src; > + reloc->read_domains = I915_GEM_DOMAIN_RENDER; > + reloc->write_domain = 0; > + reloc->presumed_offset = 0; > + reloc++; > + > + /* BG 11 */ > + b[11] = src_mem_type << SRC_MEM_TYPE_SHIFT; > + > + /* BG 16 */ > + b[16] = SURFACE_TYPE_2D | > + ((TILE_4_WIDTH - 1) << DEST_SURF_WIDTH_SHIFT) | > + (TILE_4_HEIGHT - 1); > + > + /* BG 19 */ > + b[19] = SURFACE_TYPE_2D | > + ((TILE_4_WIDTH - 1) << SRC_SURF_WIDTH_SHIFT) | > + (TILE_4_HEIGHT - 1); > + > + b += XY_BLOCK_COPY_BLT_LEN_DWORD; > + > + b[0] = MI_FLUSH_DW | MI_FLUSH_LLC | MI_INVALIDATE_TLB; > + reloc->offset = 23 * sizeof(uint32_t); > + reloc->delta = 0; > + reloc->target_handle = dst_compression > 0 ? dst : src; > + reloc->read_domains = 0; > + reloc->write_domain = 0; > + reloc->presumed_offset = 0; > + reloc++; > + b[3] = 0; > + > + b[4] = MI_FLUSH_DW | MI_FLUSH_CCS; > + reloc->offset = 27 * sizeof(uint32_t); > + reloc->delta = 0; > + reloc->target_handle = dst_compression > 0 ? dst : src; > + reloc->read_domains = 0; > + reloc->write_domain = 0; > + reloc->presumed_offset = 0; > + reloc++; > + b[7] = 0; > + > + b[8] = MI_BATCH_BUFFER_END; > + b[9] = 0; > + > + b += 10; > + > + return (b - batch_buf) * sizeof(uint32_t); > +} > + > +void xy_block_copy_blt(int fd, uint32_t bb_region, uint32_t src, uint32_t dst, > + uint64_t src_size, uint64_t dst_size, uint64_t ahnd, > + uint32_t length, enum copy_mode mode, bool enable_compression, > + uint32_t ctx, struct intel_execution_engine2 *e) Why are only the static functions here documented, and not the actually exported lib functions? This one especially needs to document that the fd is expected to be for a device of at least gen12, since it unconditionally calls make_block_copy_batch. -- Petri Latvala > +{ > + struct drm_i915_gem_relocation_entry reloc[4]; > + struct drm_i915_gem_exec_object2 exec[3]; > + struct drm_i915_gem_execbuffer2 execbuf; > + int len; > + uint32_t cmd, batch_buf[BATCH_SIZE / sizeof(uint32_t)] = {}; > + uint64_t offset_src, offset_dst, offset_bb, bb_size, ret; > + > + bb_size = BATCH_SIZE; > + ret = __gem_create_in_memory_regions(fd, &cmd, &bb_size, bb_region); > + igt_assert_eq(ret, 0); > + > + offset_src = get_offset(ahnd, src, src_size, 0); > + offset_dst = get_offset(ahnd, dst, dst_size, 0); > + offset_bb = get_offset(ahnd, cmd, bb_size, 0); > + > + /* construct the batch buffer */ > + memset(reloc, 0, sizeof(reloc)); > + len = make_block_copy_batch(fd, batch_buf, src, dst, length, reloc, > + offset_src, offset_dst, mode, > + enable_compression); > + > + /* write batch buffer to 'cmd' BO */ > + gem_write(fd, cmd, 0, batch_buf, len); > + > + /* Execute the batch buffer */ > + memset(exec, 0, sizeof(exec)); > + exec[0].handle = src; > + exec[1].handle = dst; > + exec[2].handle = cmd; > + exec[2].relocation_count = !ahnd ? 4 : 0; > + exec[2].relocs_ptr = to_user_pointer(reloc); > + if (ahnd) { > + exec[0].offset = offset_src; > + exec[0].flags |= EXEC_OBJECT_PINNED | EXEC_OBJECT_SUPPORTS_48B_ADDRESS; > + exec[1].offset = offset_dst; > + exec[1].flags |= EXEC_OBJECT_PINNED | EXEC_OBJECT_WRITE | > + EXEC_OBJECT_SUPPORTS_48B_ADDRESS; > + exec[2].offset = offset_bb; > + exec[2].flags |= EXEC_OBJECT_PINNED | EXEC_OBJECT_SUPPORTS_48B_ADDRESS; > + } > + > + memset(&execbuf, 0, sizeof(execbuf)); > + execbuf.buffers_ptr = to_user_pointer(exec); > + execbuf.buffer_count = 3; > + execbuf.batch_len = len; > + execbuf.flags = e ? e->flags : I915_EXEC_BLT; > + if (ctx) > + execbuf.rsvd1 = ctx; > + > + gem_execbuf(fd, &execbuf); > + gem_close(fd, cmd); > + put_offset(ahnd, src); > + put_offset(ahnd, dst); > + put_offset(ahnd, cmd); > +} > + > +/* > + * make_ctrl_surf_batch: > + * @fd: open i915 drm file descriptor > + * @batch_buf: the batch buffer to populate with the command > + * @src: handle of the source BO > + * @dst: handle of the destination BO > + * @length: size of the ctrl surf in bytes > + * @reloc: pointer to the relocation entyr for this command > + * @offset_src: source address offset > + * @offset_dst: destination address offset > + * @writetodev: flag to enable direct access of the address > + * @return: length of batch buffer created > + */ > +static int make_ctrl_surf_batch(int fd, uint32_t *batch_buf, > + uint32_t src, uint32_t dst, uint32_t length, > + struct drm_i915_gem_relocation_entry *reloc, > + uint64_t offset_src, uint64_t offset_dst, > + bool writetodev) > +{ > + int num_ccs_blocks, src_mem_access, dst_mem_access; > + uint32_t *b = batch_buf; > + uint8_t src_mocs = intel_get_uc_mocs(fd); > + uint8_t dst_mocs = src_mocs; > + > + num_ccs_blocks = length / CCS_RATIO; > + if (num_ccs_blocks < 1) > + num_ccs_blocks = 1; > + if (num_ccs_blocks > NUM_CCS_BLKS_PER_XFER) > + return 0; > + > + if (writetodev) { > + src_mem_access = DIRECT_ACCESS; > + dst_mem_access = INDIRECT_ACCESS; > + } else { > + src_mem_access = INDIRECT_ACCESS; > + dst_mem_access = DIRECT_ACCESS; > + } > + > + /* > + * We use logical AND with 1023 since the size field > + * takes values which is in the range of 0 - 1023 > + */ > + b[0] = ((XY_CTRL_SURF_COPY_BLT) | > + (src_mem_access << SRC_ACCESS_TYPE_SHIFT) | > + (dst_mem_access << DST_ACCESS_TYPE_SHIFT) | > + (((num_ccs_blocks - 1) & 1023) << CCS_SIZE_SHIFT)); > + > + b[1] = offset_src; > + b[2] = offset_src >> 32 | src_mocs << XY_CTRL_SURF_COPY_BLT_MOCS_SHIFT; > + > + /* relocate address in b[1] and b[2] */ > + reloc->offset = 1 * sizeof(uint32_t); > + reloc->delta = 0; > + reloc->target_handle = src; > + reloc->read_domains = I915_GEM_DOMAIN_RENDER; > + reloc->write_domain = 0; > + reloc->presumed_offset = 0; > + reloc++; > + > + b[3] = offset_dst; > + b[4] = offset_dst >> 32 | dst_mocs << XY_CTRL_SURF_COPY_BLT_MOCS_SHIFT; > + > + /* relocate address in b[3] and b[4] */ > + reloc->offset = 3 * (sizeof(uint32_t)); > + reloc->delta = 0; > + reloc->target_handle = dst; > + reloc->read_domains = I915_GEM_DOMAIN_RENDER; > + reloc->write_domain = I915_GEM_DOMAIN_RENDER; > + reloc->presumed_offset = 0; > + reloc++; > + > + b[5] = 0; > + > + b[6] = MI_FLUSH_DW | MI_FLUSH_LLC | MI_INVALIDATE_TLB; > + > + reloc->offset = 7 * sizeof(uint32_t); > + reloc->delta = 0; > + reloc->target_handle = > + dst_mem_access == INDIRECT_ACCESS ? dst : src; > + reloc->read_domains = 0; > + reloc->write_domain = 0; > + reloc->presumed_offset = 0; > + reloc++; > + b[9] = 0; > + > + b[10] = MI_FLUSH_DW | MI_FLUSH_CCS; > + reloc->offset = 11 * sizeof(uint32_t); > + reloc->delta = 0; > + reloc->target_handle = > + dst_mem_access == INDIRECT_ACCESS ? dst : src; > + reloc->read_domains = 0; > + reloc->write_domain = 0; > + reloc->presumed_offset = 0; > + reloc++; > + b[13] = 0; > + > + b[14] = MI_BATCH_BUFFER_END; > + b[15] = 0; > + > + b += 16; > + > + return (b - batch_buf) * sizeof(uint32_t); > +} > + > +void xy_ctrl_surf_copy_blt(int fd, uint32_t bb_region, uint32_t src, > + uint32_t dst, uint64_t src_size, uint64_t dst_size, > + uint64_t ahnd, uint32_t length, bool writetodev, > + uint32_t ctx, struct intel_execution_engine2 *e) > +{ > + struct drm_i915_gem_relocation_entry reloc[4]; > + struct drm_i915_gem_exec_object2 exec[3]; > + struct drm_i915_gem_execbuffer2 execbuf; > + int len; > + uint32_t cmd, batch_buf[BATCH_SIZE / sizeof(uint32_t)] = {}; > + uint64_t offset_src, offset_dst, offset_bb, bb_size, ret; > + > + bb_size = BATCH_SIZE; > + ret = __gem_create_in_memory_regions(fd, &cmd, &bb_size, bb_region); > + igt_assert_eq(ret, 0); > + > + offset_src = get_offset(ahnd, src, src_size, 0); > + offset_dst = get_offset(ahnd, dst, dst_size, 0); > + offset_bb = get_offset(ahnd, cmd, bb_size, 0); > + > + /* construct batch command buffer */ > + memset(reloc, 0, sizeof(reloc)); > + len = make_ctrl_surf_batch(fd, batch_buf, src, dst, length, reloc, > + offset_src, offset_dst, writetodev); > + > + /* Copy the batch buff to BO cmd */ > + gem_write(fd, cmd, 0, batch_buf, len); > + > + /* Execute the batch buffer */ > + memset(exec, 0, sizeof(exec)); > + exec[0].handle = src; > + exec[1].handle = dst; > + exec[2].handle = cmd; > + exec[2].relocation_count = !ahnd ? 4 : 0; > + exec[2].relocs_ptr = to_user_pointer(reloc); > + if (ahnd) { > + exec[0].offset = offset_src; > + exec[0].flags |= EXEC_OBJECT_PINNED | EXEC_OBJECT_SUPPORTS_48B_ADDRESS; > + exec[1].offset = offset_dst; > + exec[1].flags |= EXEC_OBJECT_PINNED | EXEC_OBJECT_WRITE | > + EXEC_OBJECT_SUPPORTS_48B_ADDRESS; > + exec[2].offset = offset_bb; > + exec[2].flags |= EXEC_OBJECT_PINNED | EXEC_OBJECT_SUPPORTS_48B_ADDRESS; > + } > + > + memset(&execbuf, 0, sizeof(execbuf)); > + execbuf.buffers_ptr = to_user_pointer(exec); > + execbuf.buffer_count = 3; > + execbuf.batch_len = len; > + execbuf.flags = e ? e->flags : I915_EXEC_BLT; > + if (ctx) > + execbuf.rsvd1 = ctx; > + > + gem_execbuf(fd, &execbuf); > + gem_close(fd, cmd); > + put_offset(ahnd, src); > + put_offset(ahnd, dst); > + put_offset(ahnd, cmd); > +} > diff --git a/lib/i915/i915_blt.h b/lib/i915/i915_blt.h > new file mode 100644 > index 00000000..ff3eee7f > --- /dev/null > +++ b/lib/i915/i915_blt.h > @@ -0,0 +1,72 @@ > +/* SPDX-License-Identifier: MIT */ > +/* > + * Copyright © 2021 Intel Corporation > + */ > + > +#include <errno.h> > +#include <sys/ioctl.h> > +#include <sys/time.h> > +#include <malloc.h> > +#include "drm.h" > +#include "igt.h" > + > +#define MI_FLUSH_DW_LEN_DWORD 4 > +#define MI_FLUSH_DW (0x26 << 23 | 1) > +#define MI_FLUSH_CCS BIT(16) > +#define MI_FLUSH_LLC BIT(9) > +#define MI_INVALIDATE_TLB BIT(18) > + > +/* XY_BLOCK_COPY_BLT instruction has 22 bit groups 1 DWORD each */ > +#define XY_BLOCK_COPY_BLT_LEN_DWORD 22 > +#define BLOCK_COPY_BLT_CMD (2 << 29 | 0x41 << 22 | 0x14) > +#define COMPRESSION_ENABLE BIT(29) > +#define AUX_CCS_E (5 << 18) > +#define NO_RESOLVE 0 > +#define FULL_RESOLVE 1 > +#define PARTIAL_RESOLVE 2 > +#define TILE_4_FORMAT (2 << 30) > +#define TILE_4_WIDTH (128) > +#define TILE_4_WIDTH_DWORD ((128 >> 2) - 1) > +#define TILE_4_HEIGHT (32) > +#define SURFACE_TYPE_2D BIT(29) > + > +#define DEST_Y2_COORDINATE_SHIFT (16) > +#define DEST_MEM_TYPE_SHIFT (31) > +#define SRC_MEM_TYPE_SHIFT (31) > +#define DEST_SURF_WIDTH_SHIFT (14) > +#define SRC_SURF_WIDTH_SHIFT (14) > + > +#define XY_CTRL_SURF_COPY_BLT (2 << 29 | 0x48 << 22 | 3) > +#define SRC_ACCESS_TYPE_SHIFT 21 > +#define DST_ACCESS_TYPE_SHIFT 20 > +#define CCS_SIZE_SHIFT 8 > +#define MI_INSTR(opcode, flags) (((opcode) << 23) | (flags)) > +#define MI_ARB_CHECK MI_INSTR(0x05, 0) > +#define NUM_CCS_BLKS_PER_XFER 1024 > +#define INDIRECT_ACCESS 0 > +#define DIRECT_ACCESS 1 > + > +#define BATCH_SIZE 4096 > +#define BOSIZE_MIN (4 * 1024) > +#define BOSIZE_MAX (4 * 1024 * 1024) > +#define CCS_RATIO 256 > + > +#define MEM_TYPE_SYS 1 > +#define MEM_TYPE_LOCAL 0 > + > +enum copy_mode { > + SYS_TO_SYS = 0, > + SYS_TO_LOCAL, > + LOCAL_TO_SYS, > + LOCAL_TO_LOCAL, > +}; > + > +void xy_block_copy_blt(int fd, uint32_t bb_region, uint32_t src, uint32_t dst, > + uint64_t src_size, uint64_t dst_size, uint64_t ahnd, > + uint32_t length, enum copy_mode mode, bool enable_compression, > + uint32_t ctx, struct intel_execution_engine2 *e); > + > +void xy_ctrl_surf_copy_blt(int fd, uint32_t bb_region, uint32_t src, uint32_t dst, > + uint64_t src_size, uint64_t dst_size, uint64_t ahnd, > + uint32_t length, bool writetodev, uint32_t ctx, > + struct intel_execution_engine2 *e); > diff --git a/lib/meson.build b/lib/meson.build > index f500f0f1..f2924541 100644 > --- a/lib/meson.build > +++ b/lib/meson.build > @@ -12,6 +12,7 @@ lib_sources = [ > 'i915/gem_vm.c', > 'i915/intel_memory_region.c', > 'i915/intel_mocs.c', > + 'i915/i915_blt.c', > 'igt_collection.c', > 'igt_color_encoding.c', > 'igt_debugfs.c', > -- > 2.25.1 > ^ permalink raw reply [flat|nested] 11+ messages in thread
* [igt-dev] [PATCH i-g-t, v5 3/5] lib/intel_chipset.h: Add has_flat_ccs flag 2021-12-19 13:14 [igt-dev] [PATCH i-g-t,v5 0/5] Add testing for CCS apoorva1.singh 2021-12-19 13:14 ` [igt-dev] [PATCH i-g-t, v5 1/5] lib/i915: Introduce library intel_mocs apoorva1.singh 2021-12-19 13:14 ` [igt-dev] [PATCH i-g-t, v5 2/5] lib/i915: Introduce library i915_blt apoorva1.singh @ 2021-12-19 13:14 ` apoorva1.singh 2021-12-19 13:14 ` [igt-dev] [PATCH i-g-t, v5 4/5] i915/gem_engine_topology: Only use the main copy engines for XY_BLOCK_COPY apoorva1.singh ` (3 subsequent siblings) 6 siblings, 0 replies; 11+ messages in thread From: apoorva1.singh @ 2021-12-19 13:14 UTC (permalink / raw) To: apoorva1.singh, igt-dev, ramalingam.c, zbigniew.kempczynski, arjun.melkaveri From: Apoorva Singh <apoorva1.singh@intel.com> Add a new platform flag, has_flat_ccs, for platforms supporting Flat CCS. Signed-off-by: Apoorva Singh <apoorva1.singh@intel.com> Cc: Zbigniew Kempczyński <zbigniew.kempczynski@intel.com> Cc: Melkaveri, Arjun <arjun.melkaveri@intel.com> Acked-by: Zbigniew Kempczyński <zbigniew.kempczynski@intel.com> --- lib/intel_chipset.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/lib/intel_chipset.h b/lib/intel_chipset.h index 2b795527..d2719932 100644 --- a/lib/intel_chipset.h +++ b/lib/intel_chipset.h @@ -40,6 +40,7 @@ struct intel_device_info { unsigned graphics_ver; unsigned display_ver; unsigned gt; /* 0 if unknown */ + bool has_flat_ccs : 1; bool is_mobile : 1; bool is_whitney : 1; bool is_almador : 1; @@ -209,4 +210,6 @@ void intel_check_pch(void); IS_CHERRYVIEW(devid) || \ IS_BROXTON(devid))) +#define HAS_FLAT_CCS(devid) (intel_get_device_info(devid)->has_flat_ccs) + #endif /* _INTEL_CHIPSET_H */ -- 2.25.1 ^ permalink raw reply related [flat|nested] 11+ messages in thread
* [igt-dev] [PATCH i-g-t, v5 4/5] i915/gem_engine_topology: Only use the main copy engines for XY_BLOCK_COPY 2021-12-19 13:14 [igt-dev] [PATCH i-g-t,v5 0/5] Add testing for CCS apoorva1.singh ` (2 preceding siblings ...) 2021-12-19 13:14 ` [igt-dev] [PATCH i-g-t, v5 3/5] lib/intel_chipset.h: Add has_flat_ccs flag apoorva1.singh @ 2021-12-19 13:14 ` apoorva1.singh 2021-12-19 13:14 ` [igt-dev] [PATCH i-g-t,v5 5/5] i915/gem_ccs: Add testing for CCS apoorva1.singh ` (2 subsequent siblings) 6 siblings, 0 replies; 11+ messages in thread From: apoorva1.singh @ 2021-12-19 13:14 UTC (permalink / raw) To: apoorva1.singh, igt-dev, ramalingam.c, zbigniew.kempczynski, arjun.melkaveri From: Chris Wilson <chris.p.wilson@intel.com> XY_BLOCK_COPY blt command is used to transfer the ccs data. So, we can only run the tests on those engines which have support for the "block_copy" capability. Signed-off-by: Chris Wilson <chris.p.wilson@intel.com> Signed-off-by: Apoorva Singh <apoorva1.singh@intel.com> Cc: Zbigniew Kempczyński <zbigniew.kempczynski@intel.com> Cc: Melkaveri, Arjun <arjun.melkaveri@intel.com> --- lib/i915/gem_engine_topology.c | 38 ++++++++++++++++++++++++++++++++++ lib/i915/gem_engine_topology.h | 5 +++++ 2 files changed, 43 insertions(+) diff --git a/lib/i915/gem_engine_topology.c b/lib/i915/gem_engine_topology.c index 729f42b0..37b5875e 100644 --- a/lib/i915/gem_engine_topology.c +++ b/lib/i915/gem_engine_topology.c @@ -488,6 +488,44 @@ int gem_engine_property_printf(int i915, const char *engine, const char *attr, return ret; } +static bool +__gem_engine_has_capability(int i915, const char *engine, + const char *attr, const char *cap) +{ + char buf[4096] = {}; + FILE *file; + + file = __open_attr(igt_sysfs_open(i915), "r", + "engine", engine, attr, NULL); + if (file) { + fread(buf, 1, sizeof(buf) - 1, file); + fclose(file); + } + + return strstr(buf, cap); +} + +bool gem_engine_has_capability(int i915, const char *engine, const char *cap) +{ + return __gem_engine_has_capability(i915, engine, "capabilities", cap); +} + +bool gem_engine_has_known_capability(int i915, const char *engine, const char *cap) +{ + return __gem_engine_has_capability(i915, engine, "known_capabilities", cap); +} + +bool gem_engine_can_block_copy(int i915, const struct intel_execution_engine2 *engine) +{ + if (engine->class != I915_ENGINE_CLASS_COPY) + return false; + + if (!gem_engine_has_known_capability(i915, engine->name, "block_copy")) + return intel_gen(intel_get_drm_devid(i915)) >= 12; + + return gem_engine_has_capability(i915, engine->name, "block_copy"); +} + uint32_t gem_engine_mmio_base(int i915, const char *engine) { unsigned int mmio = 0; diff --git a/lib/i915/gem_engine_topology.h b/lib/i915/gem_engine_topology.h index 4cfab560..d24bc9e8 100644 --- a/lib/i915/gem_engine_topology.h +++ b/lib/i915/gem_engine_topology.h @@ -124,6 +124,11 @@ int gem_engine_property_printf(int i915, const char *engine, const char *attr, uint32_t gem_engine_mmio_base(int i915, const char *engine); +bool gem_engine_has_capability(int i915, const char *engine, const char *cap); +bool gem_engine_has_known_capability(int i915, const char *engine, const char *cap); + +bool gem_engine_can_block_copy(int i915, const struct intel_execution_engine2 *engine); + void dyn_sysfs_engines(int i915, int engines, const char *file, void (*test)(int i915, int engine)); -- 2.25.1 ^ permalink raw reply related [flat|nested] 11+ messages in thread
* [igt-dev] [PATCH i-g-t,v5 5/5] i915/gem_ccs: Add testing for CCS 2021-12-19 13:14 [igt-dev] [PATCH i-g-t,v5 0/5] Add testing for CCS apoorva1.singh ` (3 preceding siblings ...) 2021-12-19 13:14 ` [igt-dev] [PATCH i-g-t, v5 4/5] i915/gem_engine_topology: Only use the main copy engines for XY_BLOCK_COPY apoorva1.singh @ 2021-12-19 13:14 ` apoorva1.singh 2021-12-19 13:51 ` [igt-dev] ✓ Fi.CI.BAT: success for Add testing for CCS (rev5) Patchwork 2021-12-19 14:56 ` [igt-dev] ✓ Fi.CI.IGT: " Patchwork 6 siblings, 0 replies; 11+ messages in thread From: apoorva1.singh @ 2021-12-19 13:14 UTC (permalink / raw) To: apoorva1.singh, igt-dev, ramalingam.c, zbigniew.kempczynski, arjun.melkaveri From: CQ Tang <cq.tang@intel.com> Add gem_ccs test for CCS testing. Commands are constructed with XY_BLOCK_COPY_BLT and XY_CTRL_SURF_COPY_BLT instructions. Signed-off-by: CQ Tang <cq.tang@intel.com> Signed-off-by: Apoorva Singh <apoorva1.singh@intel.com> Cc: Zbigniew Kempczyński <zbigniew.kempczynski@intel.com> Cc: Melkaveri, Arjun <arjun.melkaveri@intel.com> --- tests/i915/gem_ccs.c | 413 +++++++++++++++++++++++++++++++++++++++++++ tests/meson.build | 1 + 2 files changed, 414 insertions(+) create mode 100644 tests/i915/gem_ccs.c diff --git a/tests/i915/gem_ccs.c b/tests/i915/gem_ccs.c new file mode 100644 index 00000000..2e2b6e3b --- /dev/null +++ b/tests/i915/gem_ccs.c @@ -0,0 +1,413 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2021 Intel Corporation + */ + +#include <errno.h> +#include <sys/ioctl.h> +#include <sys/time.h> +#include <malloc.h> +#include "drm.h" +#include "igt.h" +#include "i915/gem.h" +#include "i915/gem_create.h" +#include "lib/intel_chipset.h" +#include "i915/i915_blt.h" + +IGT_TEST_DESCRIPTION("Exercise the memory bandwidth compression and " + "decompression when copying data between " + "system and local memory"); + +static void igt_wr_xy_ctrl_surf_copy_blt(int fd, uint32_t region, uint32_t src, uint32_t dst, + uint32_t out, uint64_t src_size, uint64_t dst_size, + uint64_t out_size, uint64_t ahnd, int ccssize, + uint8_t *pattern_buf, uint8_t *read_buf, int bosize, + struct intel_execution_engine2 *e) +{ + gem_write(fd, src, 0, pattern_buf, bosize); + + /* + * 'dst' is lmem BO with ccs, directly + * copy content in 'src' BO to 'dst' BO's ccs + */ + xy_ctrl_surf_copy_blt(fd, region, src, dst, src_size, dst_size, + ahnd, ccssize, true, 0, e); + + memset(read_buf, 0, ccssize); + gem_write(fd, out, 0, read_buf, ccssize); + + /* copy 'dst' BO's ccs into 'out' BO */ + xy_ctrl_surf_copy_blt(fd, region, dst, out, dst_size, out_size, + ahnd, ccssize, false, 0, e); + + gem_read(fd, out, 0, read_buf, ccssize); + + igt_assert_eq(memcmp(read_buf, pattern_buf, ccssize), 0); +} + +static void igt_overwritten_xy_block_copy_blt(int fd, uint32_t region, uint32_t src, uint32_t dst, + uint32_t out, uint64_t src_size, uint64_t dst_size, + uint64_t out_size, uint64_t ahnd, int ccssize, + uint8_t *pattern_buf, uint8_t *read_buf, int bosize, + struct intel_execution_engine2 *e) +{ + bool enable_compression = true; + + igt_info("copy random pattern to lmem BO with compression\n"); + + gem_write(fd, src, 0, pattern_buf, bosize); + gem_write(fd, dst, 0, pattern_buf, bosize); + + /* + * 'dst' is lmem BO with ccs, + * copy content in 'src' BO to 'dst' BO + */ + xy_block_copy_blt(fd, region, src, dst, src_size, dst_size, ahnd, + bosize, SYS_TO_LOCAL, enable_compression, 0, e); + + memset(read_buf, 0, ccssize); + gem_write(fd, out, 0, read_buf, ccssize); + + /* copy 'dst' BO's ccs into 'out' BO */ + xy_ctrl_surf_copy_blt(fd, region, dst, out, dst_size, out_size, + ahnd, ccssize, false, 0, e); + + gem_read(fd, out, 0, read_buf, ccssize); + + igt_assert_neq(memcmp(read_buf, pattern_buf, ccssize), 0); + + memset(read_buf, 0, bosize); + gem_read(fd, dst, 0, read_buf, bosize); + + igt_assert_neq(memcmp(read_buf, pattern_buf, bosize), 0); + + memset(read_buf, 0, bosize); + gem_write(fd, out, 0, read_buf, bosize); + + /* copy 'dst' BO into 'out' BO */ + xy_block_copy_blt(fd, region, dst, out, dst_size, out_size, ahnd, + bosize, LOCAL_TO_SYS, enable_compression, 0, e); + + gem_read(fd, out, 0, read_buf, bosize); + + igt_assert_eq(memcmp(read_buf, pattern_buf, bosize), 0); + + /* decompress 'dst' in place */ + xy_block_copy_blt(fd, region, dst, dst, dst_size, dst_size, ahnd, + bosize, LOCAL_TO_LOCAL, enable_compression, 0, e); + + memset(read_buf, 0, bosize); + gem_read(fd, dst, 0, read_buf, bosize); + + igt_assert_eq(memcmp(read_buf, pattern_buf, bosize), 0); + + memset(read_buf, 0, bosize); + gem_write(fd, out, 0, read_buf, bosize); + + /* copy decompressed 'dst' to 'out' */ + xy_block_copy_blt(fd, region, dst, out, dst_size, out_size, ahnd, + bosize, LOCAL_TO_SYS, enable_compression, 0, e); + + gem_read(fd, out, 0, read_buf, bosize); + + igt_assert_eq(memcmp(read_buf, pattern_buf, bosize), 0); +} + +static void igt_corrupted_xy_ctrl_surf_copy_blt(int fd, uint32_t region, uint32_t src, uint32_t dst, + uint32_t out, uint64_t src_size, uint64_t dst_size, + uint64_t out_size, uint64_t ahnd, int ccssize, + uint8_t *pattern_buf, uint8_t *read_buf, int bosize, + struct intel_execution_engine2 *e) +{ + bool enable_compression = true; + + gem_write(fd, src, 0, pattern_buf, bosize); + + igt_info("corrupt CCS via XY_CTRL_SURF_COPY_BLT\n"); + + /* corrupt 'dst' BO's ccs by writing directly */ + xy_ctrl_surf_copy_blt(fd, region, src, dst, src_size, dst_size, + ahnd, ccssize, true, 0, e); + + memset(read_buf, 0, bosize); + gem_write(fd, out, 0, read_buf, bosize); + + /* copy 'dst' BO into 'out' BO */ + xy_block_copy_blt(fd, region, dst, out, dst_size, out_size, ahnd, + bosize, LOCAL_TO_SYS, enable_compression, 0, e); + + gem_read(fd, out, 0, read_buf, bosize); + + igt_assert_neq(memcmp(read_buf, pattern_buf, bosize), 0); + + memset(read_buf, 0, ccssize); + gem_write(fd, out, 0, read_buf, ccssize); + + /* copy 'dst' BO's ccs into 'out' BO */ + xy_ctrl_surf_copy_blt(fd, region, dst, out, dst_size, out_size, + ahnd, ccssize, false, 0, e); + + gem_read(fd, out, 0, read_buf, ccssize); + + igt_assert_eq(memcmp(read_buf, pattern_buf, ccssize), 0); +} + +static void igt_copy_zero_pattern_xy_block_copy_blt(int fd, uint32_t region, uint32_t src, + uint32_t dst, uint32_t out, uint64_t src_size, + uint64_t dst_size, uint64_t out_size, + uint64_t ahnd, int ccssize, + uint8_t *pattern_buf, uint8_t *read_buf, + uint8_t *input_buf, int bosize, + struct intel_execution_engine2 *e) +{ + bool enable_compression = true; + + igt_info("copy zeros pattern to lmem BO with compression\n"); + + gem_write(fd, src, 0, pattern_buf, bosize); + gem_write(fd, dst, 0, pattern_buf, bosize); + /* set ccs to random pattern */ + xy_ctrl_surf_copy_blt(fd, region, src, dst, src_size, dst_size, + ahnd, ccssize, true, 0, e); + + memset(input_buf, 0, bosize); + gem_write(fd, src, 0, input_buf, bosize); + + /* copy 'src' to 'dst' with compression */ + xy_block_copy_blt(fd, region, src, dst, src_size, dst_size, ahnd, + bosize, SYS_TO_LOCAL, enable_compression, 0, e); + + gem_write(fd, out, 0, pattern_buf, bosize); + + /* copy 'dst' BO back into 'out' BO */ + xy_block_copy_blt(fd, region, dst, out, dst_size, out_size, ahnd, + bosize, LOCAL_TO_SYS, enable_compression, 0, e); + + gem_read(fd, out, 0, read_buf, bosize); + + igt_assert_eq(memcmp(read_buf, input_buf, bosize), 0); + + memset(read_buf, 0, bosize); + gem_read(fd, dst, 0, read_buf, bosize); + + igt_assert_eq(memcmp(read_buf, pattern_buf, bosize), 0); + + memset(read_buf, 0, ccssize); + gem_write(fd, out, 0, read_buf, ccssize); + + /* copy 'dst' BO's ccs into 'out' BO */ + xy_ctrl_surf_copy_blt(fd, region, dst, out, dst_size, out_size, + ahnd, ccssize, false, 0, e); + + gem_read(fd, out, 0, read_buf, ccssize); + + igt_assert_neq(memcmp(read_buf, pattern_buf, ccssize), 0); +} + +static void igt_copy_repeat_pattern_xy_block_copy_blt(int fd, uint32_t region, uint32_t src, + uint32_t dst, uint32_t out, uint64_t src_size, + uint64_t dst_size, uint64_t out_size, + uint64_t ahnd, int ccssize, + uint8_t *pattern_buf, uint8_t *read_buf, + uint8_t *input_buf, int bosize, + struct intel_execution_engine2 *e) +{ + int i; + bool enable_compression = true; + + igt_info("copy repeat pattern to lmem BO with compression\n"); + + gem_write(fd, src, 0, pattern_buf, bosize); + gem_write(fd, src, 0, pattern_buf, ccssize); + + xy_ctrl_surf_copy_blt(fd, region, src, dst, src_size, dst_size, + ahnd, ccssize, true, 0, e); + gem_write(fd, dst, 0, pattern_buf, bosize); + + /* generate repeating pattern */ + input_buf[0] = (uint8_t)rand(); + input_buf[1] = (uint8_t)rand(); + input_buf[2] = (uint8_t)rand(); + input_buf[3] = (uint8_t)rand(); + for (i = 4; i < bosize; i++) + input_buf[i] = input_buf[i - 4]; + gem_write(fd, src, 0, input_buf, bosize); + + xy_block_copy_blt(fd, region, src, dst, src_size, dst_size, ahnd, + bosize, SYS_TO_LOCAL, enable_compression, 0, e); + + memset(read_buf, 0, bosize); + gem_write(fd, out, 0, read_buf, bosize); + + /* copy 'dst' BO back into 'out' BO */ + xy_block_copy_blt(fd, region, dst, out, dst_size, out_size, ahnd, + bosize, LOCAL_TO_SYS, enable_compression, 0, e); + + gem_read(fd, out, 0, read_buf, bosize); + + igt_assert_eq(memcmp(read_buf, input_buf, bosize), 0); + + memset(read_buf, 0, bosize); + gem_read(fd, dst, 0, read_buf, bosize); + + igt_assert_neq(memcmp(read_buf, pattern_buf, bosize), 0); + + memset(read_buf, 0, ccssize); + gem_write(fd, out, 0, read_buf, ccssize); + + /* copy 'dst' BO's ccs into 'out' BO */ + xy_ctrl_surf_copy_blt(fd, region, dst, out, dst_size, out_size, + ahnd, ccssize, false, 0, e); + + gem_read(fd, out, 0, read_buf, ccssize); + + igt_assert_neq(memcmp(read_buf, pattern_buf, ccssize), 0); +} + +/* + * Allocate a BO in SMEM. + * Fill a pattern + * Use XY_BLOCK_COPY_BLT to copy it to LMEM with compression enabled + * Clear the BO in SMEM, and the pattern_buf in which the pattern was + * stored + * Use XY_BLOCK_COPY_BLT to copy it back to the BO in SMEM with + * resolve + * Compare the value in the BO in SMEM matches the pattern + */ +static void test_ccs(int fd, int size, uint32_t region, char *sub_name, + struct intel_execution_engine2 *e) +{ + int bosize, ccssize, ret, i; + int start, end; + uint32_t src, dst, out; + uint8_t *pattern_buf, *input_buf, *read_buf; + uint64_t ahnd, src_size, dst_size, out_size; + struct timeval tv; + + ahnd = get_reloc_ahnd(fd, 0); + + if (size > 0) { + start = size; + end = start + 1; + } else { + start = BOSIZE_MIN; + end = BOSIZE_MAX; + } + + for (bosize = start; bosize < end; bosize *= 2) { + /* allocate working buffers */ + pattern_buf = malloc(bosize); + igt_assert(pattern_buf); + input_buf = malloc(bosize); + igt_assert(input_buf); + read_buf = malloc(bosize); + igt_assert(read_buf); + + ccssize = bosize / CCS_RATIO; + src_size = dst_size = out_size = bosize; + + /* allocate working BOs in the right location */ + ret = __gem_create_in_memory_regions(fd, &src, &src_size, + INTEL_MEMORY_REGION_ID(I915_SYSTEM_MEMORY, 0)); + igt_assert_eq(ret, 0); + + ret = __gem_create_in_memory_regions(fd, &dst, &dst_size, region); + igt_assert_eq(ret, 0); + + ret = __gem_create_in_memory_regions(fd, &out, &out_size, + INTEL_MEMORY_REGION_ID(I915_SYSTEM_MEMORY, 0)); + igt_assert_eq(ret, 0); + + /* fill in random pattern */ + ret = gettimeofday(&tv, NULL); + igt_assert(!ret); + srandom((int)tv.tv_usec); + + for (i = 0; i < bosize; i++) + pattern_buf[i] = (uint8_t)rand(); + + igt_info("progress: bosize %d, ccssize %d\n", bosize, ccssize); + + igt_dynamic_f("write_read_in_ccs_surface-%s-%s", sub_name, e->name) + igt_wr_xy_ctrl_surf_copy_blt(fd, region, src, dst, out, src_size, dst_size, + out_size, ahnd, ccssize, pattern_buf, read_buf, + bosize, e); + igt_dynamic_f("verify_compression_of_random_data-%s-%s", sub_name, e->name) + igt_overwritten_xy_block_copy_blt(fd, region, src, dst, out, src_size, + dst_size, out_size, ahnd, ccssize, + pattern_buf, read_buf, bosize, e); + igt_dynamic_f("verify_corrupted_pattern_in_ccs_surface-%s-%s", sub_name, e->name) + igt_corrupted_xy_ctrl_surf_copy_blt(fd, region, src, dst, out, src_size, + dst_size, out_size, ahnd, ccssize, + pattern_buf, read_buf, bosize, e); + igt_dynamic_f("copy_zero_pattern_with_compression-%s-%s", sub_name, e->name) + igt_copy_zero_pattern_xy_block_copy_blt(fd, region, src, dst, out, src_size, + dst_size, out_size, ahnd, ccssize, + pattern_buf, read_buf, input_buf, + bosize, e); + igt_dynamic_f("copy_repeat_pattern_with_compression-%s-%s", sub_name, e->name) + igt_copy_repeat_pattern_xy_block_copy_blt(fd, region, src, dst, out, + src_size, dst_size, out_size, + ahnd, ccssize, pattern_buf, + read_buf, input_buf, bosize, e); + + gem_close(fd, out); + gem_close(fd, dst); + gem_close(fd, src); + free(read_buf); + free(input_buf); + free(pattern_buf); + } + + put_ahnd(ahnd); +} + +static void subtest_ccs(int drm_fd, struct igt_collection *set, const char *subtest, int size) +{ + struct intel_execution_engine2 *e; + struct igt_collection *regions; + char *sub_name; + uint32_t region; + + igt_subtest_with_dynamic(subtest) { + for_each_physical_engine(drm_fd, e) { + if (!gem_engine_can_block_copy(drm_fd, e)) + continue; + + for_each_combination(regions, 1, set) { + sub_name = memregion_dynamic_subtest_name(regions); + region = igt_collection_get_value(regions, 0); + test_ccs(drm_fd, size, region, sub_name, e); + free(sub_name); + } + } + } +} + +igt_main +{ + struct drm_i915_query_memory_regions *query_info; + struct igt_collection *set; + int drm_fd; + + igt_fixture { + drm_fd = drm_open_driver(DRIVER_INTEL); + igt_require_gem(drm_fd); + igt_require(AT_LEAST_GEN(intel_get_drm_devid(drm_fd), 12) > 0); + igt_require(HAS_FLAT_CCS(intel_get_drm_devid(drm_fd))); + + query_info = gem_get_query_memory_regions(drm_fd); + igt_require(query_info); + + set = get_memory_region_set(query_info, I915_DEVICE_MEMORY); + } + + subtest_ccs(drm_fd, set, "basic-gem-ccs-4K", 4 * 1024); + subtest_ccs(drm_fd, set, "basic-gem-ccs-64K", 64 * 1024); + subtest_ccs(drm_fd, set, "basic-gem-ccs-1M", 1024 * 1024); + subtest_ccs(drm_fd, set, "basic-gem-ccs-all", 0); + + igt_fixture { + close(drm_fd); + } +} diff --git a/tests/meson.build b/tests/meson.build index c14acf99..e0b48d66 100644 --- a/tests/meson.build +++ b/tests/meson.build @@ -107,6 +107,7 @@ i915_progs = [ 'gem_blits', 'gem_busy', 'gem_caching', + 'gem_ccs', 'gem_close', 'gem_close_race', 'gem_concurrent_blit', -- 2.25.1 ^ permalink raw reply related [flat|nested] 11+ messages in thread
* [igt-dev] ✓ Fi.CI.BAT: success for Add testing for CCS (rev5) 2021-12-19 13:14 [igt-dev] [PATCH i-g-t,v5 0/5] Add testing for CCS apoorva1.singh ` (4 preceding siblings ...) 2021-12-19 13:14 ` [igt-dev] [PATCH i-g-t,v5 5/5] i915/gem_ccs: Add testing for CCS apoorva1.singh @ 2021-12-19 13:51 ` Patchwork 2021-12-19 14:56 ` [igt-dev] ✓ Fi.CI.IGT: " Patchwork 6 siblings, 0 replies; 11+ messages in thread From: Patchwork @ 2021-12-19 13:51 UTC (permalink / raw) To: apoorva1.singh; +Cc: igt-dev [-- Attachment #1: Type: text/plain, Size: 5692 bytes --] == Series Details == Series: Add testing for CCS (rev5) URL : https://patchwork.freedesktop.org/series/96648/ State : success == Summary == CI Bug Log - changes from CI_DRM_11014 -> IGTPW_6505 ==================================================== Summary ------- **SUCCESS** No regressions found. External URL: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/index.html Participating hosts (41 -> 36) ------------------------------ Additional (2): fi-bxt-dsi fi-bdw-5557u Missing (7): bat-dg1-6 bat-dg1-5 fi-bsw-cyan bat-adlp-6 bat-jsl-2 fi-bsw-nick fi-bdw-samus Known issues ------------ Here are the changes found in IGTPW_6505 that come from known issues: ### IGT changes ### #### Issues hit #### * igt@gem_exec_suspend@basic-s3: - fi-skl-6600u: [PASS][1] -> [INCOMPLETE][2] ([i915#4547]) [1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11014/fi-skl-6600u/igt@gem_exec_suspend@basic-s3.html [2]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/fi-skl-6600u/igt@gem_exec_suspend@basic-s3.html * igt@gem_huc_copy@huc-copy: - fi-bxt-dsi: NOTRUN -> [SKIP][3] ([fdo#109271] / [i915#2190]) [3]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/fi-bxt-dsi/igt@gem_huc_copy@huc-copy.html * igt@gem_lmem_swapping@verify-random: - fi-bxt-dsi: NOTRUN -> [SKIP][4] ([fdo#109271] / [i915#4613]) +3 similar issues [4]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/fi-bxt-dsi/igt@gem_lmem_swapping@verify-random.html * igt@i915_selftest@live@hangcheck: - fi-snb-2600: [PASS][5] -> [INCOMPLETE][6] ([i915#3921]) [5]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11014/fi-snb-2600/igt@i915_selftest@live@hangcheck.html [6]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/fi-snb-2600/igt@i915_selftest@live@hangcheck.html * igt@kms_chamelium@common-hpd-after-suspend: - fi-bxt-dsi: NOTRUN -> [SKIP][7] ([fdo#109271] / [fdo#111827]) +8 similar issues [7]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/fi-bxt-dsi/igt@kms_chamelium@common-hpd-after-suspend.html * igt@kms_force_connector_basic@force-load-detect: - fi-bxt-dsi: NOTRUN -> [SKIP][8] ([fdo#109271]) +30 similar issues [8]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/fi-bxt-dsi/igt@kms_force_connector_basic@force-load-detect.html * igt@kms_pipe_crc_basic@compare-crc-sanitycheck-pipe-d: - fi-bxt-dsi: NOTRUN -> [SKIP][9] ([fdo#109271] / [i915#533]) [9]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/fi-bxt-dsi/igt@kms_pipe_crc_basic@compare-crc-sanitycheck-pipe-d.html * igt@runner@aborted: - fi-skl-6600u: NOTRUN -> [FAIL][10] ([i915#4312]) [10]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/fi-skl-6600u/igt@runner@aborted.html - fi-bdw-5557u: NOTRUN -> [FAIL][11] ([i915#2426] / [i915#4312]) [11]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/fi-bdw-5557u/igt@runner@aborted.html #### Possible fixes #### * igt@i915_selftest@live@gem_contexts: - {fi-tgl-dsi}: [INCOMPLETE][12] ([i915#402]) -> [PASS][13] [12]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11014/fi-tgl-dsi/igt@i915_selftest@live@gem_contexts.html [13]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/fi-tgl-dsi/igt@i915_selftest@live@gem_contexts.html * igt@i915_selftest@live@hugepages: - {fi-tgl-dsi}: [INCOMPLETE][14] -> [PASS][15] [14]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11014/fi-tgl-dsi/igt@i915_selftest@live@hugepages.html [15]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/fi-tgl-dsi/igt@i915_selftest@live@hugepages.html * igt@kms_frontbuffer_tracking@basic: - fi-cml-u2: [DMESG-WARN][16] ([i915#4269]) -> [PASS][17] [16]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11014/fi-cml-u2/igt@kms_frontbuffer_tracking@basic.html [17]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/fi-cml-u2/igt@kms_frontbuffer_tracking@basic.html {name}: This element is suppressed. This means it is ignored when computing the status of the difference (SUCCESS, WARNING, or FAILURE). [fdo#109271]: https://bugs.freedesktop.org/show_bug.cgi?id=109271 [fdo#109315]: https://bugs.freedesktop.org/show_bug.cgi?id=109315 [fdo#111827]: https://bugs.freedesktop.org/show_bug.cgi?id=111827 [i915#2190]: https://gitlab.freedesktop.org/drm/intel/issues/2190 [i915#2426]: https://gitlab.freedesktop.org/drm/intel/issues/2426 [i915#2575]: https://gitlab.freedesktop.org/drm/intel/issues/2575 [i915#3921]: https://gitlab.freedesktop.org/drm/intel/issues/3921 [i915#402]: https://gitlab.freedesktop.org/drm/intel/issues/402 [i915#4269]: https://gitlab.freedesktop.org/drm/intel/issues/4269 [i915#4312]: https://gitlab.freedesktop.org/drm/intel/issues/4312 [i915#4547]: https://gitlab.freedesktop.org/drm/intel/issues/4547 [i915#4613]: https://gitlab.freedesktop.org/drm/intel/issues/4613 [i915#533]: https://gitlab.freedesktop.org/drm/intel/issues/533 Build changes ------------- * CI: CI-20190529 -> None * IGT: IGT_6313 -> IGTPW_6505 CI-20190529: 20190529 CI_DRM_11014: c4f095f24fcdc6e85ae112052b3034328e24ae66 @ git://anongit.freedesktop.org/gfx-ci/linux IGTPW_6505: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/index.html IGT_6313: 1793ed798cc09966c27bf478781e0c1d6bb23bad @ https://gitlab.freedesktop.org/drm/igt-gpu-tools.git == Testlist changes == +igt@gem_ccs@basic-gem-ccs-1m +igt@gem_ccs@basic-gem-ccs-4k +igt@gem_ccs@basic-gem-ccs-64k +igt@gem_ccs@basic-gem-ccs-all == Logs == For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/index.html [-- Attachment #2: Type: text/html, Size: 6814 bytes --] ^ permalink raw reply [flat|nested] 11+ messages in thread
* [igt-dev] ✓ Fi.CI.IGT: success for Add testing for CCS (rev5) 2021-12-19 13:14 [igt-dev] [PATCH i-g-t,v5 0/5] Add testing for CCS apoorva1.singh ` (5 preceding siblings ...) 2021-12-19 13:51 ` [igt-dev] ✓ Fi.CI.BAT: success for Add testing for CCS (rev5) Patchwork @ 2021-12-19 14:56 ` Patchwork 6 siblings, 0 replies; 11+ messages in thread From: Patchwork @ 2021-12-19 14:56 UTC (permalink / raw) To: apoorva1.singh; +Cc: igt-dev [-- Attachment #1: Type: text/plain, Size: 30244 bytes --] == Series Details == Series: Add testing for CCS (rev5) URL : https://patchwork.freedesktop.org/series/96648/ State : success == Summary == CI Bug Log - changes from CI_DRM_11014_full -> IGTPW_6505_full ==================================================== Summary ------- **SUCCESS** No regressions found. External URL: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/index.html Participating hosts (10 -> 7) ------------------------------ Missing (3): pig-skl-6260u pig-kbl-iris pig-glk-j5005 Possible new issues ------------------- Here are the unknown changes that may have been introduced in IGTPW_6505_full: ### IGT changes ### #### Possible regressions #### * {igt@gem_ccs@basic-gem-ccs-4k} (NEW): - shard-iclb: NOTRUN -> [SKIP][1] +3 similar issues [1]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb3/igt@gem_ccs@basic-gem-ccs-4k.html * {igt@gem_ccs@basic-gem-ccs-all} (NEW): - shard-tglb: NOTRUN -> [SKIP][2] +3 similar issues [2]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-tglb2/igt@gem_ccs@basic-gem-ccs-all.html New tests --------- New tests have been introduced between CI_DRM_11014_full and IGTPW_6505_full: ### New IGT tests (4) ### * igt@gem_ccs@basic-gem-ccs-1m: - Statuses : 6 skip(s) - Exec time: [0.0] s * igt@gem_ccs@basic-gem-ccs-4k: - Statuses : 6 skip(s) - Exec time: [0.0] s * igt@gem_ccs@basic-gem-ccs-64k: - Statuses : 6 skip(s) - Exec time: [0.0] s * igt@gem_ccs@basic-gem-ccs-all: - Statuses : 6 skip(s) - Exec time: [0.0] s Known issues ------------ Here are the changes found in IGTPW_6505_full that come from known issues: ### IGT changes ### #### Issues hit #### * igt@feature_discovery@psr2: - shard-iclb: NOTRUN -> [SKIP][3] ([i915#658]) [3]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb7/igt@feature_discovery@psr2.html * igt@gem_create@create-massive: - shard-kbl: NOTRUN -> [DMESG-WARN][4] ([i915#3002]) [4]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-kbl7/igt@gem_create@create-massive.html * igt@gem_ctx_persistence@legacy-engines-hostile-preempt: - shard-snb: NOTRUN -> [SKIP][5] ([fdo#109271] / [i915#1099]) +2 similar issues [5]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-snb6/igt@gem_ctx_persistence@legacy-engines-hostile-preempt.html * igt@gem_eio@unwedge-stress: - shard-tglb: [PASS][6] -> [TIMEOUT][7] ([i915#3063] / [i915#3648]) [6]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11014/shard-tglb2/igt@gem_eio@unwedge-stress.html [7]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-tglb8/igt@gem_eio@unwedge-stress.html * igt@gem_exec_fair@basic-none-rrul@rcs0: - shard-iclb: NOTRUN -> [FAIL][8] ([i915#2842]) +3 similar issues [8]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb7/igt@gem_exec_fair@basic-none-rrul@rcs0.html - shard-glk: NOTRUN -> [FAIL][9] ([i915#2842]) [9]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-glk8/igt@gem_exec_fair@basic-none-rrul@rcs0.html - shard-tglb: NOTRUN -> [FAIL][10] ([i915#2842]) +1 similar issue [10]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-tglb6/igt@gem_exec_fair@basic-none-rrul@rcs0.html * igt@gem_exec_fair@basic-none@vcs0: - shard-apl: [PASS][11] -> [FAIL][12] ([i915#2842]) +1 similar issue [11]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11014/shard-apl1/igt@gem_exec_fair@basic-none@vcs0.html [12]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-apl3/igt@gem_exec_fair@basic-none@vcs0.html * igt@gem_exec_fair@basic-throttle@rcs0: - shard-iclb: [PASS][13] -> [FAIL][14] ([i915#2849]) [13]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11014/shard-iclb8/igt@gem_exec_fair@basic-throttle@rcs0.html [14]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb8/igt@gem_exec_fair@basic-throttle@rcs0.html * igt@gem_exec_suspend@basic-s3: - shard-kbl: [PASS][15] -> [DMESG-WARN][16] ([i915#180]) +1 similar issue [15]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11014/shard-kbl3/igt@gem_exec_suspend@basic-s3.html [16]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-kbl6/igt@gem_exec_suspend@basic-s3.html * igt@gem_exec_whisper@basic-queues-forked: - shard-iclb: NOTRUN -> [INCOMPLETE][17] ([i915#1895]) [17]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb7/igt@gem_exec_whisper@basic-queues-forked.html * igt@gem_huc_copy@huc-copy: - shard-apl: NOTRUN -> [SKIP][18] ([fdo#109271] / [i915#2190]) [18]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-apl6/igt@gem_huc_copy@huc-copy.html - shard-kbl: NOTRUN -> [SKIP][19] ([fdo#109271] / [i915#2190]) [19]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-kbl7/igt@gem_huc_copy@huc-copy.html * igt@gem_lmem_swapping@heavy-verify-random: - shard-kbl: NOTRUN -> [SKIP][20] ([fdo#109271] / [i915#4613]) +1 similar issue [20]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-kbl4/igt@gem_lmem_swapping@heavy-verify-random.html * igt@gem_pwrite@basic-exhaustion: - shard-kbl: NOTRUN -> [WARN][21] ([i915#2658]) [21]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-kbl3/igt@gem_pwrite@basic-exhaustion.html * igt@gem_pxp@create-protected-buffer: - shard-tglb: NOTRUN -> [SKIP][22] ([i915#4270]) [22]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-tglb3/igt@gem_pxp@create-protected-buffer.html * igt@gem_pxp@dmabuf-shared-protected-dst-is-context-refcounted: - shard-iclb: NOTRUN -> [SKIP][23] ([i915#4270]) +2 similar issues [23]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb8/igt@gem_pxp@dmabuf-shared-protected-dst-is-context-refcounted.html * igt@gem_render_copy@x-tiled-to-vebox-yf-tiled: - shard-kbl: NOTRUN -> [SKIP][24] ([fdo#109271]) +306 similar issues [24]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-kbl6/igt@gem_render_copy@x-tiled-to-vebox-yf-tiled.html * igt@gem_render_copy@y-tiled-to-vebox-linear: - shard-iclb: NOTRUN -> [SKIP][25] ([i915#768]) +3 similar issues [25]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb6/igt@gem_render_copy@y-tiled-to-vebox-linear.html * igt@gem_userptr_blits@dmabuf-sync: - shard-kbl: NOTRUN -> [SKIP][26] ([fdo#109271] / [i915#3323]) [26]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-kbl6/igt@gem_userptr_blits@dmabuf-sync.html * igt@gem_userptr_blits@readonly-pwrite-unsync: - shard-iclb: NOTRUN -> [SKIP][27] ([i915#3297]) [27]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb4/igt@gem_userptr_blits@readonly-pwrite-unsync.html * igt@gen9_exec_parse@shadow-peek: - shard-tglb: NOTRUN -> [SKIP][28] ([i915#2856]) [28]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-tglb8/igt@gen9_exec_parse@shadow-peek.html - shard-iclb: NOTRUN -> [SKIP][29] ([i915#2856]) [29]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb8/igt@gen9_exec_parse@shadow-peek.html * igt@i915_pm_dc@dc9-dpms: - shard-iclb: [PASS][30] -> [SKIP][31] ([i915#4281]) [30]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11014/shard-iclb7/igt@i915_pm_dc@dc9-dpms.html [31]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb3/igt@i915_pm_dc@dc9-dpms.html * igt@i915_pm_rpm@dpms-mode-unset-non-lpsp: - shard-tglb: NOTRUN -> [SKIP][32] ([fdo#111644] / [i915#1397] / [i915#2411]) [32]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-tglb2/igt@i915_pm_rpm@dpms-mode-unset-non-lpsp.html - shard-iclb: NOTRUN -> [SKIP][33] ([fdo#110892]) [33]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb4/igt@i915_pm_rpm@dpms-mode-unset-non-lpsp.html * igt@i915_pm_sseu@full-enable: - shard-tglb: NOTRUN -> [SKIP][34] ([i915#4387]) [34]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-tglb2/igt@i915_pm_sseu@full-enable.html - shard-iclb: NOTRUN -> [SKIP][35] ([i915#4387]) [35]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb4/igt@i915_pm_sseu@full-enable.html * igt@i915_suspend@fence-restore-tiled2untiled: - shard-apl: [PASS][36] -> [DMESG-WARN][37] ([i915#180]) +4 similar issues [36]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11014/shard-apl2/igt@i915_suspend@fence-restore-tiled2untiled.html [37]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-apl3/igt@i915_suspend@fence-restore-tiled2untiled.html * igt@kms_big_fb@linear-8bpp-rotate-90: - shard-iclb: NOTRUN -> [SKIP][38] ([fdo#110725] / [fdo#111614]) +1 similar issue [38]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb1/igt@kms_big_fb@linear-8bpp-rotate-90.html * igt@kms_big_fb@x-tiled-max-hw-stride-32bpp-rotate-180-hflip: - shard-kbl: NOTRUN -> [SKIP][39] ([fdo#109271] / [i915#3777]) +1 similar issue [39]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-kbl1/igt@kms_big_fb@x-tiled-max-hw-stride-32bpp-rotate-180-hflip.html * igt@kms_big_fb@y-tiled-8bpp-rotate-270: - shard-tglb: NOTRUN -> [SKIP][40] ([fdo#111614]) [40]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-tglb3/igt@kms_big_fb@y-tiled-8bpp-rotate-270.html * igt@kms_big_fb@yf-tiled-64bpp-rotate-180: - shard-iclb: NOTRUN -> [SKIP][41] ([fdo#110723]) [41]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb5/igt@kms_big_fb@yf-tiled-64bpp-rotate-180.html * igt@kms_big_fb@yf-tiled-max-hw-stride-32bpp-rotate-0-async-flip: - shard-tglb: NOTRUN -> [SKIP][42] ([fdo#111615]) [42]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-tglb2/igt@kms_big_fb@yf-tiled-max-hw-stride-32bpp-rotate-0-async-flip.html * igt@kms_big_fb@yf-tiled-max-hw-stride-64bpp-rotate-0: - shard-apl: NOTRUN -> [SKIP][43] ([fdo#109271]) +122 similar issues [43]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-apl8/igt@kms_big_fb@yf-tiled-max-hw-stride-64bpp-rotate-0.html * igt@kms_big_joiner@2x-modeset: - shard-iclb: NOTRUN -> [SKIP][44] ([i915#2705]) [44]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb5/igt@kms_big_joiner@2x-modeset.html - shard-tglb: NOTRUN -> [SKIP][45] ([i915#2705]) [45]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-tglb6/igt@kms_big_joiner@2x-modeset.html * igt@kms_ccs@pipe-a-bad-aux-stride-y_tiled_gen12_rc_ccs_cc: - shard-iclb: NOTRUN -> [SKIP][46] ([fdo#109278] / [i915#3886]) +2 similar issues [46]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb3/igt@kms_ccs@pipe-a-bad-aux-stride-y_tiled_gen12_rc_ccs_cc.html * igt@kms_ccs@pipe-b-ccs-on-another-bo-y_tiled_gen12_mc_ccs: - shard-glk: NOTRUN -> [SKIP][47] ([fdo#109271] / [i915#3886]) +2 similar issues [47]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-glk8/igt@kms_ccs@pipe-b-ccs-on-another-bo-y_tiled_gen12_mc_ccs.html - shard-tglb: NOTRUN -> [SKIP][48] ([i915#3689] / [i915#3886]) +1 similar issue [48]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-tglb6/igt@kms_ccs@pipe-b-ccs-on-another-bo-y_tiled_gen12_mc_ccs.html - shard-apl: NOTRUN -> [SKIP][49] ([fdo#109271] / [i915#3886]) +3 similar issues [49]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-apl8/igt@kms_ccs@pipe-b-ccs-on-another-bo-y_tiled_gen12_mc_ccs.html * igt@kms_ccs@pipe-b-missing-ccs-buffer-y_tiled_gen12_rc_ccs_cc: - shard-kbl: NOTRUN -> [SKIP][50] ([fdo#109271] / [i915#3886]) +14 similar issues [50]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-kbl4/igt@kms_ccs@pipe-b-missing-ccs-buffer-y_tiled_gen12_rc_ccs_cc.html * igt@kms_ccs@pipe-d-bad-aux-stride-y_tiled_gen12_mc_ccs: - shard-tglb: NOTRUN -> [SKIP][51] ([i915#3689]) +3 similar issues [51]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-tglb5/igt@kms_ccs@pipe-d-bad-aux-stride-y_tiled_gen12_mc_ccs.html * igt@kms_ccs@pipe-d-bad-pixel-format-y_tiled_ccs: - shard-snb: NOTRUN -> [SKIP][52] ([fdo#109271]) +98 similar issues [52]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-snb7/igt@kms_ccs@pipe-d-bad-pixel-format-y_tiled_ccs.html * igt@kms_ccs@pipe-d-random-ccs-data-yf_tiled_ccs: - shard-tglb: NOTRUN -> [SKIP][53] ([fdo#111615] / [i915#3689]) [53]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-tglb3/igt@kms_ccs@pipe-d-random-ccs-data-yf_tiled_ccs.html * igt@kms_chamelium@dp-crc-multiple: - shard-apl: NOTRUN -> [SKIP][54] ([fdo#109271] / [fdo#111827]) +6 similar issues [54]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-apl8/igt@kms_chamelium@dp-crc-multiple.html * igt@kms_chamelium@hdmi-crc-fast: - shard-iclb: NOTRUN -> [SKIP][55] ([fdo#109284] / [fdo#111827]) +8 similar issues [55]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb1/igt@kms_chamelium@hdmi-crc-fast.html * igt@kms_chamelium@hdmi-crc-multiple: - shard-snb: NOTRUN -> [SKIP][56] ([fdo#109271] / [fdo#111827]) +4 similar issues [56]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-snb7/igt@kms_chamelium@hdmi-crc-multiple.html * igt@kms_color@pipe-d-ctm-max: - shard-iclb: NOTRUN -> [SKIP][57] ([fdo#109278] / [i915#1149]) [57]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb3/igt@kms_color@pipe-d-ctm-max.html * igt@kms_color_chamelium@pipe-a-degamma: - shard-kbl: NOTRUN -> [SKIP][58] ([fdo#109271] / [fdo#111827]) +30 similar issues [58]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-kbl7/igt@kms_color_chamelium@pipe-a-degamma.html * igt@kms_color_chamelium@pipe-d-ctm-max: - shard-tglb: NOTRUN -> [SKIP][59] ([fdo#109284] / [fdo#111827]) +4 similar issues [59]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-tglb1/igt@kms_color_chamelium@pipe-d-ctm-max.html - shard-glk: NOTRUN -> [SKIP][60] ([fdo#109271] / [fdo#111827]) +4 similar issues [60]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-glk9/igt@kms_color_chamelium@pipe-d-ctm-max.html - shard-iclb: NOTRUN -> [SKIP][61] ([fdo#109278] / [fdo#109284] / [fdo#111827]) [61]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb5/igt@kms_color_chamelium@pipe-d-ctm-max.html * igt@kms_content_protection@atomic-dpms: - shard-kbl: NOTRUN -> [TIMEOUT][62] ([i915#1319]) [62]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-kbl6/igt@kms_content_protection@atomic-dpms.html * igt@kms_content_protection@dp-mst-type-1: - shard-iclb: NOTRUN -> [SKIP][63] ([i915#3116]) [63]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb6/igt@kms_content_protection@dp-mst-type-1.html * igt@kms_content_protection@srm: - shard-glk: NOTRUN -> [SKIP][64] ([fdo#109271]) +49 similar issues [64]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-glk3/igt@kms_content_protection@srm.html - shard-tglb: NOTRUN -> [SKIP][65] ([fdo#111828]) [65]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-tglb5/igt@kms_content_protection@srm.html - shard-iclb: NOTRUN -> [SKIP][66] ([fdo#109300] / [fdo#111066]) [66]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb8/igt@kms_content_protection@srm.html - shard-apl: NOTRUN -> [TIMEOUT][67] ([i915#1319]) [67]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-apl1/igt@kms_content_protection@srm.html * igt@kms_content_protection@uevent: - shard-kbl: NOTRUN -> [FAIL][68] ([i915#2105]) [68]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-kbl4/igt@kms_content_protection@uevent.html * igt@kms_cursor_crc@pipe-a-cursor-512x512-offscreen: - shard-iclb: NOTRUN -> [SKIP][69] ([fdo#109278] / [fdo#109279]) [69]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb4/igt@kms_cursor_crc@pipe-a-cursor-512x512-offscreen.html * igt@kms_cursor_crc@pipe-c-cursor-32x10-rapid-movement: - shard-tglb: NOTRUN -> [SKIP][70] ([i915#3359]) +2 similar issues [70]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-tglb1/igt@kms_cursor_crc@pipe-c-cursor-32x10-rapid-movement.html * igt@kms_cursor_crc@pipe-c-cursor-suspend: - shard-kbl: NOTRUN -> [INCOMPLETE][71] ([i915#3614]) [71]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-kbl4/igt@kms_cursor_crc@pipe-c-cursor-suspend.html - shard-apl: NOTRUN -> [DMESG-WARN][72] ([i915#180]) [72]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-apl8/igt@kms_cursor_crc@pipe-c-cursor-suspend.html * igt@kms_cursor_edge_walk@pipe-d-256x256-left-edge: - shard-iclb: NOTRUN -> [SKIP][73] ([fdo#109278]) +22 similar issues [73]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb8/igt@kms_cursor_edge_walk@pipe-d-256x256-left-edge.html * igt@kms_cursor_legacy@cursorb-vs-flipa-toggle: - shard-iclb: NOTRUN -> [SKIP][74] ([fdo#109274] / [fdo#109278]) +5 similar issues [74]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb3/igt@kms_cursor_legacy@cursorb-vs-flipa-toggle.html * igt@kms_dsc@xrgb8888-dsc-compression: - shard-tglb: NOTRUN -> [SKIP][75] ([i915#3828]) [75]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-tglb6/igt@kms_dsc@xrgb8888-dsc-compression.html - shard-iclb: NOTRUN -> [SKIP][76] ([i915#3828]) [76]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb7/igt@kms_dsc@xrgb8888-dsc-compression.html * igt@kms_fbcon_fbt@fbc-suspend: - shard-apl: [PASS][77] -> [INCOMPLETE][78] ([i915#180] / [i915#1982]) [77]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11014/shard-apl1/igt@kms_fbcon_fbt@fbc-suspend.html [78]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-apl3/igt@kms_fbcon_fbt@fbc-suspend.html * igt@kms_flip@2x-flip-vs-rmfb-interruptible: - shard-iclb: NOTRUN -> [SKIP][79] ([fdo#109274]) +6 similar issues [79]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb4/igt@kms_flip@2x-flip-vs-rmfb-interruptible.html * igt@kms_flip_scaled_crc@flip-32bpp-ytile-to-32bpp-ytilegen12rcccs: - shard-apl: NOTRUN -> [SKIP][80] ([fdo#109271] / [i915#2672]) [80]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-apl6/igt@kms_flip_scaled_crc@flip-32bpp-ytile-to-32bpp-ytilegen12rcccs.html - shard-iclb: NOTRUN -> [SKIP][81] ([i915#2587]) [81]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb4/igt@kms_flip_scaled_crc@flip-32bpp-ytile-to-32bpp-ytilegen12rcccs.html * igt@kms_flip_scaled_crc@flip-64bpp-ytile-to-16bpp-ytile: - shard-iclb: [PASS][82] -> [SKIP][83] ([i915#3701]) [82]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11014/shard-iclb5/igt@kms_flip_scaled_crc@flip-64bpp-ytile-to-16bpp-ytile.html [83]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb2/igt@kms_flip_scaled_crc@flip-64bpp-ytile-to-16bpp-ytile.html * igt@kms_frontbuffer_tracking@fbc-2p-scndscrn-pri-shrfb-draw-mmap-cpu: - shard-iclb: NOTRUN -> [SKIP][84] ([fdo#109280]) +19 similar issues [84]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb4/igt@kms_frontbuffer_tracking@fbc-2p-scndscrn-pri-shrfb-draw-mmap-cpu.html * igt@kms_frontbuffer_tracking@fbcpsr-2p-primscrn-cur-indfb-draw-mmap-cpu: - shard-tglb: NOTRUN -> [SKIP][85] ([fdo#111825]) +18 similar issues [85]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-tglb1/igt@kms_frontbuffer_tracking@fbcpsr-2p-primscrn-cur-indfb-draw-mmap-cpu.html * igt@kms_pipe_crc_basic@read-crc-pipe-d: - shard-apl: NOTRUN -> [SKIP][86] ([fdo#109271] / [i915#533]) [86]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-apl6/igt@kms_pipe_crc_basic@read-crc-pipe-d.html * igt@kms_pipe_crc_basic@suspend-read-crc-pipe-d: - shard-kbl: NOTRUN -> [SKIP][87] ([fdo#109271] / [i915#533]) +1 similar issue [87]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-kbl6/igt@kms_pipe_crc_basic@suspend-read-crc-pipe-d.html * igt@kms_plane_alpha_blend@pipe-a-alpha-basic: - shard-apl: NOTRUN -> [FAIL][88] ([fdo#108145] / [i915#265]) [88]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-apl4/igt@kms_plane_alpha_blend@pipe-a-alpha-basic.html * igt@kms_plane_alpha_blend@pipe-b-constant-alpha-max: - shard-glk: NOTRUN -> [FAIL][89] ([fdo#108145] / [i915#265]) +1 similar issue [89]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-glk6/igt@kms_plane_alpha_blend@pipe-b-constant-alpha-max.html * igt@kms_plane_alpha_blend@pipe-c-constant-alpha-max: - shard-kbl: NOTRUN -> [FAIL][90] ([fdo#108145] / [i915#265]) +3 similar issues [90]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-kbl6/igt@kms_plane_alpha_blend@pipe-c-constant-alpha-max.html * igt@kms_plane_lowres@pipe-c-tiling-none: - shard-iclb: NOTRUN -> [SKIP][91] ([i915#3536]) +2 similar issues [91]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb1/igt@kms_plane_lowres@pipe-c-tiling-none.html * igt@kms_plane_lowres@pipe-c-tiling-x: - shard-tglb: NOTRUN -> [SKIP][92] ([i915#3536]) [92]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-tglb5/igt@kms_plane_lowres@pipe-c-tiling-x.html * igt@kms_plane_multiple@atomic-pipe-d-tiling-yf: - shard-tglb: NOTRUN -> [SKIP][93] ([fdo#111615] / [fdo#112054]) +1 similar issue [93]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-tglb6/igt@kms_plane_multiple@atomic-pipe-d-tiling-yf.html * igt@kms_psr2_sf@plane-move-sf-dmg-area: - shard-iclb: NOTRUN -> [SKIP][94] ([fdo#111068] / [i915#658]) +1 similar issue [94]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb6/igt@kms_psr2_sf@plane-move-sf-dmg-area.html - shard-apl: NOTRUN -> [SKIP][95] ([fdo#109271] / [i915#658]) +1 similar issue [95]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-apl4/igt@kms_psr2_sf@plane-move-sf-dmg-area.html * igt@kms_psr2_su@page_flip-p010: - shard-tglb: NOTRUN -> [SKIP][96] ([i915#1911]) [96]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-tglb3/igt@kms_psr2_su@page_flip-p010.html - shard-glk: NOTRUN -> [SKIP][97] ([fdo#109271] / [i915#658]) [97]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-glk3/igt@kms_psr2_su@page_flip-p010.html * igt@kms_psr2_su@page_flip-xrgb8888: - shard-kbl: NOTRUN -> [SKIP][98] ([fdo#109271] / [i915#658]) +2 similar issues [98]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-kbl4/igt@kms_psr2_su@page_flip-xrgb8888.html * igt@kms_psr@psr2_primary_mmap_cpu: - shard-tglb: NOTRUN -> [FAIL][99] ([i915#132] / [i915#3467]) [99]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-tglb3/igt@kms_psr@psr2_primary_mmap_cpu.html * igt@kms_psr@psr2_primary_mmap_gtt: - shard-iclb: [PASS][100] -> [SKIP][101] ([fdo#109441]) +1 similar issue [100]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11014/shard-iclb2/igt@kms_psr@psr2_primary_mmap_gtt.html [101]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb5/igt@kms_psr@psr2_primary_mmap_gtt.html * igt@kms_psr@psr2_sprite_plane_move: - shard-iclb: NOTRUN -> [SKIP][102] ([fdo#109441]) +1 similar issue [102]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb7/igt@kms_psr@psr2_sprite_plane_move.html * igt@kms_setmode@basic: - shard-apl: [PASS][103] -> [FAIL][104] ([i915#31]) [103]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11014/shard-apl4/igt@kms_setmode@basic.html [104]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-apl2/igt@kms_setmode@basic.html - shard-glk: [PASS][105] -> [FAIL][106] ([i915#31]) [105]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11014/shard-glk7/igt@kms_setmode@basic.html [106]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-glk9/igt@kms_setmode@basic.html * igt@kms_writeback@writeback-check-output: - shard-apl: NOTRUN -> [SKIP][107] ([fdo#109271] / [i915#2437]) +1 similar issue [107]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-apl8/igt@kms_writeback@writeback-check-output.html - shard-iclb: NOTRUN -> [SKIP][108] ([i915#2437]) +1 similar issue [108]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb8/igt@kms_writeback@writeback-check-output.html - shard-tglb: NOTRUN -> [SKIP][109] ([i915#2437]) [109]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-tglb7/igt@kms_writeback@writeback-check-output.html - shard-glk: NOTRUN -> [SKIP][110] ([fdo#109271] / [i915#2437]) [110]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-glk1/igt@kms_writeback@writeback-check-output.html * igt@kms_writeback@writeback-fb-id: - shard-kbl: NOTRUN -> [SKIP][111] ([fdo#109271] / [i915#2437]) +1 similar issue [111]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-kbl3/igt@kms_writeback@writeback-fb-id.html * igt@perf@gen12-mi-rpc: - shard-iclb: NOTRUN -> [SKIP][112] ([fdo#109289]) [112]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb8/igt@perf@gen12-mi-rpc.html * igt@prime_nv_api@i915_nv_import_twice: - shard-iclb: NOTRUN -> [SKIP][113] ([fdo#109291]) +1 similar issue [113]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb7/igt@prime_nv_api@i915_nv_import_twice.html * igt@prime_nv_pcopy@test2: - shard-tglb: NOTRUN -> [SKIP][114] ([fdo#109291]) [114]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-tglb2/igt@prime_nv_pcopy@test2.html * igt@prime_vgem@fence-read-hang: - shard-iclb: NOTRUN -> [SKIP][115] ([fdo#109295]) [115]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb2/igt@prime_vgem@fence-read-hang.html * igt@sysfs_clients@fair-0: - shard-tglb: NOTRUN -> [SKIP][116] ([i915#2994]) +1 similar issue [116]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-tglb7/igt@sysfs_clients@fair-0.html - shard-glk: NOTRUN -> [SKIP][117] ([fdo#109271] / [i915#2994]) +1 similar issue [117]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-glk5/igt@sysfs_clients@fair-0.html * igt@sysfs_clients@fair-7: - shard-apl: NOTRUN -> [SKIP][118] ([fdo#109271] / [i915#2994]) +1 similar issue [118]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-apl4/igt@sysfs_clients@fair-7.html - shard-iclb: NOTRUN -> [SKIP][119] ([i915#2994]) +1 similar issue [119]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb5/igt@sysfs_clients@fair-7.html - shard-kbl: NOTRUN -> [SKIP][120] ([fdo#109271] / [i915#2994]) +3 similar issues [120]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-kbl7/igt@sysfs_clients@fair-7.html #### Possible fixes #### * igt@gem_ctx_isolation@preservation-s3@vcs0: - shard-kbl: [DMESG-WARN][121] ([i915#180]) -> [PASS][122] +8 similar issues [121]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11014/shard-kbl6/igt@gem_ctx_isolation@preservation-s3@vcs0.html [122]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-kbl3/igt@gem_ctx_isolation@preservation-s3@vcs0.html * igt@gem_exec_fair@basic-deadline: - shard-kbl: [FAIL][123] ([i915#2846]) -> [PASS][124] [123]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11014/shard-kbl7/igt@gem_exec_fair@basic-deadline.html [124]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-kbl4/igt@gem_exec_fair@basic-deadline.html * igt@i915_pm_dc@dc6-psr: - shard-iclb: [FAIL][125] ([i915#454]) -> [PASS][126] [125]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11014/shard-iclb4/igt@i915_pm_dc@dc6-psr.html [126]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-iclb7/igt@i915_pm_dc@dc6-psr.html * igt@i915_pm_dc@dc9-dpms: - shard-apl: [SKIP][127] ([fdo#109271]) -> [PASS][128] [127]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11014/shard-apl2/igt@i915_pm_dc@dc9-dpms.html [128]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-apl6/igt@i915_pm_dc@dc9-dpms.html * igt@kms_big_fb@linear-32bpp-rotate-180: - shard-glk: [DMESG-WARN][129] ([i915#118]) -> [PASS][130] [129]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11014/shard-glk7/igt@kms_big_fb@linear-32bpp-rotate-180.html [130]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-glk9/igt@kms_big_fb@linear-32bpp-rotate-180.html * igt@kms_big_fb@x-tiled-32bpp-rotate-0: - shard-glk: [FAIL][131] ([i915#1888] / [i915#3653]) -> [PASS][132] [131]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11014/shard-glk2/igt@kms_big_fb@x-tiled-32bpp-rotate-0.html [132]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-glk2/igt@kms_big_fb@x-tiled-32bpp-rotate-0.html * igt@kms_big_fb@y-tiled-32bpp-rotate-180: - shard-glk: [DMESG-FAIL][133] ([i915#118] / [i915#1888]) -> [PASS][134] [133]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11014/shard-glk2/igt@kms_big_fb@y-tiled-32bpp-rotate-180.html [134]: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/shard-glk5/igt@kms_big_fb@y-tiled-32bpp-rotate-180.html * igt@kms_cursor_legacy@2x-long-flip-vs-cursor-legacy: - shard- == Logs == For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/IGTPW_6505/index.html [-- Attachment #2: Type: text/html, Size: 33998 bytes --] ^ permalink raw reply [flat|nested] 11+ messages in thread
end of thread, other threads:[~2021-12-20 13:51 UTC | newest] Thread overview: 11+ messages (download: mbox.gz / follow: Atom feed) -- links below jump to the message on this page -- 2021-12-19 13:14 [igt-dev] [PATCH i-g-t,v5 0/5] Add testing for CCS apoorva1.singh 2021-12-19 13:14 ` [igt-dev] [PATCH i-g-t, v5 1/5] lib/i915: Introduce library intel_mocs apoorva1.singh 2021-12-20 12:36 ` Zbigniew Kempczyński 2021-12-19 13:14 ` [igt-dev] [PATCH i-g-t, v5 2/5] lib/i915: Introduce library i915_blt apoorva1.singh 2021-12-20 13:06 ` Zbigniew Kempczyński 2021-12-20 13:49 ` Petri Latvala 2021-12-19 13:14 ` [igt-dev] [PATCH i-g-t, v5 3/5] lib/intel_chipset.h: Add has_flat_ccs flag apoorva1.singh 2021-12-19 13:14 ` [igt-dev] [PATCH i-g-t, v5 4/5] i915/gem_engine_topology: Only use the main copy engines for XY_BLOCK_COPY apoorva1.singh 2021-12-19 13:14 ` [igt-dev] [PATCH i-g-t,v5 5/5] i915/gem_ccs: Add testing for CCS apoorva1.singh 2021-12-19 13:51 ` [igt-dev] ✓ Fi.CI.BAT: success for Add testing for CCS (rev5) Patchwork 2021-12-19 14:56 ` [igt-dev] ✓ Fi.CI.IGT: " Patchwork
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.