Skip to contentSkip to conversation

drm/i915: Add engine scratch register to live_lrc_fixed

PATCH In review Mika Kuoppala 3 participants 9 messages Apr 24, 2020

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

PATCH 1/4 drm/i915: Add engine scratch register to live_lrc_fixed

General purpose registers are per engine and
in a fixed location. Add to live_lrc_fixed.

---
 drivers/gpu/drm/i915/gt/intel_lrc.c    | 12 ++++++++++++
 drivers/gpu/drm/i915/gt/selftest_lrc.c |  5 +++++
 2 files changed, 17 insertions(+)
drivers/gpu/drm/i915/gt/intel_lrc.c +12 -0
index 214ea2a34693..c1f30fe12d5d 100644
@@ -250,6 +250,18 @@ static int lrc_ring_mi_mode(const struct intel_engine_cs *engine)
 		return -1;
 }
 
+static int lrc_ring_gpr0(const struct intel_engine_cs *engine)
+{
+	if (INTEL_GEN(engine->i915) >= 12)
+		return 0x74;
+	else if (INTEL_GEN(engine->i915) >= 9)
+		return 0x68;
+	else if (engine->class == RENDER_CLASS)
+		return 0xd8;
+	else
+		return -1;
+}
+
 static int lrc_ring_wa_bb_per_ctx(const struct intel_engine_cs *engine)
 {
 	if (INTEL_GEN(engine->i915) >= 12)
drivers/gpu/drm/i915/gt/selftest_lrc.c +5 -0
index e964c1402d29..d10c38aec500 100644
@@ -4613,6 +4613,11 @@ static int live_lrc_fixed(void *arg)
 				CTX_TIMESTAMP - 1,
 				"RING_CTX_TIMESTAMP"
 			},
+			{
+				i915_mmio_reg_offset(GEN8_RING_CS_GPR(engine->mmio_base, 0)),
+				lrc_ring_gpr0(engine),
+				"RING_CS_GPR0"
+			},
 			{ },
 		}, *t;
 		u32 *hw;
Signature · 6 lines
2.17.1

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#1 lore raw

PATCH 2/4 drm/i915: Add per ctx batchbuffer wa for timestamp

Restoration of a previous timestamp can collide with updating the timestamp, causing a value corruption.

Combat this issue by using indirect ctx bb to modify the context image during restoring process.

We can preload value into scratch register. From which we then do the actual write with LRR. LRR is faster and thus less error prone as probability of race drops.

v2: tidying (Chris)
v3: lrr for all engines
v4: grp
v5: reg bit

References: HSDES#16010904313
Testcase: igt/i915_selftest/gt_lrc

---
 drivers/gpu/drm/i915/gt/intel_context_types.h |   3 +
 drivers/gpu/drm/i915/gt/intel_gpu_commands.h  |   3 +-
 drivers/gpu/drm/i915/gt/intel_lrc.c           | 160 +++++++++++++++---
 3 files changed, 146 insertions(+), 20 deletions(-)
drivers/gpu/drm/i915/gt/intel_context_types.h +3 -0
index 07cb83a0d017..c7573d565f58 100644
@@ -70,6 +70,9 @@ struct intel_context {
 
 	u32 *lrc_reg_state;
 	u64 lrc_desc;
+
+	u32 ctx_bb_offset;
+
 	u32 tag; /* cookie passed to HW to track this context on submission */
 
 	/* Time on GPU as tracked by the hw. */
drivers/gpu/drm/i915/gt/intel_gpu_commands.h +2 -1
index f04214a54f75..ee10122a511e 100644
@@ -138,7 +138,7 @@
  */
 #define MI_LOAD_REGISTER_IMM(x)	MI_INSTR(0x22, 2*(x)-1)
 /* Gen11+. addr = base + (ctx_restore ? offset & GENMASK(12,2) : offset) */
-#define   MI_LRI_CS_MMIO		(1<<19)
+#define   MI_LRI_LRM_CS_MMIO		REG_BIT(19)
 #define   MI_LRI_FORCE_POSTED		(1<<12)
 #define MI_LOAD_REGISTER_IMM_MAX_REGS (126)
 #define MI_STORE_REGISTER_MEM        MI_INSTR(0x24, 1)
@@ -156,6 +156,7 @@
 #define MI_LOAD_REGISTER_MEM	   MI_INSTR(0x29, 1)
 #define MI_LOAD_REGISTER_MEM_GEN8  MI_INSTR(0x29, 2)
 #define MI_LOAD_REGISTER_REG    MI_INSTR(0x2A, 1)
+#define   MI_LRR_SOURCE_CS_MMIO		REG_BIT(18)
 #define MI_BATCH_BUFFER		MI_INSTR(0x30, 1)
 #define   MI_BATCH_NON_SECURE		(1)
 /* for snb/ivb/vlv this also means "batch in ppgtt" when ppgtt is enabled. */
drivers/gpu/drm/i915/gt/intel_lrc.c +141 -19

225 lines not on this page · raw message

Signature · 6 lines
2.17.1

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#2 lore raw

PATCH 2/4 drm/i915: Add per ctx batchbuffer wa for timestamp

Restoration of a previous timestamp can collide with updating the timestamp, causing a value corruption.

Combat this issue by using indirect ctx bb to modify the context image during restoring process.

We can preload value into scratch register. From which we then do the actual write with LRR. LRR is faster and thus less error prone as probability of race drops.

v2: tidying (Chris)
v3: lrr for all engines
v4: grp
v5: reg bit

References: HSDES#16010904313
Testcase: igt/i915_selftest/gt_lrc

---
 drivers/gpu/drm/i915/gt/intel_context_types.h |   3 +
 drivers/gpu/drm/i915/gt/intel_gpu_commands.h  |   3 +-
 drivers/gpu/drm/i915/gt/intel_lrc.c           | 160 +++++++++++++++---
 3 files changed, 146 insertions(+), 20 deletions(-)
drivers/gpu/drm/i915/gt/intel_context_types.h +3 -0
index 07cb83a0d017..c7573d565f58 100644
@@ -70,6 +70,9 @@ struct intel_context {
 
 	u32 *lrc_reg_state;
 	u64 lrc_desc;
+
+	u32 ctx_bb_offset;
+
 	u32 tag; /* cookie passed to HW to track this context on submission */
 
 	/* Time on GPU as tracked by the hw. */
drivers/gpu/drm/i915/gt/intel_gpu_commands.h +2 -1
index f04214a54f75..ee10122a511e 100644
@@ -138,7 +138,7 @@
  */
 #define MI_LOAD_REGISTER_IMM(x)	MI_INSTR(0x22, 2*(x)-1)
 /* Gen11+. addr = base + (ctx_restore ? offset & GENMASK(12,2) : offset) */
-#define   MI_LRI_CS_MMIO		(1<<19)
+#define   MI_LRI_LRM_CS_MMIO		REG_BIT(19)
 #define   MI_LRI_FORCE_POSTED		(1<<12)
 #define MI_LOAD_REGISTER_IMM_MAX_REGS (126)
 #define MI_STORE_REGISTER_MEM        MI_INSTR(0x24, 1)
@@ -156,6 +156,7 @@
 #define MI_LOAD_REGISTER_MEM	   MI_INSTR(0x29, 1)
 #define MI_LOAD_REGISTER_MEM_GEN8  MI_INSTR(0x29, 2)
 #define MI_LOAD_REGISTER_REG    MI_INSTR(0x2A, 1)
+#define   MI_LRR_SOURCE_CS_MMIO		REG_BIT(18)
 #define MI_BATCH_BUFFER		MI_INSTR(0x30, 1)
 #define   MI_BATCH_NON_SECURE		(1)
 /* for snb/ivb/vlv this also means "batch in ppgtt" when ppgtt is enabled. */
drivers/gpu/drm/i915/gt/intel_lrc.c +141 -19

225 lines not on this page · raw message

Signature · 6 lines
2.17.1

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#3 lore raw

Re: [Intel-gfx] [PATCH 2/4] drm/i915: Add per ctx batchbuffer wa for timestamp

Quoting Mika Kuoppala (2020-04-24 17:54:27)

Quoted 5 lines
        if (wa_ctx->indirect_ctx.size) {
drivers/gpu/drm/i915/gt/intel_lrc.c +3 -1
-               const u32 ggtt_offset = i915_ggtt_offset(wa_ctx->vma);
+               const u32 bb_offset = i915_ggtt_offset(wa_ctx->vma) +
+                       wa_ctx->indirect_ctx.offset;
+               const u32 bb_size = wa_ctx->indirect_ctx.size;

drivers/gpu/drm/i915/gt/intel_lrc.c static void init_common_reg_state(u32 * const regs, · line 4901

Quoted 10 lines
drivers/gpu/drm/i915/gt/intel_lrc.c +1 -8
 
-               GEM_BUG_ON(lrc_ring_indirect_ptr(engine) == -1);
-               regs[lrc_ring_indirect_ptr(engine) + 1] =
-                       (ggtt_offset + wa_ctx->indirect_ctx.offset) |
-                       (wa_ctx->indirect_ctx.size / CACHELINE_BYTES);
-
-               GEM_BUG_ON(lrc_ring_indirect_offset(engine) == -1);
-               regs[lrc_ring_indirect_offset(engine) + 1] =
-                       lrc_ring_indirect_offset_default(engine) << 6;
+               lrc_ring_setup_indirect_ctx(ce, bb_offset, bb_size);

Eek, please teach this to stick to regs and engine.

Otherwise we'll fall into the virtual engine trap. -Chris
_______________________________________________
Intel-gfx mailing list [email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#4 lore raw

PATCH 3/4 drm/i915: Add live selftests for indirect ctx batchbuffers

In reply to Mika Kuoppala

Indirect ctx batchbuffers are a hw feature of which batch can be run, by hardware, during context restoration stage. Driver can setup a batchbuffer and also an offset into the context image. When context image is marshalled from memory to registers, and when the offset from the start of context register state is equal of what driver pre-determined, batch will run. So one can manipulate context restoration process at cacheline granularity, given some limitations, as you need to have rudimentaries in place before you can run a batch.

Add selftest which will write the ring start register to a canary spot. This will test that hardware will run a batchbuffer for the context in question.

v2: request wait fix, naming (Chris)
v3: test order (Chris)

---
 drivers/gpu/drm/i915/gt/selftest_lrc.c | 151 +++++++++++++++++++++++++
 1 file changed, 151 insertions(+)
drivers/gpu/drm/i915/gt/selftest_lrc.c +151 -0
index d10c38aec500..beeb4b7cd161 100644
@@ -5710,6 +5710,156 @@ static int live_lrc_isolation(void *arg)
 	return err;
 }
 
+static int indirect_ctx_submit_req(struct intel_context *ce)
+{
+	struct i915_request *rq;
+	int err = 0;
+
+	rq = intel_context_create_request(ce);
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
+
+	i915_request_get(rq);
+	i915_request_add(rq);
+
+	if (i915_request_wait(rq, 0, HZ / 5) < 0)
+		err = -ETIME;
+
+	i915_request_put(rq);
+
+	return err;
+}
+
+#define CTX_BB_CANARY_OFFSET (3*1024)
+#define CTX_BB_CANARY_INDEX  (CTX_BB_CANARY_OFFSET/sizeof(u32))
+
+static u32 *
+emit_indirect_ctx_bb_canary(struct intel_context *ce, u32 *cs)
+{
+	const u32 ring_start_reg = i915_mmio_reg_offset(RING_START(0));
+	const u32 srm = MI_STORE_REGISTER_MEM_GEN8 |
+		MI_SRM_LRM_GLOBAL_GTT | MI_LRI_LRM_CS_MMIO;
+
+	*cs++ = srm;
+	*cs++ = ring_start_reg;
+	*cs++ = i915_ggtt_offset(ce->state) +
+		ce->ctx_bb_offset + CTX_BB_CANARY_OFFSET;
+	*cs++ = 0;
+
+	return cs;
+}
+
+static void
+indirect_ctx_bb_setup(struct intel_context *ce)
+{
+	u32 *cs = context_indirect_bb(ce);
+
+	cs[CTX_BB_CANARY_INDEX] = 0xdeadf00d;
+
+	setup_indirect_ctx_bb(ce, emit_indirect_ctx_bb_canary);
+}
+
+static bool check_ring_start(struct intel_context *ce)
+{
+	const u32 * const ctx_bb = (void *)(ce->lrc_reg_state) -
+		LRC_STATE_OFFSET + ce->ctx_bb_offset;
+
+	if (ctx_bb[CTX_BB_CANARY_INDEX] == ce->lrc_reg_state[CTX_RING_START])
+		return true;
+
+	pr_err("ring start mismatch: canary 0x%08x vs state 0x%08x\n",
+	       ctx_bb[CTX_BB_CANARY_INDEX],
+	       ce->lrc_reg_state[CTX_RING_START]);
+
+	return false;
+}
+
+static int indirect_ctx_bb_check(struct intel_context *ce)
+{
+	int err;
+
+	err = indirect_ctx_submit_req(ce);
+	if (err)
+		return err;
+
+	if (!check_ring_start(ce))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int __live_lrc_indirect_ctx_bb(struct intel_engine_cs *engine)
+{
+	struct intel_context *a, *b;
+	int err = 0;
+
+	a = intel_context_create(engine);
+	b = intel_context_create(engine);
+
+	err = intel_context_pin(a);
+	if (err)
+		return err;
+
+	err = intel_context_pin(b);
+	if (err) {
+		intel_context_put(a);
+		return err;
+	}
+
+	/* We use the already reserved extra page in context state */
+	if (!a->ctx_bb_offset) {
+		GEM_BUG_ON(b->ctx_bb_offset);
+		GEM_BUG_ON(INTEL_GEN(engine->i915) == 12);
+		goto out;
+	}
+
+	/* In order to test that our per context bb is truly per context,
+	 * and executes at the intended spot on context restoring process,
+	 * make the batch store the ring start value to memory.
+	 * As ring start is restored apriori of starting the indirect ctx bb and
+	 * as it will be different for each context, it fits to this purpose.
+	 */
+	indirect_ctx_bb_setup(a);
+	indirect_ctx_bb_setup(b);
+
+	err = indirect_ctx_bb_check(a);
+	if (err)
+		goto out;
+
+	err = indirect_ctx_bb_check(b);
+out:
+	intel_context_unpin(b);
+	intel_context_put(b);
+
+	intel_context_unpin(a);
+	intel_context_put(a);
+
+	return err;
+}
+
+static int live_lrc_indirect_ctx_bb(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	int err = 0;
+
+	for_each_engine(engine, gt, id) {
+
+		intel_engine_pm_get(engine);
+		err = __live_lrc_indirect_ctx_bb(engine);
+		intel_engine_pm_put(engine);
+
+		if (igt_flush_test(gt->i915))
+			err = -EIO;
+
+		if (err)
+			break;
+	}
+
+	return err;
+}
+
 static void garbage_reset(struct intel_engine_cs *engine,
 			  struct i915_request *rq)
 {
@@ -5945,6 +6095,7 @@ int intel_lrc_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(live_lrc_timestamp),
 		SUBTEST(live_lrc_garbage),
 		SUBTEST(live_pphwsp_runtime),
+		SUBTEST(live_lrc_indirect_ctx_bb),
 	};
 
 	if (!HAS_LOGICAL_RING_CONTEXTS(i915))
Signature · 6 lines
2.17.1

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#5 lore raw

PATCH 4/4 drm/i915: Use indirect ctx bb to mend CMD_BUF_CCTL

In reply to Mika Kuoppala

Use indirect ctx bb to load cmd buffer control value from context image to avoid corruption.

v2: add to lrc layout (Chris)
v3: end to a cacheline (Chris)
v4: add to lrc fixed (Chris)

Testcase: igt/i915_selftest/gt_lrc

---
 drivers/gpu/drm/i915/gt/intel_lrc.c    | 109 ++++++++++++++++++++++++-
 drivers/gpu/drm/i915/gt/selftest_lrc.c |   5 ++
 drivers/gpu/drm/i915/i915_reg.h        |   1 +
 3 files changed, 112 insertions(+), 3 deletions(-)
drivers/gpu/drm/i915/gt/intel_lrc.c +106 -3
index d24fddc2ade0..1b25237d0833 100644
@@ -294,6 +294,14 @@ static int lrc_ring_indirect_offset(const struct intel_engine_cs *engine)
 	return x + 2;
 }
 
+static int lrc_ring_cmd_buf_cctl(const struct intel_engine_cs *engine)
+{
+	if (engine->class != RENDER_CLASS)
+		return -1;
+
+	return 0xb6;
+}
+
 static u32
 lrc_ring_indirect_offset_default(const struct intel_engine_cs *engine)
 {
@@ -608,7 +616,7 @@ static void set_offsets(u32 *regs,
 #define REG16(x) \
 	(((x) >> 9) | BIT(7) | BUILD_BUG_ON_ZERO(x >= 0x10000)), \
 	(((x) >> 2) & 0x7f)
-#define END(x) 0, (x)
+#define END(total_state_size) 0, (total_state_size)
 {
 	const u32 base = engine->mmio_base;
 
@@ -1016,8 +1024,63 @@ static const u8 gen12_rcs_offsets[] = {
 	NOP(6),
 	LRI(1, 0),
 	REG(0x0c8),
+	NOP(3+9+1),
+
+	LRI(51, POSTED),
+	REG16(0x588),
+	REG16(0x588),
+	REG16(0x588),
+	REG16(0x588),
+	REG16(0x588),
+	REG16(0x588),
+	REG(0x028),
+	REG(0x09c),
+	REG(0x0c0),
+	REG(0x178),
+	REG(0x17c),
+	REG16(0x358),
+	REG(0x170),
+	REG(0x150),
+	REG(0x154),
+	REG(0x158),
+	REG16(0x41c),
+	REG16(0x600),
+	REG16(0x604),
+	REG16(0x608),
+	REG16(0x60c),
+	REG16(0x610),
+	REG16(0x614),
+	REG16(0x618),
+	REG16(0x61c),
+	REG16(0x620),
+	REG16(0x624),
+	REG16(0x628),
+	REG16(0x62c),
+	REG16(0x630),
+	REG16(0x634),
+	REG16(0x638),
+	REG16(0x63c),
+	REG16(0x640),
+	REG16(0x644),
+	REG16(0x648),
+	REG16(0x64c),
+	REG16(0x650),
+	REG16(0x654),
+	REG16(0x658),
+	REG16(0x65c),
+	REG16(0x660),
+	REG16(0x664),
+	REG16(0x668),
+	REG16(0x66c),
+	REG16(0x670),
+	REG16(0x674),
+	REG16(0x678),
+	REG16(0x67c),
+	REG(0x068),
+	REG(0x084),
+	NOP(1),
 
-	END(80)
+	END(192)
 };
 
 #undef END
@@ -3249,6 +3312,39 @@ gen12_emit_restore_scratch(struct intel_context *ce, u32 *cs)
 	return cs;
 }
 
+static u32 *
+gen12_emit_cmd_buf_wa(struct intel_context *ce, u32 *cs)
+{
+	const u32 lrc_offset = i915_ggtt_offset(ce->state) +
+		LRC_STATE_OFFSET;
+	const u32 scratch_reg = i915_mmio_reg_offset(GEN8_RING_CS_GPR(0, 0));
+
+	GEM_BUG_ON(lrc_ring_cmd_buf_cctl(ce->engine) == -1);
+
+	*cs++ = MI_LOAD_REGISTER_MEM_GEN8 |
+		MI_SRM_LRM_GLOBAL_GTT | MI_LRI_LRM_CS_MMIO;
+	*cs++ = scratch_reg;
+	*cs++ = lrc_offset + lrc_ring_cmd_buf_cctl(ce->engine) * sizeof(u32);
+	*cs++ = 0;
+
+	*cs++ = MI_LOAD_REGISTER_REG |
+		MI_LRR_SOURCE_CS_MMIO | MI_LRI_LRM_CS_MMIO;
+	*cs++ = scratch_reg;
+	*cs++ = i915_mmio_reg_offset(RING_CMD_BUF_CCTL(0));
+
+	return cs;
+}
+
+static u32 *
+gen12_emit_indirect_ctx_rcs(struct intel_context *ce, u32 *cs)
+{
+	cs = gen12_emit_timestamp_wa(ce, cs);
+	cs = gen12_emit_cmd_buf_wa(ce, cs);
+	cs = gen12_emit_restore_scratch(ce, cs);
+
+	return cs;
+}
+
 static u32 *
 gen12_emit_indirect_ctx_xcs(struct intel_context *ce, u32 *cs)
 {
@@ -3330,9 +3426,16 @@ __execlists_update_reg_state(struct intel_context *ce,
 	}
 
 	if (ce->ctx_bb_offset) {
+		u32 *(*fn)(struct intel_context *ce, u32 *cs);
+
+		if (ce->engine->class == RENDER_CLASS)
+			fn = gen12_emit_indirect_ctx_rcs;
+		else
+			fn = gen12_emit_indirect_ctx_xcs;
+
 		/* Mutually exclusive wrt to global indirect bb */
 		GEM_BUG_ON(engine->wa_ctx.indirect_ctx.size);
-		setup_indirect_ctx_bb(ce, gen12_emit_indirect_ctx_xcs);
+		setup_indirect_ctx_bb(ce, fn);
 	}
 }
 
drivers/gpu/drm/i915/gt/selftest_lrc.c +5 -0
index beeb4b7cd161..db56b6af2bb2 100644
@@ -4618,6 +4618,11 @@ static int live_lrc_fixed(void *arg)
 				lrc_ring_gpr0(engine),
 				"RING_CS_GPR0"
 			},
+			{
+				i915_mmio_reg_offset(RING_CMD_BUF_CCTL(engine->mmio_base)),
+				lrc_ring_cmd_buf_cctl(engine),
+				"RING_CMD_BUF_CCTL"
+			},
 			{ },
 		}, *t;
 		u32 *hw;
drivers/gpu/drm/i915/i915_reg.h +1 -0
index 4a1965467374..0ef30e3cdd3f 100644
@@ -2657,6 +2657,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define RING_DMA_FADD_UDW(base)	_MMIO((base) + 0x60) /* gen8+ */
 #define RING_INSTPM(base)	_MMIO((base) + 0xc0)
 #define RING_MI_MODE(base)	_MMIO((base) + 0x9c)
+#define RING_CMD_BUF_CCTL(base) _MMIO((base) + 0x84)
 #define INSTPS		_MMIO(0x2070) /* 965+ only */
 #define GEN4_INSTDONE1	_MMIO(0x207c) /* 965+ only, aka INSTDONE_2 on SNB */
 #define ACTHD_I965	_MMIO(0x2074)
Signature · 6 lines
2.17.1

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#6 lore raw

PATCH 4/4 drm/i915: Use indirect ctx bb to mend CMD_BUF_CCTL

Use indirect ctx bb to load cmd buffer control value from context image to avoid corruption.

v2: add to lrc layout (Chris)
v3: end to a cacheline (Chris)
v4: add to lrc fixed (Chris)
v5: value in offset+1

Testcase: igt/i915_selftest/gt_lrc

---
 drivers/gpu/drm/i915/gt/intel_lrc.c    | 109 ++++++++++++++++++++++++-
 drivers/gpu/drm/i915/gt/selftest_lrc.c |   5 ++
 drivers/gpu/drm/i915/i915_reg.h        |   1 +
 3 files changed, 112 insertions(+), 3 deletions(-)
drivers/gpu/drm/i915/gt/intel_lrc.c +106 -3
index 66452f8cb3c4..dc37b43e31e8 100644
@@ -294,6 +294,14 @@ static int lrc_ring_indirect_offset(const struct intel_engine_cs *engine)
 	return x + 2;
 }
 
+static int lrc_ring_cmd_buf_cctl(const struct intel_engine_cs *engine)
+{
+	if (engine->class != RENDER_CLASS)
+		return -1;
+
+	return 0xb6;
+}
+
 static u32
 lrc_ring_indirect_offset_default(const struct intel_engine_cs *engine)
 {
@@ -608,7 +616,7 @@ static void set_offsets(u32 *regs,
 #define REG16(x) \
 	(((x) >> 9) | BIT(7) | BUILD_BUG_ON_ZERO(x >= 0x10000)), \
 	(((x) >> 2) & 0x7f)
-#define END(x) 0, (x)
+#define END(total_state_size) 0, (total_state_size)
 {
 	const u32 base = engine->mmio_base;
 
@@ -1016,8 +1024,63 @@ static const u8 gen12_rcs_offsets[] = {
 	NOP(6),
 	LRI(1, 0),
 	REG(0x0c8),
+	NOP(3+9+1),
+
+	LRI(51, POSTED),
+	REG16(0x588),
+	REG16(0x588),
+	REG16(0x588),
+	REG16(0x588),
+	REG16(0x588),
+	REG16(0x588),
+	REG(0x028),
+	REG(0x09c),
+	REG(0x0c0),
+	REG(0x178),
+	REG(0x17c),
+	REG16(0x358),
+	REG(0x170),
+	REG(0x150),
+	REG(0x154),
+	REG(0x158),
+	REG16(0x41c),
+	REG16(0x600),
+	REG16(0x604),
+	REG16(0x608),
+	REG16(0x60c),
+	REG16(0x610),
+	REG16(0x614),
+	REG16(0x618),
+	REG16(0x61c),
+	REG16(0x620),
+	REG16(0x624),
+	REG16(0x628),
+	REG16(0x62c),
+	REG16(0x630),
+	REG16(0x634),
+	REG16(0x638),
+	REG16(0x63c),
+	REG16(0x640),
+	REG16(0x644),
+	REG16(0x648),
+	REG16(0x64c),
+	REG16(0x650),
+	REG16(0x654),
+	REG16(0x658),
+	REG16(0x65c),
+	REG16(0x660),
+	REG16(0x664),
+	REG16(0x668),
+	REG16(0x66c),
+	REG16(0x670),
+	REG16(0x674),
+	REG16(0x678),
+	REG16(0x67c),
+	REG(0x068),
+	REG(0x084),
+	NOP(1),
 
-	END(80)
+	END(192)
 };
 
 #undef END
@@ -3249,6 +3312,39 @@ gen12_emit_restore_scratch(struct intel_context *ce, u32 *cs)
 	return cs;
 }
 
+static u32 *
+gen12_emit_cmd_buf_wa(struct intel_context *ce, u32 *cs)
+{
+	const u32 lrc_offset = i915_ggtt_offset(ce->state) +
+		LRC_STATE_OFFSET;
+	const u32 scratch_reg = i915_mmio_reg_offset(GEN8_RING_CS_GPR(0, 0));
+
+	GEM_BUG_ON(lrc_ring_cmd_buf_cctl(ce->engine) == -1);
+
+	*cs++ = MI_LOAD_REGISTER_MEM_GEN8 |
+		MI_SRM_LRM_GLOBAL_GTT | MI_LRI_LRM_CS_MMIO;
+	*cs++ = scratch_reg;
+	*cs++ = lrc_offset + (lrc_ring_cmd_buf_cctl(ce->engine) + 1)* sizeof(u32);
+	*cs++ = 0;
+
+	*cs++ = MI_LOAD_REGISTER_REG |
+		MI_LRR_SOURCE_CS_MMIO | MI_LRI_LRM_CS_MMIO;
+	*cs++ = scratch_reg;
+	*cs++ = i915_mmio_reg_offset(RING_CMD_BUF_CCTL(0));
+
+	return cs;
+}
+
+static u32 *
+gen12_emit_indirect_ctx_rcs(struct intel_context *ce, u32 *cs)
+{
+	cs = gen12_emit_timestamp_wa(ce, cs);
+	cs = gen12_emit_cmd_buf_wa(ce, cs);
+	cs = gen12_emit_restore_scratch(ce, cs);
+
+	return cs;
+}
+
 static u32 *
 gen12_emit_indirect_ctx_xcs(struct intel_context *ce, u32 *cs)
 {
@@ -3330,9 +3426,16 @@ __execlists_update_reg_state(struct intel_context *ce,
 	}
 
 	if (ce->ctx_bb_offset) {
+		u32 *(*fn)(struct intel_context *ce, u32 *cs);
+
+		if (ce->engine->class == RENDER_CLASS)
+			fn = gen12_emit_indirect_ctx_rcs;
+		else
+			fn = gen12_emit_indirect_ctx_xcs;
+
 		/* Mutually exclusive wrt to global indirect bb */
 		GEM_BUG_ON(engine->wa_ctx.indirect_ctx.size);
-		setup_indirect_ctx_bb(ce, gen12_emit_indirect_ctx_xcs);
+		setup_indirect_ctx_bb(ce, fn);
 	}
 }
 
drivers/gpu/drm/i915/gt/selftest_lrc.c +5 -0
index beeb4b7cd161..db56b6af2bb2 100644
@@ -4618,6 +4618,11 @@ static int live_lrc_fixed(void *arg)
 				lrc_ring_gpr0(engine),
 				"RING_CS_GPR0"
 			},
+			{
+				i915_mmio_reg_offset(RING_CMD_BUF_CCTL(engine->mmio_base)),
+				lrc_ring_cmd_buf_cctl(engine),
+				"RING_CMD_BUF_CCTL"
+			},
 			{ },
 		}, *t;
 		u32 *hw;
drivers/gpu/drm/i915/i915_reg.h +1 -0
index 4a1965467374..0ef30e3cdd3f 100644
@@ -2657,6 +2657,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define RING_DMA_FADD_UDW(base)	_MMIO((base) + 0x60) /* gen8+ */
 #define RING_INSTPM(base)	_MMIO((base) + 0xc0)
 #define RING_MI_MODE(base)	_MMIO((base) + 0x9c)
+#define RING_CMD_BUF_CCTL(base) _MMIO((base) + 0x84)
 #define INSTPS		_MMIO(0x2070) /* 965+ only */
 #define GEN4_INSTDONE1	_MMIO(0x207c) /* 965+ only, aka INSTDONE_2 on SNB */
 #define ACTHD_I965	_MMIO(0x2074)
Signature · 6 lines
2.17.1

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#7 lore raw

[Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for series starting with [1/4] drm/i915: Add engine scratch register to live_lrc_fixed (rev3)

In reply to Mika Kuoppala
== Series Details ==

== Series Details ==

Series: series starting with [1/4] drm/i915: Add engine scratch register to live_lrc_fixed (rev3)
URL : https://patchwork.freedesktop.org/series/76443/
State : warning

== Summary ==

$ dim checkpatch origin/drm-tip
48f89e7502e0 drm/i915: Add engine scratch register to live_lrc_fixed
c24957004e6a drm/i915: Add per ctx batchbuffer wa for timestamp
-:152: CHECK:SPACING: spaces preferred around that '*' (ctx:VxW)
#152: FILE: drivers/gpu/drm/i915/gt/intel_lrc.c:3246:
+	*cs++ = lrc_offset + (lrc_ring_gpr0(ce->engine) + 1)* sizeof(u32);
 	                                                    ^

-:190: CHECK:SPACING: spaces preferred around that '/' (ctx:VxV) #190: FILE: drivers/gpu/drm/i915/gt/intel_lrc.c:3284:
+ I915_GTT_PAGE_SIZE/sizeof(*cs));
^

-:224: CHECK:BRACES: Blank lines aren't necessary before a close brace '}' #224: FILE: drivers/gpu/drm/i915/gt/intel_lrc.c:3330:
+
+ }

total: 0 errors, 0 warnings, 3 checks, 249 lines checked 433caccc67a1 drm/i915: Add live selftests for indirect ctx batchbuffers -:55: CHECK:SPACING: spaces preferred around that '*' (ctx:VxV) #55: FILE: drivers/gpu/drm/i915/gt/selftest_lrc.c:5733:
+#define CTX_BB_CANARY_OFFSET (3*1024)

                                ^

-:56: CHECK:SPACING: spaces preferred around that '/' (ctx:VxV) #56: FILE: drivers/gpu/drm/i915/gt/selftest_lrc.c:5734:
+#define CTX_BB_CANARY_INDEX (CTX_BB_CANARY_OFFSET/sizeof(u32))

                                                   ^

-:170: CHECK:BRACES: Blank lines aren't necessary after an open brace '{' #170: FILE: drivers/gpu/drm/i915/gt/selftest_lrc.c:5848:
+ for_each_engine(engine, gt, id) {
+

total: 0 errors, 0 warnings, 3 checks, 163 lines checked
b9ae36b10e73 drm/i915: Use indirect ctx bb to mend CMD_BUF_CCTL
-:42: ERROR:COMPLEX_MACRO: Macros with complex values should be enclosed in parentheses #42: FILE: drivers/gpu/drm/i915/gt/intel_lrc.c:619:
+#define END(total_state_size) 0, (total_state_size)

-:50: CHECK:SPACING: spaces preferred around that '+' (ctx:VxV) #50: FILE: drivers/gpu/drm/i915/gt/intel_lrc.c:1027:
+ NOP(3+9+1),
^

-:50: CHECK:SPACING: spaces preferred around that '+' (ctx:VxV) #50: FILE: drivers/gpu/drm/i915/gt/intel_lrc.c:1027:
+ NOP(3+9+1),
^

-:127: CHECK:SPACING: spaces preferred around that '*' (ctx:VxW) #127: FILE: drivers/gpu/drm/i915/gt/intel_lrc.c:3327:
+ *cs++ = lrc_offset + (lrc_ring_cmd_buf_cctl(ce->engine) + 1)* sizeof(u32);
^

total: 1 errors, 0 warnings, 3 checks, 160 lines checked

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#8 lore raw

[Intel-gfx] ✗ Fi.CI.BAT: failure for series starting with [1/4] drm/i915: Add engine scratch register to live_lrc_fixed (rev3)

In reply to Mika Kuoppala
== Series Details ==

== Series Details ==

Series: series starting with [1/4] drm/i915: Add engine scratch register to live_lrc_fixed (rev3)
URL : https://patchwork.freedesktop.org/series/76443/
State : failure

== Summary ==

CI Bug Log - changes from CI_DRM_8361 -> Patchwork_17458
====================================================

Summary
-------

**FAILURE**

Serious unknown changes coming with Patchwork_17458 absolutely need to be verified manually.

If you think the reported changes have nothing to do with the changes introduced in Patchwork_17458, please notify your bug team to allow them to document this new failure mode, which will reduce false positives in CI.

External URL: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17458/index.html

Possible new issues
-------------------

Here are the unknown changes that may have been introduced in Patchwork_17458:

### IGT changes ###

#### Possible regressions ####

* igt@i915_selftest@live@gt_lrc:
- fi-icl-guc: [PASS][1] -> [DMESG-FAIL][2]
[1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8361/fi-icl-guc/igt@i915_selftest@live@gt_lrc.html
[2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17458/fi-icl-guc/igt@i915_selftest@live@gt_lrc.html
- fi-icl-y: [PASS][3] -> [DMESG-FAIL][4]
[3]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8361/fi-icl-y/igt@i915_selftest@live@gt_lrc.html
[4]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17458/fi-icl-y/igt@i915_selftest@live@gt_lrc.html
- fi-icl-u2: [PASS][5] -> [DMESG-FAIL][6]
[5]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8361/fi-icl-u2/igt@i915_selftest@live@gt_lrc.html
[6]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17458/fi-icl-u2/igt@i915_selftest@live@gt_lrc.html

#### Suppressed ####

The following results come from untrusted machines, tests, or statuses. They do not affect the overall result.

* igt@i915_selftest@live@gt_lrc:
- {fi-ehl-1}: [PASS][7] -> [DMESG-FAIL][8]
[7]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8361/fi-ehl-1/igt@i915_selftest@live@gt_lrc.html
[8]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17458/fi-ehl-1/igt@i915_selftest@live@gt_lrc.html

{name}: This element is suppressed. This means it is ignored when computing
the status of the difference (SUCCESS, WARNING, or FAILURE).

Participating hosts (49 -> 19)
------------------------------

ERROR: It appears as if the changes made in Patchwork_17458 prevented too many machines from booting.

Missing (30): fi-kbl-soraka fi-bdw-gvtdvm fi-apl-guc fi-skl-lmem fi-skl-6600u fi-cml-u2 fi-bxt-dsi fi-bdw-5557u fi-cml-s fi-bsw-n3050 fi-glk-dsi fi-kbl-7500u fi-ctg-p8600 fi-bsw-nick fi-skl-6700k2 fi-kbl-r fi-skl-guc fi-cfl-8700k fi-hsw-4200u fi-byt-squawks fi-bsw-cyan fi-cfl-guc fi-kbl-guc fi-whl-u fi-kbl-x1275 fi-cfl-8109u fi-kbl-8809g fi-bsw-kefka fi-byt-clapper fi-bdw-samus

Build changes
-------------

* CI: CI-20190529 -> None
* Linux: CI_DRM_8361 -> Patchwork_17458

CI-20190529: 20190529
CI_DRM_8361: b4686529aa525cedc337041c3e2741a93c1a0449 @ git://anongit.freedesktop.org/gfx-ci/linux
IGT_5610: 71fed15724898a8f914666093352a964b70a62fc @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
Patchwork_17458: b9ae36b10e73ad42cf10969652d33a38fb45ba4f @ git://anongit.freedesktop.org/gfx-ci/linux

== Linux commits ==

b9ae36b10e73 drm/i915: Use indirect ctx bb to mend CMD_BUF_CCTL 433caccc67a1 drm/i915: Add live selftests for indirect ctx batchbuffers c24957004e6a drm/i915: Add per ctx batchbuffer wa for timestamp 48f89e7502e0 drm/i915: Add engine scratch register to live_lrc_fixed

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17458/index.html
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx