[Intel-gfx] [RFC PATCH v3 2/2] drm/i915/gen7: Clear all EU/L3 residual contexts

Akeem G Abodunrin akeem.g.abodunrin at intel.com
Thu Jan 16 17:46:55 UTC 2020


From: Prathap Kumar Valsan <prathap.kumar.valsan at intel.com>

**** NOTE: ****
This series is in active development and is not intended to be merged to
mainline in its current form. The intent of the RFC is simply to outline
the strategy for the mitigation, as a focus for active discussion, and
to openly share progress. There has been only minimal attention paid to
performance thus far, as the focus is on robustness. It is not
anticipated that there will be any measurable performance impact in the
final version.
**** END NOTE ****

On gen7 and gen7.5 devices, there could be leftover data residuals in
EU/L3 from the retiring context. This patch introduces workaround to clear
that residual contexts, by submitting a batch buffer with dedicated HW
context to the GPU with ring allocation for each context switching.

v2: Addressed comments about unused code, code formatting, and include
additional debug code as suggested by Chris Wilson.
v3: Expand debug code for every batch_alloc_items() call...
Current patch series shows significant performance improvements, on par
with current drm-tips.

Signed-off-by: Mika Kuoppala <mika.kuoppala at linux.intel.com>
Signed-off-by: Prathap Kumar Valsan <prathap.kumar.valsan at intel.com>
Signed-off-by: Akeem G Abodunrin <akeem.g.abodunrin at intel.com>
Cc: Chris Wilson <chris.p.wilson at intel.com>
Cc: Balestrieri Francesco <francesco.balestrieri at intel.com>
Cc: Bloomfield Jon <jon.bloomfield at intel.com>
Cc: Dutt Sudeep <sudeep.dutt at intel.com>
---
 drivers/gpu/drm/i915/Makefile                 |   1 +
 drivers/gpu/drm/i915/gt/gen7_renderclear.c    | 524 ++++++++++++++++++
 drivers/gpu/drm/i915/gt/gen7_renderclear.h    |  15 +
 drivers/gpu/drm/i915/gt/intel_gpu_commands.h  |  17 +-
 .../gpu/drm/i915/gt/intel_ring_submission.c   |   3 +-
 drivers/gpu/drm/i915/i915_utils.h             |   5 +
 6 files changed, 561 insertions(+), 4 deletions(-)
 create mode 100644 drivers/gpu/drm/i915/gt/gen7_renderclear.c
 create mode 100644 drivers/gpu/drm/i915/gt/gen7_renderclear.h

diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 3c88d7d8c764..f96bae664a03 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -78,6 +78,7 @@ gt-y += \
 	gt/debugfs_gt.o \
 	gt/debugfs_gt_pm.o \
 	gt/gen6_ppgtt.o \
+	gt/gen7_renderclear.o \
 	gt/gen8_ppgtt.o \
 	gt/intel_breadcrumbs.o \
 	gt/intel_context.o \
diff --git a/drivers/gpu/drm/i915/gt/gen7_renderclear.c b/drivers/gpu/drm/i915/gt/gen7_renderclear.c
new file mode 100644
index 000000000000..5425c2149b30
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/gen7_renderclear.c
@@ -0,0 +1,524 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include "gen7_renderclear.h"
+#include "i915_drv.h"
+#include "i915_utils.h"
+#include "intel_gpu_commands.h"
+
+#define MAX_URB_ENTRIES 64
+#define STATE_SIZE (4 * 1024)
+#define GT3_INLINE_DATA_DELAYS 0x1E00
+#define batch_advance(Y, CS) GEM_BUG_ON((Y)->end != (CS))
+
+/* Media CB Kernel for gen7 devices */
+static const u32 cb7_kernel[][4] = {
+	{ 0x00000001, 0x26020128, 0x00000024, 0x00000000 },
+	{ 0x00000040, 0x20280c21, 0x00000028, 0x00000001 },
+	{ 0x01000010, 0x20000c20, 0x0000002c, 0x00000000 },
+	{ 0x00010220, 0x34001c00, 0x00001400, 0x0000002c },
+	{ 0x00600001, 0x20600061, 0x00000000, 0x00000000 },
+	{ 0x00000008, 0x20601c85, 0x00000e00, 0x0000000c },
+	{ 0x00000005, 0x20601ca5, 0x00000060, 0x00000001 },
+	{ 0x00000008, 0x20641c85, 0x00000e00, 0x0000000d },
+	{ 0x00000005, 0x20641ca5, 0x00000064, 0x00000003 },
+	{ 0x00000041, 0x207424a5, 0x00000064, 0x00000034 },
+	{ 0x00000040, 0x206014a5, 0x00000060, 0x00000074 },
+	{ 0x00000008, 0x20681c85, 0x00000e00, 0x00000008 },
+	{ 0x00000005, 0x20681ca5, 0x00000068, 0x0000000f },
+	{ 0x00000041, 0x20701ca5, 0x00000060, 0x00000010 },
+	{ 0x00000040, 0x206814a5, 0x00000068, 0x00000070 },
+	{ 0x00600001, 0x20a00061, 0x00000000, 0x00000000 },
+	{ 0x00000005, 0x206c1c85, 0x00000e00, 0x00000007 },
+	{ 0x00000041, 0x206c1ca5, 0x0000006c, 0x00000004 },
+	{ 0x00600001, 0x20800021, 0x008d0000, 0x00000000 },
+	{ 0x00000001, 0x20800021, 0x0000006c, 0x00000000 },
+	{ 0x00000001, 0x20840021, 0x00000068, 0x00000000 },
+	{ 0x00000001, 0x20880061, 0x00000000, 0x00000003 },
+	{ 0x00000005, 0x208c0d21, 0x00000086, 0xffffffff },
+	{ 0x05600032, 0x20a01fa1, 0x008d0080, 0x02190001 },
+	{ 0x00000040, 0x20a01ca5, 0x000000a0, 0x00000001 },
+	{ 0x05600032, 0x20a01fa1, 0x008d0080, 0x040a8001 },
+	{ 0x02000040, 0x20281c21, 0x00000028, 0xffffffff },
+	{ 0x00010220, 0x34001c00, 0x00001400, 0xfffffffc },
+	{ 0x00000001, 0x26020128, 0x00000024, 0x00000000 },
+	{ 0x00000001, 0x220000e4, 0x00000000, 0x00000000 },
+	{ 0x00000001, 0x220801ec, 0x00000000, 0x007f007f },
+	{ 0x00600001, 0x20400021, 0x008d0000, 0x00000000 },
+	{ 0x00600001, 0x2fe00021, 0x008d0000, 0x00000000 },
+	{ 0x00200001, 0x20400121, 0x00450020, 0x00000000 },
+	{ 0x00000001, 0x20480061, 0x00000000, 0x000f000f },
+	{ 0x00000005, 0x204c0d21, 0x00000046, 0xffffffef },
+	{ 0x00800001, 0x20600061, 0x00000000, 0x00000000 },
+	{ 0x00800001, 0x20800061, 0x00000000, 0x00000000 },
+	{ 0x00800001, 0x20a00061, 0x00000000, 0x00000000 },
+	{ 0x00800001, 0x20c00061, 0x00000000, 0x00000000 },
+	{ 0x00800001, 0x20e00061, 0x00000000, 0x00000000 },
+	{ 0x00800001, 0x21000061, 0x00000000, 0x00000000 },
+	{ 0x00800001, 0x21200061, 0x00000000, 0x00000000 },
+	{ 0x00800001, 0x21400061, 0x00000000, 0x00000000 },
+	{ 0x05600032, 0x20001fa0, 0x008d0040, 0x120a8000 },
+	{ 0x00000040, 0x20402d21, 0x00000020, 0x00100010 },
+	{ 0x05600032, 0x20001fa0, 0x008d0040, 0x120a8000 },
+	{ 0x02000040, 0x22083d8c, 0x00000208, 0xffffffff },
+	{ 0x00800001, 0xa0000109, 0x00000602, 0x00000000 },
+	{ 0x00000040, 0x22001c84, 0x00000200, 0x00000020 },
+	{ 0x00010220, 0x34001c00, 0x00001400, 0xfffffff8 },
+	{ 0x07600032, 0x20001fa0, 0x008d0fe0, 0x82000010 },
+	{ 0x00000000, 0x00000000, 0x00000000, 0x00000000 },
+	{ 0x00000000, 0x00000000, 0x00000000, 0x00000000 },
+	{ 0x00000000, 0x00000000, 0x00000000, 0x00000000 },
+	{ 0x00000000, 0x00000000, 0x00000000, 0x00000000 },
+	{ 0x00000000, 0x00000000, 0x00000000, 0x00000000 },
+	{ 0x00000000, 0x00000000, 0x00000000, 0x00000000 },
+	{ 0x00000000, 0x00000000, 0x00000000, 0x00000000 },
+	{ 0x00000000, 0x00000000, 0x00000000, 0x00000000 },
+};
+
+/* Media CB Kernel for gen7.5 devices */
+static const u32 cb75_kernel[][4] = {
+	{ 0x00000001, 0x26020128, 0x00000024, 0x00000000 },
+	{ 0x00000040, 0x20280c21, 0x00000028, 0x00000001 },
+	{ 0x01000010, 0x20000c20, 0x0000002c, 0x00000000 },
+	{ 0x00010220, 0x34001c00, 0x00001400, 0x00000160 },
+	{ 0x00600001, 0x20600061, 0x00000000, 0x00000000 },
+	{ 0x00000008, 0x20601c85, 0x00000e00, 0x0000000c },
+	{ 0x00000005, 0x20601ca5, 0x00000060, 0x00000001 },
+	{ 0x00000008, 0x20641c85, 0x00000e00, 0x0000000d },
+	{ 0x00000005, 0x20641ca5, 0x00000064, 0x00000003 },
+	{ 0x00000041, 0x207424a5, 0x00000064, 0x00000034 },
+	{ 0x00000040, 0x206014a5, 0x00000060, 0x00000074 },
+	{ 0x00000008, 0x20681c85, 0x00000e00, 0x00000008 },
+	{ 0x00000005, 0x20681ca5, 0x00000068, 0x0000000f },
+	{ 0x00000041, 0x20701ca5, 0x00000060, 0x00000010 },
+	{ 0x00000040, 0x206814a5, 0x00000068, 0x00000070 },
+	{ 0x00600001, 0x20a00061, 0x00000000, 0x00000000 },
+	{ 0x00000005, 0x206c1c85, 0x00000e00, 0x00000007 },
+	{ 0x00000041, 0x206c1ca5, 0x0000006c, 0x00000004 },
+	{ 0x00600001, 0x20800021, 0x008d0000, 0x00000000 },
+	{ 0x00000001, 0x20800021, 0x0000006c, 0x00000000 },
+	{ 0x00000001, 0x20840021, 0x00000068, 0x00000000 },
+	{ 0x00000001, 0x20880061, 0x00000000, 0x00000003 },
+	{ 0x00000005, 0x208c0d21, 0x00000086, 0xffffffff },
+	{ 0x05600032, 0x20a01fa1, 0x008d0080, 0x02190001 },
+	{ 0x00000040, 0x20a01ca5, 0x000000a0, 0x00000001 },
+	{ 0x05600032, 0x20a01fa1, 0x008d0080, 0x040a8001 },
+	{ 0x02000040, 0x20281c21, 0x00000028, 0xffffffff },
+	{ 0x00010220, 0x34001c00, 0x00001400, 0xffffffe0 },
+	{ 0x00000001, 0x26020128, 0x00000024, 0x00000000 },
+	{ 0x00000001, 0x220000e4, 0x00000000, 0x00000000 },
+	{ 0x00000001, 0x220801ec, 0x00000000, 0x007f007f },
+	{ 0x00600001, 0x20400021, 0x008d0000, 0x00000000 },
+	{ 0x00600001, 0x2fe00021, 0x008d0000, 0x00000000 },
+	{ 0x00200001, 0x20400121, 0x00450020, 0x00000000 },
+	{ 0x00000001, 0x20480061, 0x00000000, 0x000f000f },
+	{ 0x00000005, 0x204c0d21, 0x00000046, 0xffffffef },
+	{ 0x00800001, 0x20600061, 0x00000000, 0x00000000 },
+	{ 0x00800001, 0x20800061, 0x00000000, 0x00000000 },
+	{ 0x00800001, 0x20a00061, 0x00000000, 0x00000000 },
+	{ 0x00800001, 0x20c00061, 0x00000000, 0x00000000 },
+	{ 0x00800001, 0x20e00061, 0x00000000, 0x00000000 },
+	{ 0x00800001, 0x21000061, 0x00000000, 0x00000000 },
+	{ 0x00800001, 0x21200061, 0x00000000, 0x00000000 },
+	{ 0x00800001, 0x21400061, 0x00000000, 0x00000000 },
+	{ 0x05600032, 0x20001fa0, 0x008d0040, 0x120a8000 },
+	{ 0x00000040, 0x20402d21, 0x00000020, 0x00100010 },
+	{ 0x05600032, 0x20001fa0, 0x008d0040, 0x120a8000 },
+	{ 0x02000040, 0x22083d8c, 0x00000208, 0xffffffff },
+	{ 0x00800001, 0xa0000109, 0x00000602, 0x00000000 },
+	{ 0x00000040, 0x22001c84, 0x00000200, 0x00000020 },
+	{ 0x00010220, 0x34001c00, 0x00001400, 0xffffffc0 },
+	{ 0x07600032, 0x20001fa0, 0x008d0fe0, 0x82000010 },
+	{ 0x00000000, 0x00000000, 0x00000000, 0x00000000 },
+	{ 0x00000000, 0x00000000, 0x00000000, 0x00000000 },
+	{ 0x00000000, 0x00000000, 0x00000000, 0x00000000 },
+	{ 0x00000000, 0x00000000, 0x00000000, 0x00000000 },
+	{ 0x00000000, 0x00000000, 0x00000000, 0x00000000 },
+	{ 0x00000000, 0x00000000, 0x00000000, 0x00000000 },
+	{ 0x00000000, 0x00000000, 0x00000000, 0x00000000 },
+	{ 0x00000000, 0x00000000, 0x00000000, 0x00000000 },
+};
+
+struct cb_kernel {
+	const void *data;
+	u32 size;
+};
+
+#define CB_KERNEL(name) { .data = (name), .size = sizeof(name) }
+
+static const struct cb_kernel cb_kernel_gen7 = CB_KERNEL(cb7_kernel);
+static const struct cb_kernel cb_kernel_hsw = CB_KERNEL(cb75_kernel);
+
+struct batch_chunk {
+	struct i915_vma *vma;
+	u32 offset;
+	u32 *start;
+	u32 *end;
+	u32 max_items;
+};
+
+struct batch_vals {
+	u32 max_primitives;
+	u32 max_urb_entries;
+	u32 cmd_size;
+	u32 state_size;
+	u32 state_start;
+	u32 batch_size;
+	u32 surface_height;
+	u32 surface_width;
+	u32 scratch_size;
+	u32 max_size;
+};
+
+static void
+batch_get_defaults(struct drm_i915_private *i915, struct batch_vals *bv)
+{
+	if (IS_HASWELL(i915)) {
+		bv->max_primitives = 280;
+		bv->max_urb_entries = MAX_URB_ENTRIES;
+		bv->surface_height = 16 * 16;
+		bv->surface_width = 32 * 2 * 16;
+	} else {
+		bv->max_primitives = 128;
+		bv->max_urb_entries = MAX_URB_ENTRIES / 2;
+		bv->surface_height = 16 * 8;
+		bv->surface_width = 32 * 16;
+	}
+	bv->cmd_size = bv->max_primitives * 4096;
+	bv->state_size = STATE_SIZE;
+	bv->state_start = bv->cmd_size;
+	bv->batch_size = bv->cmd_size + bv->state_size;
+	bv->scratch_size = bv->surface_height * bv->surface_width;
+	bv->max_size = bv->batch_size + bv->scratch_size;
+}
+
+static void batch_init(struct batch_chunk *bc,
+		       struct i915_vma *vma,
+		       u32 *start, u32 offset, u32 max_bytes)
+{
+	bc->vma = vma;
+	bc->offset = offset;
+	bc->start = start + bc->offset / sizeof(*bc->start);
+	bc->end = bc->start;
+	bc->max_items = max_bytes / sizeof(*bc->start);
+}
+
+static u32 batch_offset(const struct batch_chunk *bc, u32 *cs)
+{
+	return (cs - bc->start) * sizeof(*bc->start) + bc->offset;
+}
+
+static u32 batch_addr(const struct batch_chunk *bc)
+{
+	return bc->vma->node.start;
+}
+
+static void batch_add(struct batch_chunk *bc, const u32 d)
+{
+	GEM_DEBUG_WARN_ON((bc->end - bc->start) >= bc->max_items);
+	*bc->end++ = d;
+}
+
+static u32 *batch_alloc_items(struct batch_chunk *bc, u32 align, u32 items)
+{
+	u32 *map;
+
+	if (align) {
+		u32 *end = ptr_align(bc->end, align);
+
+		memset32(bc->end, 0, end - bc->end);
+		bc->end = end;
+	}
+
+	map = bc->end;
+	bc->end += items;
+
+	return map;
+}
+
+static u32 *batch_alloc_bytes(struct batch_chunk *bc, u32 align, u32 bytes)
+{
+	GEM_BUG_ON(!IS_ALIGNED(bytes, sizeof(*bc->start)));
+	return batch_alloc_items(bc, align, bytes / sizeof(*bc->start));
+}
+
+static u32
+gen7_fill_surface_state(struct batch_chunk *state,
+			const u32 dst_offset,
+			const struct batch_vals *bv)
+{
+	u32 surface_h = bv->surface_height;
+	u32 surface_w = bv->surface_width;
+	u32 *cs = batch_alloc_items(state, 32, 8);
+	u32 offset = batch_offset(state, cs);
+
+#define SURFACE_2D 1
+#define SURFACEFORMAT_B8G8R8A8_UNORM 0x0C0
+#define RENDER_CACHE_READ_WRITE 1
+
+	*cs++ = SURFACE_2D << 29 |
+		(SURFACEFORMAT_B8G8R8A8_UNORM << 18) |
+		(RENDER_CACHE_READ_WRITE << 8);
+
+	*cs++ = batch_addr(state) + dst_offset;
+
+	*cs++ = ((surface_h / 4 - 1) << 16) | (surface_w / 4 - 1);
+	*cs++ = surface_w;
+	*cs++ = 0;
+	*cs++ = 0;
+	*cs++ = 0;
+#define SHADER_CHANNELS(r, g, b, a) \
+	(((r) << 25) | ((g) << 22) | ((b) << 19) | ((a) << 16))
+	*cs++ = SHADER_CHANNELS(4, 5, 6, 7);
+	batch_advance(state, cs);
+
+	return offset;
+}
+
+static u32
+gen7_fill_binding_table(struct batch_chunk *state,
+			const struct batch_vals *bv)
+{
+	u32 *cs = batch_alloc_items(state, 32, 8);
+	u32 offset = batch_offset(state, cs);
+	u32 surface_start;
+
+	surface_start = gen7_fill_surface_state(state, bv->batch_size, bv);
+	*cs++ = surface_start - state->offset;
+	*cs++ = 0;
+	*cs++ = 0;
+	*cs++ = 0;
+	*cs++ = 0;
+	*cs++ = 0;
+	*cs++ = 0;
+	*cs++ = 0;
+	batch_advance(state, cs);
+
+	return offset;
+}
+
+static u32
+gen7_fill_kernel_data(struct batch_chunk *state,
+		      const u32 *data,
+		      const u32 size)
+{
+	return batch_offset(state,
+			    memcpy(batch_alloc_bytes(state, 64, size),
+				   data, size));
+}
+
+static u32
+gen7_fill_interface_descriptor(struct batch_chunk *state,
+			       const struct batch_vals *bv,
+			       const struct cb_kernel *kernel,
+			       unsigned int count)
+{
+	u32 *cs = batch_alloc_items(state, 32, 8 * count);
+	u32 offset = batch_offset(state, cs);
+
+	*cs++ = gen7_fill_kernel_data(state, kernel->data, kernel->size);
+	*cs++ = (1 << 7) | (1 << 13);
+	*cs++ = 0;
+	*cs++ = (gen7_fill_binding_table(state, bv) - state->offset) | 1;
+	*cs++ = 0;
+	*cs++ = 0;
+	*cs++ = 0;
+	*cs++ = 0;
+	/* 1 - 63dummy idds */
+	memset32(cs, 0x00, (count - 1) * 8);
+	batch_advance(state, cs);
+
+	return offset;
+}
+
+static void
+gen7_emit_state_base_address(struct batch_chunk *batch,
+			     u32 surface_state_base)
+{
+	u32 *cs = batch_alloc_items(batch, 0, 12);
+
+	*cs++ = STATE_BASE_ADDRESS | (12 - 2);
+	/* general */
+	*cs++ = batch_addr(batch) | BASE_ADDRESS_MODIFY;
+	/* surface */
+	*cs++ = batch_addr(batch) | surface_state_base | BASE_ADDRESS_MODIFY;
+	/* dynamic */
+	*cs++ = batch_addr(batch) | BASE_ADDRESS_MODIFY;
+	/* indirect */
+	*cs++ = batch_addr(batch) | BASE_ADDRESS_MODIFY;
+	/* instruction */
+	*cs++ = batch_addr(batch) | BASE_ADDRESS_MODIFY;
+
+	/* general/dynamic/indirect/instruction access Bound */
+	*cs++ = 0;
+	*cs++ = BASE_ADDRESS_MODIFY;
+	*cs++ = 0;
+	*cs++ = BASE_ADDRESS_MODIFY;
+	*cs++ = 0;
+	*cs++ = 0;
+	batch_advance(batch, cs);
+}
+
+static void
+gen7_emit_vfe_state(struct batch_chunk *batch,
+		    const struct batch_vals *bv,
+		    u32 urb_size, u32 curbe_size,
+		    u32 mode)
+{
+	u32 urb_entries = bv->max_urb_entries;
+	u32 threads = bv->max_primitives - 1;
+	u32 *cs = batch_alloc_items(batch, 32, 8);
+
+	*cs++ = MEDIA_VFE_STATE | (8 - 2);
+
+	/* scratch buffer */
+	*cs++ = 0;
+
+	/* number of threads & urb entries for GPGPU vs Media Mode */
+	*cs++ = threads << 16 | urb_entries << 8 | mode << 2;
+
+	*cs++ = 0;
+
+	/* urb entry size & curbe size in 256 bits unit */
+	*cs++ = urb_size << 16 | curbe_size;
+
+	/* scoreboard */
+	*cs++ = 0;
+	*cs++ = 0;
+	*cs++ = 0;
+	batch_advance(batch, cs);
+}
+
+static void
+gen7_emit_interface_descriptor_load(struct batch_chunk *batch,
+				    const u32 interface_descriptor,
+				    unsigned int count)
+{
+	u32 *cs = batch_alloc_items(batch, 8, 4);
+
+	*cs++ = MEDIA_INTERFACE_DESCRIPTOR_LOAD | (4 - 2);
+	*cs++ = 0;
+	*cs++ = count * 8 * sizeof(*cs);
+
+	/*
+	 * interface descriptor address - it is relative to the dynamics base
+	 * address
+	 */
+	*cs++ = interface_descriptor;
+	batch_advance(batch, cs);
+}
+
+static void
+gen7_emit_media_object(struct batch_chunk *batch,
+		       unsigned int media_object_index)
+{
+	unsigned int x_offset = (media_object_index % 16) * 64;
+	unsigned int y_offset = (media_object_index / 16) * 16;
+	unsigned int inline_data_size;
+	unsigned int media_batch_size;
+	unsigned int i;
+	u32 *cs;
+
+	inline_data_size = 112 * 8;
+	media_batch_size = inline_data_size + 6;
+
+	cs = batch_alloc_items(batch, 8, media_batch_size);
+
+	*cs++ = MEDIA_OBJECT | (media_batch_size - 2);
+
+	/* interface descriptor offset */
+	*cs++ = 0;
+
+	/* without indirect data */
+	*cs++ = 0;
+	*cs++ = 0;
+
+	/* scoreboard */
+	*cs++ = 0;
+	*cs++ = 0;
+
+	/* inline */
+	*cs++ = (y_offset << 16) | (x_offset);
+	*cs++ = 0;
+	*cs++ = GT3_INLINE_DATA_DELAYS;
+	for (i = 3; i < inline_data_size; i++)
+		*cs++ = 0;
+
+	batch_advance(batch, cs);
+}
+
+static void gen7_emit_pipeline_flush(struct batch_chunk *batch)
+{
+	u32 *cs = batch_alloc_items(batch, 0, 5);
+
+	*cs++ = GFX_OP_PIPE_CONTROL(5);
+	*cs++ = PIPE_CONTROL_STATE_CACHE_INVALIDATE |
+		PIPE_CONTROL_GLOBAL_GTT_IVB;
+	*cs++ = 0;
+	*cs++ = 0;
+	*cs++ = 0;
+	batch_advance(batch, cs);
+}
+
+static void emit_batch(struct i915_vma * const vma,
+		       u32 *start,
+		       const struct batch_vals *bv)
+{
+	struct drm_i915_private *i915 = vma->vm->i915;
+	unsigned int desc_count = 64;
+	const u32 urb_size = 112;
+	struct batch_chunk cmds, state;
+	u32 interface_descriptor;
+	unsigned int i;
+
+	batch_init(&cmds, vma, start, 0, bv->cmd_size);
+	batch_init(&state, vma, start, bv->state_start, bv->state_size);
+
+	interface_descriptor =
+		gen7_fill_interface_descriptor(&state, bv,
+					       IS_HASWELL(i915) ?
+					       &cb_kernel_hsw : &cb_kernel_gen7,
+					       desc_count);
+	gen7_emit_pipeline_flush(&cmds);
+	batch_add(&cmds, PIPELINE_SELECT | PIPELINE_SELECT_MEDIA);
+	batch_add(&cmds, MI_NOOP);
+	gen7_emit_state_base_address(&cmds, interface_descriptor);
+	gen7_emit_pipeline_flush(&cmds);
+
+	gen7_emit_vfe_state(&cmds, bv, urb_size - 1, 0, 0);
+
+	gen7_emit_interface_descriptor_load(&cmds,
+					    interface_descriptor,
+					    desc_count);
+
+	for (i = 0; i < bv->max_primitives; i++)
+		gen7_emit_media_object(&cmds, i);
+
+	batch_add(&cmds, MI_BATCH_BUFFER_END);
+}
+
+int gen7_setup_clear_gpr_bb(struct intel_engine_cs * const engine,
+			    struct i915_vma * const vma)
+{
+	struct batch_vals bv;
+	u32 *batch;
+
+	batch_get_defaults(engine->i915, &bv);
+	if (!vma)
+		return bv.max_size;
+
+	GEM_BUG_ON(vma->obj->base.size < bv.max_size);
+
+	batch = i915_gem_object_pin_map(vma->obj, I915_MAP_WC);
+	if (IS_ERR(batch))
+		return PTR_ERR(batch);
+
+	emit_batch(vma, memset(batch, 0, bv.max_size), &bv);
+
+	i915_gem_object_flush_map(vma->obj);
+	i915_gem_object_unpin_map(vma->obj);
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/i915/gt/gen7_renderclear.h b/drivers/gpu/drm/i915/gt/gen7_renderclear.h
new file mode 100644
index 000000000000..bb100748e2c6
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/gen7_renderclear.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef __GEN7_RENDERCLEAR_H__
+#define __GEN7_RENDERCLEAR_H__
+
+struct intel_engine_cs;
+struct i915_vma;
+
+int gen7_setup_clear_gpr_bb(struct intel_engine_cs * const engine,
+			    struct i915_vma * const vma);
+
+#endif /* __GEN7_RENDERCLEAR_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
index 51b8718513bc..f04214a54f75 100644
--- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
+++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
@@ -292,10 +292,21 @@
 #define MI_STORE_URB_MEM        MI_INSTR(0x2D, 0)
 #define MI_CONDITIONAL_BATCH_BUFFER_END MI_INSTR(0x36, 0)
 
-#define PIPELINE_SELECT                ((0x3<<29)|(0x1<<27)|(0x1<<24)|(0x4<<16))
-#define GFX_OP_3DSTATE_VF_STATISTICS   ((0x3<<29)|(0x1<<27)|(0x0<<24)|(0xB<<16))
-#define MEDIA_VFE_STATE                ((0x3<<29)|(0x2<<27)|(0x0<<24)|(0x0<<16))
+#define STATE_BASE_ADDRESS \
+	((0x3 << 29) | (0x0 << 27) | (0x1 << 24) | (0x1 << 16))
+#define BASE_ADDRESS_MODIFY		REG_BIT(0)
+#define PIPELINE_SELECT \
+	((0x3 << 29) | (0x1 << 27) | (0x1 << 24) | (0x4 << 16))
+#define PIPELINE_SELECT_MEDIA	       REG_BIT(0)
+#define GFX_OP_3DSTATE_VF_STATISTICS \
+	((0x3 << 29) | (0x1 << 27) | (0x0 << 24) | (0xB << 16))
+#define MEDIA_VFE_STATE \
+	((0x3 << 29) | (0x2 << 27) | (0x0 << 24) | (0x0 << 16))
 #define  MEDIA_VFE_STATE_MMIO_ACCESS_MASK (0x18)
+#define MEDIA_INTERFACE_DESCRIPTOR_LOAD \
+	((0x3 << 29) | (0x2 << 27) | (0x0 << 24) | (0x2 << 16))
+#define MEDIA_OBJECT \
+	((0x3 << 29) | (0x2 << 27) | (0x1 << 24) | (0x0 << 16))
 #define GPGPU_OBJECT                   ((0x3<<29)|(0x2<<27)|(0x1<<24)|(0x4<<16))
 #define GPGPU_WALKER                   ((0x3<<29)|(0x2<<27)|(0x1<<24)|(0x5<<16))
 #define GFX_OP_3DSTATE_DX9_CONSTANTF_VS \
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
index 58500032c993..736f00e08648 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
@@ -34,6 +34,7 @@
 #include "gem/i915_gem_context.h"
 
 #include "gen6_ppgtt.h"
+#include "gen7_renderclear.h"
 #include "i915_drv.h"
 #include "i915_trace.h"
 #include "intel_context.h"
@@ -2006,7 +2007,7 @@ static void setup_vecs(struct intel_engine_cs *engine)
 static int gen7_ctx_switch_bb_setup(struct intel_engine_cs * const engine,
 				    struct i915_vma * const vma)
 {
-	return 0;
+	return gen7_setup_clear_gpr_bb(engine, vma);
 }
 
 static int gen7_ctx_switch_bb_init(struct intel_engine_cs *engine)
diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h
index b0ade76bec90..7ac5b3565845 100644
--- a/drivers/gpu/drm/i915/i915_utils.h
+++ b/drivers/gpu/drm/i915/i915_utils.h
@@ -172,6 +172,11 @@ __check_struct_size(size_t base, size_t arr, size_t count, size_t *size)
 	(typeof(ptr))(__v + 1);						\
 })
 
+#define ptr_align(ptr, align) ({					\
+	unsigned long __v = (unsigned long)(ptr);			\
+	(typeof(ptr))round_up(__v, (align));				\
+})
+
 #define page_mask_bits(ptr) ptr_mask_bits(ptr, PAGE_SHIFT)
 #define page_unmask_bits(ptr) ptr_unmask_bits(ptr, PAGE_SHIFT)
 #define page_pack_bits(ptr, bits) ptr_pack_bits(ptr, bits, PAGE_SHIFT)
-- 
2.20.1



More information about the Intel-gfx mailing list