[Intel-gfx] [PATCH] drm/i915/selftests: Add tiled blits selftest
Chris Wilson
chris at chris-wilson.co.uk
Thu Apr 30 00:20:35 UTC 2020
From: Zbigniew Kempczyński <zbigniew.kempczynski at intel.com>
Extend coverage of the blitter client by exercising conversion to and
from tiled sources. In the process we perform spot checks to verify that
the tiling/detiling is being applied correctly, along with position
invariance of the tiling parameters.
Signed-off-by: Zbigniew Kempczyński <zbigniew.kempczynski at intel.com>
Cc: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>
---
.../i915/gem/selftests/i915_gem_client_blt.c | 567 ++++++++++++++++++
drivers/gpu/drm/i915/i915_reg.h | 2 +
2 files changed, 569 insertions(+)
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
index b972be165e85..83023dda897c 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
@@ -7,9 +7,12 @@
#include "gt/intel_engine_user.h"
#include "gt/intel_gt.h"
+#include "gt/intel_gpu_commands.h"
+#include "gem/i915_gem_lmem.h"
#include "selftests/igt_flush_test.h"
#include "selftests/mock_drm.h"
+#include "selftests/i915_random.h"
#include "huge_gem_object.h"
#include "mock_context.h"
@@ -127,10 +130,574 @@ static int igt_client_fill(void *arg)
} while (1);
}
+#define WIDTH 512
+#define HEIGHT 32
+
+struct blit_buffer {
+ struct i915_vma *vma;
+ u32 start_val;
+ u32 tiling;
+};
+
+struct tiled_blits {
+ struct intel_context *ce;
+ struct blit_buffer buffers[3];
+ struct blit_buffer scratch;
+ struct i915_vma *batch;
+ u64 hole;
+ u32 width;
+ u32 height;
+};
+
+static int prepare_blit(const struct tiled_blits *t,
+ struct blit_buffer *dst,
+ struct blit_buffer *src,
+ struct drm_i915_gem_object *batch)
+{
+ const int gen = INTEL_GEN(to_i915(batch->base.dev));
+ bool use_64b_reloc = gen >= 8;
+ u32 src_pitch, dst_pitch;
+ u32 cmd, *cs;
+
+ cs = i915_gem_object_pin_map(batch, I915_MAP_WC);
+ if (IS_ERR(cs))
+ return PTR_ERR(cs);
+
+ *cs++ = MI_LOAD_REGISTER_IMM(1);
+ *cs++ = i915_mmio_reg_offset(BCS_SWCTRL);
+ cmd = (BCS_SRC_Y | BCS_DST_Y) << 16;
+ if (src->tiling == I915_TILING_Y)
+ cmd |= BCS_SRC_Y;
+ if (dst->tiling == I915_TILING_Y)
+ cmd |= BCS_DST_Y;
+ *cs++ = cmd;
+
+ cmd = MI_FLUSH_DW;
+ if (gen >= 8)
+ cmd++;
+ *cs++ = cmd;
+ *cs++ = 0;
+ *cs++ = 0;
+ *cs++ = 0;
+
+ cmd = XY_SRC_COPY_BLT_CMD | BLT_WRITE_RGBA | (8 - 2);
+ if (gen >= 8)
+ cmd += 2;
+
+ src_pitch = t->width * 4;
+ if (src->tiling) {
+ cmd |= XY_SRC_COPY_BLT_SRC_TILED;
+ src_pitch /= 4;
+ }
+
+ dst_pitch = t->width * 4;
+ if (dst->tiling) {
+ cmd |= XY_SRC_COPY_BLT_DST_TILED;
+ dst_pitch /= 4;
+ }
+
+ *cs++ = cmd;
+ *cs++ = BLT_DEPTH_32 | BLT_ROP_SRC_COPY | dst_pitch;
+ *cs++ = 0;
+ *cs++ = t->height << 16 | t->width;
+ *cs++ = lower_32_bits(dst->vma->node.start);
+ if (use_64b_reloc)
+ *cs++ = upper_32_bits(dst->vma->node.start);
+ *cs++ = 0;
+ *cs++ = src_pitch;
+ *cs++ = lower_32_bits(src->vma->node.start);
+ if (use_64b_reloc)
+ *cs++ = upper_32_bits(src->vma->node.start);
+
+ *cs++ = MI_BATCH_BUFFER_END;
+
+ i915_gem_object_flush_map(batch);
+ i915_gem_object_unpin_map(batch);
+
+ return 0;
+}
+
+static void tiled_blits_destroy_buffers(struct tiled_blits *t)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(t->buffers); i++)
+ i915_vma_put(t->buffers[i].vma);
+
+ i915_vma_put(t->scratch.vma);
+ i915_vma_put(t->batch);
+}
+
+static struct i915_vma *
+__create_vma(struct tiled_blits *t, size_t size, bool lmem)
+{
+ struct drm_i915_private *i915 = t->ce->vm->i915;
+ struct drm_i915_gem_object *obj;
+ struct i915_vma *vma;
+
+ if (lmem)
+ obj = i915_gem_object_create_lmem(i915, size, 0);
+ else
+ obj = i915_gem_object_create_shmem(i915, size);
+ if (IS_ERR(obj))
+ return ERR_CAST(obj);
+
+ vma = i915_vma_instance(obj, t->ce->vm, NULL);
+ if (IS_ERR(vma))
+ i915_gem_object_put(obj);
+
+ return vma;
+}
+
+static struct i915_vma *create_vma(struct tiled_blits *t, bool lmem)
+{
+ return __create_vma(t, PAGE_ALIGN(t->width * t->height * 4), lmem);
+}
+
+static int tiled_blits_create_buffers(struct tiled_blits *t,
+ int width, int height,
+ struct rnd_state *prng)
+{
+ struct drm_i915_private *i915 = t->ce->engine->i915;
+ int i;
+
+ t->width = width;
+ t->height = height;
+
+ t->batch = __create_vma(t, PAGE_SIZE, false);
+ if (IS_ERR(t->batch))
+ return PTR_ERR(t->batch);
+
+ t->scratch.vma = create_vma(t, false);
+ if (IS_ERR(t->scratch.vma)) {
+ i915_vma_put(t->batch);
+ return PTR_ERR(t->scratch.vma);
+ }
+
+ for (i = 0; i < ARRAY_SIZE(t->buffers); i++) {
+ struct i915_vma *vma;
+
+ vma = create_vma(t, HAS_LMEM(i915) && i % 2);
+ if (IS_ERR(vma)) {
+ tiled_blits_destroy_buffers(t);
+ return PTR_ERR(vma);
+ }
+
+ t->buffers[i].vma = vma;
+ t->buffers[i].tiling =
+ i915_prandom_u32_max_state(I915_TILING_Y + 1, prng);
+ }
+
+ return 0;
+}
+
+static void fill_scratch(struct tiled_blits *t, u32 *vaddr, u32 val)
+{
+ int i;
+
+ t->scratch.start_val = val;
+ for (i = 0; i < t->width * t->height; i++)
+ vaddr[i] = val++;
+
+ i915_gem_object_flush_map(t->scratch.vma->obj);
+}
+
+static void hexdump(const void *buf, size_t len)
+{
+ const size_t rowsize = 8 * sizeof(u32);
+ const void *prev = NULL;
+ bool skip = false;
+ size_t pos;
+
+ for (pos = 0; pos < len; pos += rowsize) {
+ char line[128];
+
+ if (prev && !memcmp(prev, buf + pos, rowsize)) {
+ if (!skip) {
+ pr_info("*\n");
+ skip = true;
+ }
+ continue;
+ }
+
+ WARN_ON_ONCE(hex_dump_to_buffer(buf + pos, len - pos,
+ rowsize, sizeof(u32),
+ line, sizeof(line),
+ false) >= sizeof(line));
+ pr_info("[%04zx] %s\n", pos, line);
+
+ prev = buf + pos;
+ skip = false;
+ }
+}
+
+static u64 swizzle_bit(unsigned int bit, u64 offset)
+{
+ return (offset & BIT_ULL(bit)) >> (bit - 6);
+}
+
+static u64 tiled_offset(const struct intel_gt *gt,
+ u64 v,
+ unsigned int stride,
+ unsigned int tiling)
+{
+ unsigned int swizzle;
+ u64 x, y;
+
+ if (tiling == I915_TILING_NONE)
+ return v;
+
+ y = div64_u64_rem(v, stride, &x);
+
+ if (tiling == I915_TILING_X) {
+ v = div64_u64_rem(y, 8, &y) * stride * 8;
+ v += y * 512;
+ v += div64_u64_rem(x, 512, &x) << 12;
+ v += x;
+
+ swizzle = gt->ggtt->bit_6_swizzle_x;
+ } else {
+ const unsigned int ytile_span = 16;
+ const unsigned int ytile_height = 512;
+
+ v = div64_u64_rem(y, 32, &y) * stride * 32;
+ v += y * ytile_span;
+ v += div64_u64_rem(x, ytile_span, &x) * ytile_height;
+ v += x;
+
+ swizzle = gt->ggtt->bit_6_swizzle_y;
+ }
+
+ switch (swizzle) {
+ case I915_BIT_6_SWIZZLE_9:
+ v ^= swizzle_bit(9, v);
+ break;
+ case I915_BIT_6_SWIZZLE_9_10:
+ v ^= swizzle_bit(9, v) ^ swizzle_bit(10, v);
+ break;
+ case I915_BIT_6_SWIZZLE_9_11:
+ v ^= swizzle_bit(9, v) ^ swizzle_bit(11, v);
+ break;
+ case I915_BIT_6_SWIZZLE_9_10_11:
+ v ^= swizzle_bit(9, v) ^ swizzle_bit(10, v) ^ swizzle_bit(11, v);
+ break;
+ }
+
+ return v;
+}
+
+static const char *repr_tiling(int tiling)
+{
+ switch (tiling) {
+ case I915_TILING_NONE: return "linear";
+ case I915_TILING_X: return "X";
+ case I915_TILING_Y: return "Y";
+ default: return "unknown";
+ }
+}
+
+static int verify_buffer(const struct tiled_blits *t,
+ struct blit_buffer *buf,
+ struct rnd_state *prng)
+{
+ const u32 *vaddr;
+ int ret = 0;
+ int x, y, p;
+
+ x = i915_prandom_u32_max_state(t->width, prng);
+ y = i915_prandom_u32_max_state(t->height, prng);
+ p = y * t->width + x;
+
+ vaddr = i915_gem_object_pin_map(buf->vma->obj, I915_MAP_WC);
+ if (IS_ERR(vaddr))
+ return PTR_ERR(vaddr);
+
+ if (vaddr[0] != buf->start_val) {
+ ret = -EINVAL;
+ } else {
+ u64 v = tiled_offset(buf->vma->vm->gt,
+ p * 4, t->width * 4,
+ buf->tiling);
+
+ if (vaddr[v / sizeof(*vaddr)] != buf->start_val + p)
+ ret = -EINVAL;
+ }
+ if (ret) {
+ pr_err("Invalid %s tiling detected at (%d, %d), start_val %x\n",
+ repr_tiling(buf->tiling),
+ x, y, buf->start_val);
+ hexdump(vaddr, 4096);
+ }
+
+ i915_gem_object_unpin_map(buf->vma->obj);
+ return ret;
+}
+
+static int move_to_active(struct i915_vma *vma,
+ struct i915_request *rq,
+ unsigned int flags)
+{
+ int err;
+
+ i915_vma_lock(vma);
+ err = i915_request_await_object(rq, vma->obj, false);
+ if (err == 0)
+ err = i915_vma_move_to_active(vma, rq, flags);
+ i915_vma_unlock(vma);
+
+ return err;
+}
+
+static int pin_buffer(struct i915_vma *vma, u64 addr)
+{
+ int err;
+
+ if (drm_mm_node_allocated(&vma->node) && vma->node.start != addr) {
+ err = i915_vma_unbind(vma);
+ if (err)
+ return err;
+ }
+
+ err = i915_vma_pin(vma, 0, 0, PIN_USER | PIN_OFFSET_FIXED | addr);
+ if (err)
+ return err;
+
+ return 0;
+}
+
+static int
+tiled_blit(struct tiled_blits *t,
+ struct blit_buffer *dst, u64 dst_addr,
+ struct blit_buffer *src, u64 src_addr)
+{
+ struct i915_request *rq;
+ int err;
+
+ err = pin_buffer(src->vma, src_addr);
+ if (err) {
+ pr_err("Cannot pin src @ %llx\n", src_addr);
+ return err;
+ }
+
+ err = pin_buffer(dst->vma, dst_addr);
+ if (err) {
+ pr_err("Cannot pin dst @ %llx\n", dst_addr);
+ goto err_src;
+ }
+
+ err = i915_vma_pin(t->batch, 0, 0, PIN_USER | PIN_HIGH);
+ if (err) {
+ pr_err("cannot pin batch\n");
+ goto err_dst;
+ }
+
+ err = prepare_blit(t, dst, src, t->batch->obj);
+ if (err)
+ goto err_bb;
+
+ rq = intel_context_create_request(t->ce);
+ if (IS_ERR(rq)) {
+ err = PTR_ERR(rq);
+ goto err_bb;
+ }
+
+ err = move_to_active(t->batch, rq, 0);
+ if (!err)
+ err = move_to_active(src->vma, rq, 0);
+ if (!err)
+ err = move_to_active(dst->vma, rq, 0);
+ if (!err)
+ err = rq->engine->emit_bb_start(rq,
+ t->batch->node.start,
+ t->batch->node.size,
+ 0);
+ i915_request_get(rq);
+ i915_request_add(rq);
+ if (i915_request_wait(rq, 0, HZ / 2) < 0)
+ err = -ETIME;
+ i915_request_put(rq);
+
+ dst->start_val = src->start_val;
+err_bb:
+ i915_vma_unpin(t->batch);
+err_dst:
+ i915_vma_unpin(dst->vma);
+err_src:
+ i915_vma_unpin(src->vma);
+ return err;
+}
+
+static struct tiled_blits *
+tiled_blits_create(struct intel_engine_cs *engine, struct rnd_state *prng)
+{
+ struct drm_mm_node hole;
+ struct tiled_blits *t;
+ int err;
+
+ t = kzalloc(sizeof(*t), GFP_KERNEL);
+ if (!t)
+ return ERR_PTR(-ENOMEM);
+
+ t->ce = intel_context_create(engine);
+ if (IS_ERR(t->ce)) {
+ err = PTR_ERR(t->ce);
+ goto err_free;
+ }
+
+ mutex_lock(&t->ce->vm->mutex);
+ memset(&hole, 0, sizeof(hole));
+ err = drm_mm_insert_node_in_range(&t->ce->vm->mm,
+ &hole,
+ SZ_16M, 0, I915_COLOR_UNEVICTABLE,
+ 0, U64_MAX,
+ DRM_MM_INSERT_BEST);
+ if (!err)
+ drm_mm_remove_node(&hole);
+ mutex_unlock(&t->ce->vm->mutex);
+ if (err) {
+ err = -ENODEV;
+ goto err_put;
+ }
+
+ t->hole = hole.start;
+ pr_info("Using hole at %llx\n", t->hole);
+
+ err = tiled_blits_create_buffers(t, WIDTH, HEIGHT, prng);
+ if (err)
+ goto err_put;
+
+ return t;
+
+err_put:
+ intel_context_put(t->ce);
+err_free:
+ kfree(t);
+ return ERR_PTR(err);
+}
+
+static void tiled_blits_destroy(struct tiled_blits *t)
+{
+ tiled_blits_destroy_buffers(t);
+
+ intel_context_put(t->ce);
+ kfree(t);
+}
+
+static int tiled_blits_prepare(struct tiled_blits *t,
+ struct rnd_state *prng)
+{
+ u64 offset = PAGE_ALIGN(t->width * t->height * 4);
+ u32 *map;
+ int err;
+ int i;
+
+ map = i915_gem_object_pin_map(t->scratch.vma->obj, I915_MAP_WC);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ /* Use scratch to fill objects */
+ for (i = 0; i < ARRAY_SIZE(t->buffers); i++) {
+ fill_scratch(t, map, prandom_u32_state(prng));
+ GEM_BUG_ON(verify_buffer(t, &t->scratch, prng));
+
+ err = tiled_blit(t,
+ &t->buffers[i], t->hole + offset,
+ &t->scratch, t->hole);
+ if (err == 0)
+ err = verify_buffer(t, &t->buffers[i], prng);
+ if (err) {
+ pr_err("Failed to create buffer %d\n", i);
+ break;
+ }
+ }
+
+ i915_gem_object_unpin_map(t->scratch.vma->obj);
+ return err;
+}
+
+static int tiled_blits_bounce(struct tiled_blits *t, struct rnd_state *prng)
+{
+ u64 offset =
+ round_up(t->width * t->height * 4, 2 * I915_GTT_MIN_ALIGNMENT);
+ int err;
+
+ /* We want to check position invariant tiling across GTT eviction */
+
+ err = tiled_blit(t,
+ &t->buffers[1], t->hole + offset / 2,
+ &t->buffers[0], t->hole + 2 * offset);
+ if (err)
+ return err;
+
+ err = tiled_blit(t,
+ &t->buffers[2], t->hole,
+ &t->buffers[1], t->hole + offset);
+ if (err)
+ return err;
+
+ err = verify_buffer(t, &t->buffers[2], prng);
+ if (err)
+ return err;
+
+ return 0;
+}
+
+static int __igt_client_tiled_blits(struct intel_engine_cs *engine,
+ struct rnd_state *prng)
+{
+ struct tiled_blits *t;
+ int err;
+
+ t = tiled_blits_create(engine, prng);
+ if (IS_ERR(t))
+ return PTR_ERR(t);
+
+ err = tiled_blits_prepare(t, prng);
+ if (err)
+ goto out;
+
+ err = tiled_blits_bounce(t, prng);
+ if (err)
+ goto out;
+
+out:
+ tiled_blits_destroy(t);
+ return err;
+}
+
+static int igt_client_tiled_blits(void *arg)
+{
+ struct drm_i915_private *i915 = arg;
+ I915_RND_STATE(prng);
+ int inst = 0;
+
+ /* Test requires explicit BLT tiling controls */
+ if (INTEL_GEN(i915) < 4)
+ return 0;
+
+ do {
+ struct intel_engine_cs *engine;
+ int err;
+
+ engine = intel_engine_lookup_user(i915,
+ I915_ENGINE_CLASS_COPY,
+ inst++);
+ if (!engine)
+ return 0;
+
+ err = __igt_client_tiled_blits(engine, &prng);
+ if (err == -ENODEV)
+ err = 0;
+ if (err)
+ return err;
+ } while (1);
+}
+
int i915_gem_client_blt_live_selftests(struct drm_i915_private *i915)
{
static const struct i915_subtest tests[] = {
SUBTEST(igt_client_fill),
+ SUBTEST(igt_client_tiled_blits),
};
if (intel_gt_is_wedged(&i915->gt))
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 96d9f8853343..fd9f2904d93c 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -561,6 +561,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
* Registers used only by the command parser
*/
#define BCS_SWCTRL _MMIO(0x22200)
+#define BCS_SRC_Y REG_BIT(0)
+#define BCS_DST_Y REG_BIT(1)
/* There are 16 GPR registers */
#define BCS_GPR(n) _MMIO(0x22600 + (n) * 8)
--
2.20.1
More information about the Intel-gfx
mailing list