[Intel-gfx] [PATCH v2] igt/gem_trtt: Exercise the TRTT hardware
akash.goel at intel.com
akash.goel at intel.com
Fri Jan 22 07:37:47 PST 2016
From: Akash Goel <akash.goel at intel.com>
This patch provides the testcase to exercise the TRTT hardware.
Some platforms have an additional address translation hardware support in
form of Tiled Resource Translation Table (TR-TT) which provides an extra level
of abstraction over PPGTT.
This is useful for mapping Sparse/Tiled texture resources.
TR-TT is tightly coupled with PPGTT, a new instance of TR-TT will be required
for a new PPGTT instance, but TR-TT may not enabled for every context.
1/16th of the 48bit PPGTT space is earmarked for the translation by TR-TT,
which such chunk to use is conveyed to HW through a register.
Any GFX address, which lies in that reserved 44 bit range will be translated
through TR-TT first and then through PPGTT to get the actual physical address.
TRTT is constructed as a 3 level tile Table. Each tile is 64KB is size which
leaves behind 44-16=28 address bits. 28bits are partitioned as 9+9+10, and
each level is contained within a 4KB page hence L3 and L2 is composed of
512 64b entries and L1 is composed of 1024 32b entries.
There is a provision to keep TR-TT Tables in virtual space, where the pages of
TRTT tables will be mapped to PPGTT. This is the adopted mode, as in this mode
UMD will have a full control on TR-TT management, with bare minimum support
from KMD.
So the entries of L3 table will contain the PPGTT offset of L2 Table pages,
similarly entries of L2 table will contain the PPGTT offset of L1 Table pages.
The entries of L1 table will contain the PPGTT offset of BOs actually backing
the Sparse resources.
I915_GEM_CONTEXT_SETPARAM ioctl is used to request KMD to enable TRTT for a
certain context, a new I915_CONTEXT_PARAM_ENABLE_TRTT param has been
added to the CONTEXT_SETPARAM ioctl for that purpose.
v2:
- Add new wrapper function __gem_context_require_param and used that
to detect the TR-TT support
- Use igt_main macro, rename certain function, remove extra white space,
cleanup the code (Chris)
- Enhance the basic subtest to exercise all possible TR-TT segment start
locations (i.e. 16 of them) & for every iteration create a new context.
Cc: Chris Wilson <chris at chris-wilson.co.uk>
Signed-off-by: Akash Goel <akash.goel at intel.com>
---
lib/ioctl_wrappers.c | 25 ++-
lib/ioctl_wrappers.h | 2 +
tests/Makefile.sources | 1 +
tests/gem_trtt.c | 446 +++++++++++++++++++++++++++++++++++++++++++++++++
4 files changed, 466 insertions(+), 8 deletions(-)
create mode 100644 tests/gem_trtt.c
diff --git a/lib/ioctl_wrappers.c b/lib/ioctl_wrappers.c
index e348f26..46e1db2 100644
--- a/lib/ioctl_wrappers.c
+++ b/lib/ioctl_wrappers.c
@@ -833,6 +833,22 @@ void gem_context_set_param(int fd, struct local_i915_gem_context_param *p)
do_ioctl(fd, LOCAL_IOCTL_I915_GEM_CONTEXT_SETPARAM, p);
}
+int __gem_context_require_param(int fd, uint64_t param)
+{
+ struct local_i915_gem_context_param p;
+ int ret;
+
+ p.context = 0;
+ p.param = param;
+ p.value = 0;
+ p.size = 0;
+
+ ret = drmIoctl(fd, LOCAL_IOCTL_I915_GEM_CONTEXT_GETPARAM, &p);
+ if (ret)
+ return -errno;
+ return 0;
+}
+
/**
* gem_context_require_param:
* @fd: open i915 drm file descriptor
@@ -843,14 +859,7 @@ void gem_context_set_param(int fd, struct local_i915_gem_context_param *p)
*/
void gem_context_require_param(int fd, uint64_t param)
{
- struct local_i915_gem_context_param p;
-
- p.context = 0;
- p.param = param;
- p.value = 0;
- p.size = 0;
-
- igt_require(drmIoctl(fd, LOCAL_IOCTL_I915_GEM_CONTEXT_GETPARAM, &p) == 0);
+ igt_require(__gem_context_require_param(fd, param) == 0);
}
void gem_context_require_ban_period(int fd)
diff --git a/lib/ioctl_wrappers.h b/lib/ioctl_wrappers.h
index fe2f687..258c612 100644
--- a/lib/ioctl_wrappers.h
+++ b/lib/ioctl_wrappers.h
@@ -105,9 +105,11 @@ struct local_i915_gem_context_param {
#define LOCAL_CONTEXT_PARAM_BAN_PERIOD 0x1
#define LOCAL_CONTEXT_PARAM_NO_ZEROMAP 0x2
#define LOCAL_CONTEXT_PARAM_GTT_SIZE 0x3
+#define LOCAL_CONTEXT_PARAM_TRTT 0x4
uint64_t value;
};
void gem_context_require_ban_period(int fd);
+int __gem_context_require_param(int fd, uint64_t param);
void gem_context_require_param(int fd, uint64_t param);
void gem_context_get_param(int fd, struct local_i915_gem_context_param *p);
void gem_context_set_param(int fd, struct local_i915_gem_context_param *p);
diff --git a/tests/Makefile.sources b/tests/Makefile.sources
index d594038..068a44e 100644
--- a/tests/Makefile.sources
+++ b/tests/Makefile.sources
@@ -64,6 +64,7 @@ TESTS_progs_M = \
gem_streaming_writes \
gem_tiled_blits \
gem_tiled_partial_pwrite_pread \
+ gem_trtt \
gem_userptr_blits \
gem_write_read_ring_switch \
kms_addfb_basic \
diff --git a/tests/gem_trtt.c b/tests/gem_trtt.c
new file mode 100644
index 0000000..5076e18
--- /dev/null
+++ b/tests/gem_trtt.c
@@ -0,0 +1,446 @@
+/*
+ * Copyright © 2016 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ * Authors:
+ * Akash Goel <akash.goel at intel.com>
+ *
+ */
+
+#include <unistd.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <string.h>
+#include <fcntl.h>
+#include <inttypes.h>
+#include <errno.h>
+#include <sys/stat.h>
+#include <sys/ioctl.h>
+#include <sys/time.h>
+#include <malloc.h>
+#include "drm.h"
+#include "ioctl_wrappers.h"
+#include "drmtest.h"
+#include "intel_chipset.h"
+#include "intel_io.h"
+#include "i915_drm.h"
+#include <assert.h>
+#include <sys/wait.h>
+#include <sys/ipc.h>
+#include <sys/shm.h>
+#include "igt_kms.h"
+#include <inttypes.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+
+#define BO_SIZE 4096
+#define EXEC_OBJECT_PINNED (1<<4)
+#define EXEC_OBJECT_SUPPORTS_48B_ADDRESS (1<<3)
+
+#define NO_PPGTT 0
+#define ALIASING_PPGTT 1
+#define FULL_32_BIT_PPGTT 2
+#define FULL_48_BIT_PPGTT 3
+/* uses_full_ppgtt
+ * Finds supported PPGTT details.
+ * @fd DRM fd
+ * @min can be
+ * 0 - No PPGTT
+ * 1 - Aliasing PPGTT
+ * 2 - Full PPGTT (32b)
+ * 3 - Full PPGTT (48b)
+ * RETURNS true/false if min support is present
+*/
+static bool uses_full_ppgtt(int fd, int min)
+{
+ struct drm_i915_getparam gp;
+ int val = 0;
+
+ memset(&gp, 0, sizeof(gp));
+ gp.param = 18; /* HAS_ALIASING_PPGTT */
+ gp.value = &val;
+
+ if (drmIoctl(fd, DRM_IOCTL_I915_GETPARAM, &gp))
+ return 0;
+
+ errno = 0;
+ return val >= min;
+}
+
+/* has_softpin_support
+ * Finds if softpin feature is supported
+ * @fd DRM fd
+*/
+static bool has_softpin_support(int fd)
+{
+ struct drm_i915_getparam gp;
+ int val = 0;
+
+ memset(&gp, 0, sizeof(gp));
+ gp.param = 37; /* I915_PARAM_HAS_EXEC_SOFTPIN */
+ gp.value = &val;
+
+ if (drmIoctl(fd, DRM_IOCTL_I915_GETPARAM, &gp))
+ return 0;
+
+ errno = 0;
+ return (val == 1);
+}
+
+/* has_trtt_support
+ * Finds if trtt hw is present
+ * @fd DRM fd
+*/
+static bool has_trtt_support(int fd)
+{
+ int ret = __gem_context_require_param(fd, LOCAL_CONTEXT_PARAM_TRTT);
+
+ errno = 0;
+ return (ret == 0);
+}
+
+/* mmap_bo
+ * helper for creating a CPU mmapping of the buffer
+ * @fd - drm fd
+ * @handle - handle of the buffer to mmap
+ * @size: size of the buffer
+*/
+static void* mmap_bo(int fd, uint32_t handle, uint64_t size)
+{
+ uint32_t *ptr = gem_mmap__cpu(fd, handle, 0, size, PROT_READ);
+ gem_set_domain(fd, handle, I915_GEM_DOMAIN_CPU, 0);
+ return ptr;
+}
+
+/* emit_store_dword
+ * populate batch buffer with MI_STORE_DWORD_IMM command
+ * @fd: drm file descriptor
+ * @cmd_buf: batch buffer
+ * @dw_offset: write offset in batch buffer
+ * @vaddr: destination Virtual address
+ * @data: u32 data to be stored at destination
+*/
+static int emit_store_dword(int fd, uint32_t *cmd_buf, uint32_t dw_offset,
+ uint64_t vaddr, uint32_t data)
+{
+ cmd_buf[dw_offset++] = MI_STORE_DWORD_IMM;
+ cmd_buf[dw_offset++] = vaddr & 0xFFFFFFFC;
+ cmd_buf[dw_offset++] = (vaddr >> 32) & 0xFFFF; /* bits 32:47 */
+ cmd_buf[dw_offset++] = data;
+
+ return dw_offset;
+}
+
+/* emit_store_qword
+ * populate batch buffer with MI_STORE_DWORD_IMM command
+ * @fd: drm file descriptor
+ * @cmd_buf: batch buffer
+ * @dw_offset: write offset in batch buffer
+ * @vaddr: destination Virtual address
+ * @data: u64 data to be stored at destination
+*/
+static int emit_store_qword(int fd, uint32_t *cmd_buf, uint32_t dw_offset,
+ uint64_t vaddr, uint64_t data)
+{
+ cmd_buf[dw_offset++] = MI_STORE_DWORD_IMM | 0x3;
+ cmd_buf[dw_offset++] = vaddr & 0xFFFFFFFC;
+ cmd_buf[dw_offset++] = (vaddr >> 32) & 0xFFFF; /* bits 32:47 */
+ cmd_buf[dw_offset++] = data;
+ cmd_buf[dw_offset++] = data >> 32;
+
+ return dw_offset;
+}
+
+/* emit_bb_end
+ * populate batch buffer with MI_BATCH_BUFFER_END command
+ * @fd: drm file descriptor
+ * @cmd_buf: batch buffer
+ * @dw_offset: write offset in batch buffer
+*/
+static int emit_bb_end(int fd, uint32_t *cmd_buf, uint32_t dw_offset)
+{
+ cmd_buf[dw_offset++] = MI_BATCH_BUFFER_END;
+ cmd_buf[dw_offset++] = 0;
+
+ return dw_offset;
+}
+
+/* setup_execbuffer
+ * helper for buffer execution
+ * @execbuf - pointer to execbuffer
+ * @exec_object - pointer to exec object2 struct
+ * @ring - ring to be used
+ * @buffer_count - how manu buffers to submit
+ * @batch_length - length of batch buffer
+*/
+static void setup_execbuffer(struct drm_i915_gem_execbuffer2 *execbuf,
+ struct drm_i915_gem_exec_object2 *exec_object,
+ uint32_t ctx_id, int ring, int buffer_count, int batch_length)
+{
+ memset(execbuf, 0, sizeof(*execbuf));
+
+ execbuf->buffers_ptr = (unsigned long)exec_object;
+ execbuf->buffer_count = buffer_count;
+ execbuf->batch_len = batch_length;
+ execbuf->flags = ring;
+ i915_execbuffer2_set_context_id(*execbuf, ctx_id);
+}
+
+#define TABLE_SIZE 0x1000
+#define TILE_SIZE 0x10000
+
+#define TRTT_SEGMENT_SIZE (1ULL << 44)
+#define PPGTT_SIZE (1ULL << 48)
+
+#define NULL_TILE_PATTERN 0xFFFFFFFF
+#define INVALID_TILE_PATTERN 0xFFFFFFFE
+
+struct local_i915_gem_context_trtt_param {
+ uint64_t segment_base_addr;
+ uint64_t l3_table_address;
+ uint32_t invd_tile_val;
+ uint32_t null_tile_val;
+};
+
+/* setup_trtt
+ * Helper function to request KMD to enable TRTT
+ * @fd - drm fd
+ * @ctx_id - id of the context for which TRTT is to be enabled
+ * @l3_table_address - GFX address of the L3 table
+ * @segment_base_addr - offset of the TRTT segment in PPGTT space
+ */
+static void
+setup_trtt(int fd, uint32_t ctx_id, uint64_t l3_table_address,
+ uint64_t segment_base_addr)
+{
+ struct local_i915_gem_context_param ctx_param;
+ struct local_i915_gem_context_trtt_param trtt_param;
+
+ memset(&ctx_param, 0, sizeof(ctx_param));
+
+ trtt_param.null_tile_val = NULL_TILE_PATTERN;
+ trtt_param.invd_tile_val = INVALID_TILE_PATTERN;
+ trtt_param.l3_table_address = l3_table_address;
+ trtt_param.segment_base_addr = segment_base_addr;
+
+ ctx_param.context = ctx_id;
+ ctx_param.size = sizeof(trtt_param);
+ ctx_param.param = LOCAL_CONTEXT_PARAM_TRTT;
+ ctx_param.value = (uint64_t)&trtt_param;
+
+ gem_context_set_param(fd, &ctx_param);
+}
+
+/* bo_alloc_setup
+ * allocate bo and populate exec object
+ * @exec_object2 - pointer to exec object
+ * @bo_sizee - buffer size
+ * @flags - exec flags
+ * @bo_offset - pointer to the current PPGTT offset
+ */
+static void bo_alloc_setup(int fd, struct drm_i915_gem_exec_object2 *exec_object2,
+ uint64_t bo_size, uint64_t flags, uint64_t *bo_offset)
+{
+ memset(exec_object2, 0, sizeof(*exec_object2));
+ exec_object2->handle = gem_create(fd, bo_size);
+ exec_object2->flags = flags;
+
+ if (bo_offset)
+ {
+ exec_object2->offset = *bo_offset;
+ *bo_offset += bo_size;
+ }
+}
+
+/* basic test
+ * This test will create a context, allocate a L3 table page, 2 pages apiece
+ * for L2/L1 tables and couple of data buffers of 64KB in size, matching the
+ * Tile size. The 2 data buffers will be mapped to the 2 ends of TRTT virtual
+ * space. Series of MI_STORE_DWORD_IMM commands will be added in the batch
+ * buffer to first update the TR-TT table entries and then to update the data
+ * buffers using their TR-TT VA, exercising the table programming done
+ * previously.
+ * Invoke CONTEXT_SETPARAM ioctl to request KMD to enable TRTT.
+ * Invoke execbuffer to submit the batch buffer.
+ * Verify value of first DWORD in the 2 data buffer matches the data asked
+ * to be written by the GPU.
+ */
+static void submit_trtt_context(int fd, uint64_t segment_base_addr)
+{
+ enum {
+ L3_TBL,
+ L2_TBL1,
+ L2_TBL2,
+ L1_TBL1,
+ L1_TBL2,
+ DATA1,
+ DATA2,
+ BATCH,
+ NUM_BUFFERS,
+ };
+
+ int ring, len = 0;
+ uint32_t *ptr;
+ struct drm_i915_gem_execbuffer2 execbuf;
+ struct drm_i915_gem_exec_object2 exec_object2[NUM_BUFFERS];
+ uint32_t batch_buffer[BO_SIZE];
+ uint32_t ctx_id, data32;
+ uint64_t address, data64, cur_ppgtt_off, exec_flags;
+ uint64_t first_tile_addr, last_tile_addr;
+
+ first_tile_addr = segment_base_addr;
+ last_tile_addr = first_tile_addr + TRTT_SEGMENT_SIZE - TILE_SIZE;
+
+ if (segment_base_addr == 0) {
+ /* Use the default context for first iteration */
+ ctx_id = 0;
+ cur_ppgtt_off = TRTT_SEGMENT_SIZE;
+ exec_flags = EXEC_OBJECT_SUPPORTS_48B_ADDRESS;
+ } else {
+ ctx_id = gem_context_create(fd);
+ cur_ppgtt_off = 0;
+ exec_flags = 0;
+ }
+
+ /* first allocate Batch buffer BO */
+ bo_alloc_setup(fd, &exec_object2[BATCH], BO_SIZE, exec_flags, NULL);
+
+ /* table BOs and data buffer BOs are written by GPU and are soft pinned */
+ exec_flags |= (EXEC_OBJECT_WRITE | EXEC_OBJECT_PINNED);
+
+ /* Allocate a L3 table BO */
+ bo_alloc_setup(fd, &exec_object2[L3_TBL], TABLE_SIZE, exec_flags, &cur_ppgtt_off);
+
+ /* Allocate two L2 table BOs */
+ bo_alloc_setup(fd, &exec_object2[L2_TBL1], TABLE_SIZE, exec_flags, &cur_ppgtt_off);
+ bo_alloc_setup(fd, &exec_object2[L2_TBL2], TABLE_SIZE, exec_flags, &cur_ppgtt_off);
+
+ /* Allocate two L1 table BOs */
+ bo_alloc_setup(fd, &exec_object2[L1_TBL1], TABLE_SIZE, exec_flags, &cur_ppgtt_off);
+ bo_alloc_setup(fd, &exec_object2[L1_TBL2], TABLE_SIZE, exec_flags, &cur_ppgtt_off);
+
+ /* Align the PPGTT offsets for the 2 data buffers to next 64 KB boundary */
+ cur_ppgtt_off = ALIGN(cur_ppgtt_off, TILE_SIZE);
+
+ /* Allocate two Data buffer BOs */
+ bo_alloc_setup(fd, &exec_object2[DATA1], TILE_SIZE, exec_flags, &cur_ppgtt_off);
+ bo_alloc_setup(fd, &exec_object2[DATA2], TILE_SIZE, exec_flags, &cur_ppgtt_off);
+
+ /* Add commands to update the two L3 table entries to point them to the L2 tables*/
+ address = exec_object2[L3_TBL].offset;
+ data64 = exec_object2[L2_TBL1].offset;
+ len = emit_store_qword(fd, batch_buffer, len, address, data64);
+
+ address = exec_object2[L3_TBL].offset + 511*sizeof(uint64_t);
+ data64 = exec_object2[L2_TBL2].offset;
+ len = emit_store_qword(fd, batch_buffer, len, address, data64);
+
+ /* Add commands to update an entry of 2 L2 tables to point them to the L1 tables*/
+ address = exec_object2[L2_TBL1].offset;
+ data64 = exec_object2[L1_TBL1].offset;
+ len = emit_store_qword(fd, batch_buffer, len, address, data64);
+
+ address = exec_object2[L2_TBL2].offset + 511*sizeof(uint64_t);
+ data64 = exec_object2[L1_TBL2].offset;
+ len = emit_store_qword(fd, batch_buffer, len, address, data64);
+
+ /* Add commands to update an entry of 2 L1 tables to point them to the data buffers*/
+ address = exec_object2[L1_TBL1].offset;
+ data32 = exec_object2[DATA1].offset >> 16;
+ len = emit_store_dword(fd, batch_buffer, len, address, data32);
+
+ address = exec_object2[L1_TBL2].offset + 1023*sizeof(uint32_t);
+ data32 = exec_object2[DATA2].offset >> 16;
+ len = emit_store_dword(fd, batch_buffer, len, address, data32);
+
+ /* Add commands to update the 2 data buffers, using their TRTT VA */
+ data32 = 0x12345678;
+ len = emit_store_dword(fd, batch_buffer, len, first_tile_addr, data32);
+ len = emit_store_dword(fd, batch_buffer, len, last_tile_addr, data32);
+
+ len = emit_bb_end(fd, batch_buffer, len);
+ gem_write(fd, exec_object2[BATCH].handle, 0, batch_buffer, len*4);
+
+ /* Request KMD to setup the TR-TT */
+ setup_trtt(fd, ctx_id, exec_object2[L3_TBL].offset, first_tile_addr);
+
+ ring = I915_EXEC_RENDER;
+ setup_execbuffer(&execbuf, exec_object2, ctx_id, ring, NUM_BUFFERS, len*4);
+
+ /* submit command buffer */
+ gem_execbuf(fd, &execbuf);
+
+ /* read the 2 data buffers to check for the value written by the GPU */
+ ptr = mmap_bo(fd, exec_object2[DATA1].handle, TILE_SIZE);
+ igt_fail_on_f(ptr[0] != data32,
+ "\nCPU read does not match GPU write,\
+ expected: 0x%x, got: 0x%x\n",
+ data32, ptr[0]);
+
+ ptr = mmap_bo(fd, exec_object2[DATA2].handle, TILE_SIZE);
+ igt_fail_on_f(ptr[0] != data32,
+ "\nCPU read does not match GPU write,\
+ expected: 0x%x, got: 0x%x\n",
+ data32, ptr[0]);
+
+ gem_close(fd, exec_object2[L3_TBL].handle);
+ gem_close(fd, exec_object2[L2_TBL1].handle);
+ gem_close(fd, exec_object2[L2_TBL2].handle);
+ gem_close(fd, exec_object2[L1_TBL1].handle);
+ gem_close(fd, exec_object2[L1_TBL2].handle);
+ gem_close(fd, exec_object2[DATA1].handle);
+ gem_close(fd, exec_object2[DATA2].handle);
+ gem_close(fd, exec_object2[BATCH].handle);
+
+ if (ctx_id)
+ gem_context_destroy(fd, ctx_id);
+}
+
+static void gem_basic_trtt_use(void)
+{
+ int fd;
+ uint64_t segment_base_addr;
+
+ fd = drm_open_driver(DRIVER_INTEL);
+ igt_require(uses_full_ppgtt(fd, FULL_48_BIT_PPGTT));
+ igt_require(has_softpin_support(fd));
+ igt_require(has_trtt_support(fd));
+
+ for (segment_base_addr = 0;
+ segment_base_addr < PPGTT_SIZE;
+ segment_base_addr += TRTT_SEGMENT_SIZE)
+ {
+ submit_trtt_context(fd, segment_base_addr);
+ }
+
+ close(fd);
+}
+
+igt_main
+{
+
+ /* test needs 48 PPGTT & Soft Pin support */
+ igt_subtest("basic") {
+ gem_basic_trtt_use();
+ }
+}
+
--
1.9.2
More information about the Intel-gfx
mailing list