From f1d8e2bf877d3d322aa7149c43bbc99466014eed Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Fri, 7 Oct 2022 20:53:45 +0100
Subject: drm/i915/perf: remove redundant variable 'taken'

The assignment to variable taken is redundant and so it can be
removed as well as the variable too.

Cleans up clang-scan build warnings:
warning: Although the value stored to 'taken' is used in the enclosing
expression, the value is never actually read from 'taken'
[deadcode.DeadStores]

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221007195345.2749911-1-colin.i.king@gmail.com
---
 drivers/gpu/drm/i915/i915_perf.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

(limited to 'drivers/gpu/drm/i915/i915_perf.c')

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 0defbb43ceea..15816df916c7 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -656,7 +656,6 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 	size_t start_offset = *offset;
 	unsigned long flags;
 	u32 head, tail;
-	u32 taken;
 	int ret = 0;
 
 	if (drm_WARN_ON(&uncore->i915->drm, !stream->enabled))
@@ -692,7 +691,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 
 
 	for (/* none */;
-	     (taken = OA_TAKEN(tail, head));
+	     OA_TAKEN(tail, head);
 	     head = (head + report_size) & mask) {
 		u8 *report = oa_buf_base + head;
 		u32 *report32 = (void *)report;
@@ -950,7 +949,6 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream,
 	size_t start_offset = *offset;
 	unsigned long flags;
 	u32 head, tail;
-	u32 taken;
 	int ret = 0;
 
 	if (drm_WARN_ON(&uncore->i915->drm, !stream->enabled))
@@ -984,7 +982,7 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream,
 
 
 	for (/* none */;
-	     (taken = OA_TAKEN(tail, head));
+	     OA_TAKEN(tail, head);
 	     head = (head + report_size) & mask) {
 		u8 *report = oa_buf_base + head;
 		u32 *report32 = (void *)report;
-- 
cgit v1.2.3


From 682aa4373f156512245d391b15dde798d4594a13 Mon Sep 17 00:00:00 2001
From: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Date: Wed, 26 Oct 2022 22:20:47 +0000
Subject: drm/i915/perf: Fix OA filtering logic for GuC mode

With GuC mode of submission, GuC is in control of defining the context
id field that is part of the OA reports. To filter reports, UMD and KMD
must know what sw context id was chosen by GuC. There is not interface
between KMD and GuC to determine this, so read the upper-dword of
EXECLIST_STATUS to filter/squash OA reports for the specific context.

v2: Explain guc id stealing w.r.t OA use case

Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221026222102.5526-2-umesh.nerlige.ramappa@intel.com
---
 drivers/gpu/drm/i915/gt/intel_lrc.h |   2 +
 drivers/gpu/drm/i915/i915_perf.c    | 144 +++++++++++++++++++++++++++++++-----
 2 files changed, 127 insertions(+), 19 deletions(-)

(limited to 'drivers/gpu/drm/i915/i915_perf.c')

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.h b/drivers/gpu/drm/i915/gt/intel_lrc.h
index a390f0813c8b..7111bae759f3 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.h
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.h
@@ -110,6 +110,8 @@ enum {
 #define XEHP_SW_CTX_ID_WIDTH			16
 #define XEHP_SW_COUNTER_SHIFT			58
 #define XEHP_SW_COUNTER_WIDTH			6
+#define GEN12_GUC_SW_CTX_ID_SHIFT		39
+#define GEN12_GUC_SW_CTX_ID_WIDTH		16
 
 static inline void lrc_runtime_start(struct intel_context *ce)
 {
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 15816df916c7..255335868b6a 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1231,6 +1231,128 @@ retry:
 	return stream->pinned_ctx;
 }
 
+static int
+__store_reg_to_mem(struct i915_request *rq, i915_reg_t reg, u32 ggtt_offset)
+{
+	u32 *cs, cmd;
+
+	cmd = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT;
+	if (GRAPHICS_VER(rq->engine->i915) >= 8)
+		cmd++;
+
+	cs = intel_ring_begin(rq, 4);
+	if (IS_ERR(cs))
+		return PTR_ERR(cs);
+
+	*cs++ = cmd;
+	*cs++ = i915_mmio_reg_offset(reg);
+	*cs++ = ggtt_offset;
+	*cs++ = 0;
+
+	intel_ring_advance(rq, cs);
+
+	return 0;
+}
+
+static int
+__read_reg(struct intel_context *ce, i915_reg_t reg, u32 ggtt_offset)
+{
+	struct i915_request *rq;
+	int err;
+
+	rq = i915_request_create(ce);
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
+
+	i915_request_get(rq);
+
+	err = __store_reg_to_mem(rq, reg, ggtt_offset);
+
+	i915_request_add(rq);
+	if (!err && i915_request_wait(rq, 0, HZ / 2) < 0)
+		err = -ETIME;
+
+	i915_request_put(rq);
+
+	return err;
+}
+
+static int
+gen12_guc_sw_ctx_id(struct intel_context *ce, u32 *ctx_id)
+{
+	struct i915_vma *scratch;
+	u32 *val;
+	int err;
+
+	scratch = __vm_create_scratch_for_read_pinned(&ce->engine->gt->ggtt->vm, 4);
+	if (IS_ERR(scratch))
+		return PTR_ERR(scratch);
+
+	err = i915_vma_sync(scratch);
+	if (err)
+		goto err_scratch;
+
+	err = __read_reg(ce, RING_EXECLIST_STATUS_HI(ce->engine->mmio_base),
+			 i915_ggtt_offset(scratch));
+	if (err)
+		goto err_scratch;
+
+	val = i915_gem_object_pin_map_unlocked(scratch->obj, I915_MAP_WB);
+	if (IS_ERR(val)) {
+		err = PTR_ERR(val);
+		goto err_scratch;
+	}
+
+	*ctx_id = *val;
+	i915_gem_object_unpin_map(scratch->obj);
+
+err_scratch:
+	i915_vma_unpin_and_release(&scratch, 0);
+	return err;
+}
+
+/*
+ * For execlist mode of submission, pick an unused context id
+ * 0 - (NUM_CONTEXT_TAG -1) are used by other contexts
+ * XXX_MAX_CONTEXT_HW_ID is used by idle context
+ *
+ * For GuC mode of submission read context id from the upper dword of the
+ * EXECLIST_STATUS register. Note that we read this value only once and expect
+ * that the value stays fixed for the entire OA use case. There are cases where
+ * GuC KMD implementation may deregister a context to reuse it's context id, but
+ * we prevent that from happening to the OA context by pinning it.
+ */
+static int gen12_get_render_context_id(struct i915_perf_stream *stream)
+{
+	u32 ctx_id, mask;
+	int ret;
+
+	if (intel_engine_uses_guc(stream->engine)) {
+		ret = gen12_guc_sw_ctx_id(stream->pinned_ctx, &ctx_id);
+		if (ret)
+			return ret;
+
+		mask = ((1U << GEN12_GUC_SW_CTX_ID_WIDTH) - 1) <<
+			(GEN12_GUC_SW_CTX_ID_SHIFT - 32);
+	} else if (GRAPHICS_VER_FULL(stream->engine->i915) >= IP_VER(12, 50)) {
+		ctx_id = (XEHP_MAX_CONTEXT_HW_ID - 1) <<
+			(XEHP_SW_CTX_ID_SHIFT - 32);
+
+		mask = ((1U << XEHP_SW_CTX_ID_WIDTH) - 1) <<
+			(XEHP_SW_CTX_ID_SHIFT - 32);
+	} else {
+		ctx_id = (GEN12_MAX_CONTEXT_HW_ID - 1) <<
+			 (GEN11_SW_CTX_ID_SHIFT - 32);
+
+		mask = ((1U << GEN11_SW_CTX_ID_WIDTH) - 1) <<
+			(GEN11_SW_CTX_ID_SHIFT - 32);
+	}
+	stream->specific_ctx_id = ctx_id & mask;
+	stream->specific_ctx_id_mask = mask;
+
+	return 0;
+}
+
 /**
  * oa_get_render_ctx_id - determine and hold ctx hw id
  * @stream: An i915-perf stream opened for OA metrics
@@ -1244,6 +1366,7 @@ retry:
 static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 {
 	struct intel_context *ce;
+	int ret = 0;
 
 	ce = oa_pin_context(stream);
 	if (IS_ERR(ce))
@@ -1290,24 +1413,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 
 	case 11:
 	case 12:
-		if (GRAPHICS_VER_FULL(ce->engine->i915) >= IP_VER(12, 50)) {
-			stream->specific_ctx_id_mask =
-				((1U << XEHP_SW_CTX_ID_WIDTH) - 1) <<
-				(XEHP_SW_CTX_ID_SHIFT - 32);
-			stream->specific_ctx_id =
-				(XEHP_MAX_CONTEXT_HW_ID - 1) <<
-				(XEHP_SW_CTX_ID_SHIFT - 32);
-		} else {
-			stream->specific_ctx_id_mask =
-				((1U << GEN11_SW_CTX_ID_WIDTH) - 1) << (GEN11_SW_CTX_ID_SHIFT - 32);
-			/*
-			 * Pick an unused context id
-			 * 0 - BITS_PER_LONG are used by other contexts
-			 * GEN12_MAX_CONTEXT_HW_ID (0x7ff) is used by idle context
-			 */
-			stream->specific_ctx_id =
-				(GEN12_MAX_CONTEXT_HW_ID - 1) << (GEN11_SW_CTX_ID_SHIFT - 32);
-		}
+		ret = gen12_get_render_context_id(stream);
 		break;
 
 	default:
@@ -1321,7 +1427,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 		stream->specific_ctx_id,
 		stream->specific_ctx_id_mask);
 
-	return 0;
+	return ret;
 }
 
 /**
-- 
cgit v1.2.3


From 81d5f7d91492aa3a362937926cdc094a7dc1e4b7 Mon Sep 17 00:00:00 2001
From: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Date: Wed, 26 Oct 2022 22:20:48 +0000
Subject: drm/i915/perf: Add 32-bit OAG and OAR formats for DG2

Add new OA formats for DG2.

MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18893

v2:
- Update commit title (Ashutosh)
- Coding style fixes (Lionel)
- 64 bit OA formats need UMD changes in GPUvis, drop for now and send in a
  separate series with UMD changes

v3:
- Update commit message to drop 64 bit related description

Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> #1
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221026222102.5526-3-umesh.nerlige.ramappa@intel.com
---
 drivers/gpu/drm/i915/i915_perf.c | 7 +++++++
 include/uapi/drm/i915_drm.h      | 4 ++++
 2 files changed, 11 insertions(+)

(limited to 'drivers/gpu/drm/i915/i915_perf.c')

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 255335868b6a..2b772a6b1cd6 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -320,6 +320,8 @@ static const struct i915_oa_format oa_formats[I915_OA_FORMAT_MAX] = {
 	[I915_OA_FORMAT_A12]		    = { 0, 64 },
 	[I915_OA_FORMAT_A12_B8_C8]	    = { 2, 128 },
 	[I915_OA_FORMAT_A32u40_A4u32_B8_C8] = { 5, 256 },
+	[I915_OAR_FORMAT_A32u40_A4u32_B8_C8]    = { 5, 256 },
+	[I915_OA_FORMAT_A24u40_A14u32_B8_C8]    = { 5, 256 },
 };
 
 #define SAMPLE_OA_REPORT      (1<<0)
@@ -4515,6 +4517,11 @@ static void oa_init_supported_formats(struct i915_perf *perf)
 		oa_format_add(perf, I915_OA_FORMAT_C4_B8);
 		break;
 
+	case INTEL_DG2:
+		oa_format_add(perf, I915_OAR_FORMAT_A32u40_A4u32_B8_C8);
+		oa_format_add(perf, I915_OA_FORMAT_A24u40_A14u32_B8_C8);
+		break;
+
 	default:
 		MISSING_CASE(platform);
 	}
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 08d69e36fb66..b946674c68cc 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -2666,6 +2666,10 @@ enum drm_i915_oa_format {
 	I915_OA_FORMAT_A12_B8_C8,
 	I915_OA_FORMAT_A32u40_A4u32_B8_C8,
 
+	/* DG2 */
+	I915_OAR_FORMAT_A32u40_A4u32_B8_C8,
+	I915_OA_FORMAT_A24u40_A14u32_B8_C8,
+
 	I915_OA_FORMAT_MAX	    /* non-ABI */
 };
 
-- 
cgit v1.2.3


From 2d9da585216bd151779c45bb7dc736ea4e9e0249 Mon Sep 17 00:00:00 2001
From: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Date: Wed, 26 Oct 2022 22:20:49 +0000
Subject: drm/i915/perf: Fix noa wait predication for DG2

Predication for batch buffer commands changed in XEHPSDV.
MI_BATCH_BUFFER_START predicates based on MI_SET_PREDICATE_RESULT
register. The MI_SET_PREDICATE_RESULT register can only be modified
with MI_SET_PREDICATE command. When configured, the MI_SET_PREDICATE
command sets MI_SET_PREDICATE_RESULT based on bit 0 of
MI_PREDICATE_RESULT_2. Use this to configure predication in noa_wait.

Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221026222102.5526-4-umesh.nerlige.ramappa@intel.com
---
 drivers/gpu/drm/i915/gt/intel_engine_regs.h |  1 +
 drivers/gpu/drm/i915/i915_perf.c            | 24 ++++++++++++++++++++----
 2 files changed, 21 insertions(+), 4 deletions(-)

(limited to 'drivers/gpu/drm/i915/i915_perf.c')

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_regs.h b/drivers/gpu/drm/i915/gt/intel_engine_regs.h
index fe1a0d5fd4b1..ee3efd06ee54 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_regs.h
@@ -201,6 +201,7 @@
 #define RING_CONTEXT_STATUS_PTR(base)		_MMIO((base) + 0x3a0)
 #define RING_CTX_TIMESTAMP(base)		_MMIO((base) + 0x3a8) /* gen8+ */
 #define RING_PREDICATE_RESULT(base)		_MMIO((base) + 0x3b8)
+#define MI_PREDICATE_RESULT_2_ENGINE(base)	_MMIO((base) + 0x3bc)
 #define RING_FORCE_TO_NONPRIV(base, i)		_MMIO(((base) + 0x4D0) + (i) * 4)
 #define   RING_FORCE_TO_NONPRIV_DENY		REG_BIT(30)
 #define   RING_FORCE_TO_NONPRIV_ADDRESS_MASK	REG_GENMASK(25, 2)
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 2b772a6b1cd6..e68666b44a72 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -286,6 +286,7 @@ static u32 i915_perf_stream_paranoid = true;
 #define OAREPORT_REASON_CTX_SWITCH     (1<<3)
 #define OAREPORT_REASON_CLK_RATIO      (1<<5)
 
+#define HAS_MI_SET_PREDICATE(i915) (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50))
 
 /* For sysctl proc_dointvec_minmax of i915_oa_max_sample_rate
  *
@@ -1760,6 +1761,9 @@ static int alloc_noa_wait(struct i915_perf_stream *stream)
 		DELTA_TARGET,
 		N_CS_GPR
 	};
+	i915_reg_t mi_predicate_result = HAS_MI_SET_PREDICATE(i915) ?
+					  MI_PREDICATE_RESULT_2_ENGINE(base) :
+					  MI_PREDICATE_RESULT_1(RENDER_RING_BASE);
 
 	bo = i915_gem_object_create_internal(i915, 4096);
 	if (IS_ERR(bo)) {
@@ -1797,7 +1801,7 @@ retry:
 			stream, cs, true /* save */, CS_GPR(i),
 			INTEL_GT_SCRATCH_FIELD_PERF_CS_GPR + 8 * i, 2);
 	cs = save_restore_register(
-		stream, cs, true /* save */, MI_PREDICATE_RESULT_1(RENDER_RING_BASE),
+		stream, cs, true /* save */, mi_predicate_result,
 		INTEL_GT_SCRATCH_FIELD_PERF_PREDICATE_RESULT_1, 1);
 
 	/* First timestamp snapshot location. */
@@ -1851,7 +1855,10 @@ retry:
 	 */
 	*cs++ = MI_LOAD_REGISTER_REG | (3 - 2);
 	*cs++ = i915_mmio_reg_offset(CS_GPR(JUMP_PREDICATE));
-	*cs++ = i915_mmio_reg_offset(MI_PREDICATE_RESULT_1(RENDER_RING_BASE));
+	*cs++ = i915_mmio_reg_offset(mi_predicate_result);
+
+	if (HAS_MI_SET_PREDICATE(i915))
+		*cs++ = MI_SET_PREDICATE | 1;
 
 	/* Restart from the beginning if we had timestamps roll over. */
 	*cs++ = (GRAPHICS_VER(i915) < 8 ?
@@ -1861,6 +1868,9 @@ retry:
 	*cs++ = i915_ggtt_offset(vma) + (ts0 - batch) * 4;
 	*cs++ = 0;
 
+	if (HAS_MI_SET_PREDICATE(i915))
+		*cs++ = MI_SET_PREDICATE;
+
 	/*
 	 * Now add the diff between to previous timestamps and add it to :
 	 *      (((1 * << 64) - 1) - delay_ns)
@@ -1888,7 +1898,10 @@ retry:
 	 */
 	*cs++ = MI_LOAD_REGISTER_REG | (3 - 2);
 	*cs++ = i915_mmio_reg_offset(CS_GPR(JUMP_PREDICATE));
-	*cs++ = i915_mmio_reg_offset(MI_PREDICATE_RESULT_1(RENDER_RING_BASE));
+	*cs++ = i915_mmio_reg_offset(mi_predicate_result);
+
+	if (HAS_MI_SET_PREDICATE(i915))
+		*cs++ = MI_SET_PREDICATE | 1;
 
 	/* Predicate the jump.  */
 	*cs++ = (GRAPHICS_VER(i915) < 8 ?
@@ -1898,13 +1911,16 @@ retry:
 	*cs++ = i915_ggtt_offset(vma) + (jump - batch) * 4;
 	*cs++ = 0;
 
+	if (HAS_MI_SET_PREDICATE(i915))
+		*cs++ = MI_SET_PREDICATE;
+
 	/* Restore registers. */
 	for (i = 0; i < N_CS_GPR; i++)
 		cs = save_restore_register(
 			stream, cs, false /* restore */, CS_GPR(i),
 			INTEL_GT_SCRATCH_FIELD_PERF_CS_GPR + 8 * i, 2);
 	cs = save_restore_register(
-		stream, cs, false /* restore */, MI_PREDICATE_RESULT_1(RENDER_RING_BASE),
+		stream, cs, false /* restore */, mi_predicate_result,
 		INTEL_GT_SCRATCH_FIELD_PERF_PREDICATE_RESULT_1, 1);
 
 	/* And return to the ring. */
-- 
cgit v1.2.3


From a5c3a3cbf0292b1772436e7da0fdda7d818b177d Mon Sep 17 00:00:00 2001
From: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Date: Wed, 26 Oct 2022 22:20:50 +0000
Subject: drm/i915/perf: Determine gen12 oa ctx offset at runtime

Some SKUs of same gen12 platform may have different oactxctrl
offsets. For gen12, determine oactxctrl offsets at runtime.

v2: (Lionel)
- Move MI definitions to intel_gpu_commands.h
- Ensure __find_reg_in_lri does read past context image size

v3: (Ashutosh)
- Drop unnecessary use of double underscores
- fix find_reg_in_lri
- Return error if oa context offset is U32_MAX
- Error out if oa_ctx_ctrl_offset does not find offset

v4: (Ashutosh)
- Warn on odd MI LRI_LEN
- Remove unnecessary check for valid_oactxctrl_offset
- Drop valid_oactxctrl_offset macro

v5: Drop unrelated comment

Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221026222102.5526-5-umesh.nerlige.ramappa@intel.com
---
 drivers/gpu/drm/i915/gt/intel_gpu_commands.h |   4 +
 drivers/gpu/drm/i915/i915_perf.c             | 146 ++++++++++++++++++++++-----
 drivers/gpu/drm/i915/i915_perf_oa_regs.h     |   2 +-
 3 files changed, 127 insertions(+), 25 deletions(-)

(limited to 'drivers/gpu/drm/i915/i915_perf.c')

diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
index d4e9702d3c8e..f50ea92910d9 100644
--- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
+++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
@@ -187,6 +187,10 @@
 #define   MI_BATCH_RESOURCE_STREAMER REG_BIT(10)
 #define   MI_BATCH_PREDICATE         REG_BIT(15) /* HSW+ on RCS only*/
 
+#define MI_OPCODE(x)		(((x) >> 23) & 0x3f)
+#define IS_MI_LRI_CMD(x)	(MI_OPCODE(x) == MI_OPCODE(MI_INSTR(0x22, 0)))
+#define MI_LRI_LEN(x)		(((x) & 0xff) + 1)
+
 /*
  * 3D instructions used by the kernel
  */
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index e68666b44a72..b71b5cf21176 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1356,6 +1356,74 @@ static int gen12_get_render_context_id(struct i915_perf_stream *stream)
 	return 0;
 }
 
+static bool oa_find_reg_in_lri(u32 *state, u32 reg, u32 *offset, u32 end)
+{
+	u32 idx = *offset;
+	u32 len = min(MI_LRI_LEN(state[idx]) + idx, end);
+	bool found = false;
+
+	idx++;
+	for (; idx < len; idx += 2) {
+		if (state[idx] == reg) {
+			found = true;
+			break;
+		}
+	}
+
+	*offset = idx;
+	return found;
+}
+
+static u32 oa_context_image_offset(struct intel_context *ce, u32 reg)
+{
+	u32 offset, len = (ce->engine->context_size - PAGE_SIZE) / 4;
+	u32 *state = ce->lrc_reg_state;
+
+	for (offset = 0; offset < len; ) {
+		if (IS_MI_LRI_CMD(state[offset])) {
+			/*
+			 * We expect reg-value pairs in MI_LRI command, so
+			 * MI_LRI_LEN() should be even, if not, issue a warning.
+			 */
+			drm_WARN_ON(&ce->engine->i915->drm,
+				    MI_LRI_LEN(state[offset]) & 0x1);
+
+			if (oa_find_reg_in_lri(state, reg, &offset, len))
+				break;
+		} else {
+			offset++;
+		}
+	}
+
+	return offset < len ? offset : U32_MAX;
+}
+
+static int set_oa_ctx_ctrl_offset(struct intel_context *ce)
+{
+	i915_reg_t reg = GEN12_OACTXCONTROL(ce->engine->mmio_base);
+	struct i915_perf *perf = &ce->engine->i915->perf;
+	u32 offset = perf->ctx_oactxctrl_offset;
+
+	/* Do this only once. Failure is stored as offset of U32_MAX */
+	if (offset)
+		goto exit;
+
+	offset = oa_context_image_offset(ce, i915_mmio_reg_offset(reg));
+	perf->ctx_oactxctrl_offset = offset;
+
+	drm_dbg(&ce->engine->i915->drm,
+		"%s oa ctx control at 0x%08x dword offset\n",
+		ce->engine->name, offset);
+
+exit:
+	return offset && offset != U32_MAX ? 0 : -ENODEV;
+}
+
+static bool engine_supports_mi_query(struct intel_engine_cs *engine)
+{
+	return engine->class == RENDER_CLASS;
+}
+
 /**
  * oa_get_render_ctx_id - determine and hold ctx hw id
  * @stream: An i915-perf stream opened for OA metrics
@@ -1375,6 +1443,21 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 	if (IS_ERR(ce))
 		return PTR_ERR(ce);
 
+	if (engine_supports_mi_query(stream->engine)) {
+		/*
+		 * We are enabling perf query here. If we don't find the context
+		 * offset here, just return an error.
+		 */
+		ret = set_oa_ctx_ctrl_offset(ce);
+		if (ret) {
+			intel_context_unpin(ce);
+			drm_err(&stream->perf->i915->drm,
+				"Enabling perf query failed for %s\n",
+				stream->engine->name);
+			return ret;
+		}
+	}
+
 	switch (GRAPHICS_VER(ce->engine->i915)) {
 	case 7: {
 		/*
@@ -2406,10 +2489,11 @@ static int gen12_configure_oar_context(struct i915_perf_stream *stream,
 	int err;
 	struct intel_context *ce = stream->pinned_ctx;
 	u32 format = stream->oa_buffer.format;
+	u32 offset = stream->perf->ctx_oactxctrl_offset;
 	struct flex regs_context[] = {
 		{
 			GEN8_OACTXCONTROL,
-			stream->perf->ctx_oactxctrl_offset + 1,
+			offset + 1,
 			active ? GEN8_OA_COUNTER_RESUME : 0,
 		},
 	};
@@ -2434,12 +2518,13 @@ static int gen12_configure_oar_context(struct i915_perf_stream *stream,
 		},
 	};
 
-	/* Modify the context image of pinned context with regs_context*/
+	/* Modify the context image of pinned context with regs_context */
 	err = intel_context_lock_pinned(ce);
 	if (err)
 		return err;
 
-	err = gen8_modify_context(ce, regs_context, ARRAY_SIZE(regs_context));
+	err = gen8_modify_context(ce, regs_context,
+				  ARRAY_SIZE(regs_context));
 	intel_context_unlock_pinned(ce);
 	if (err)
 		return err;
@@ -2564,6 +2649,7 @@ lrc_configure_all_contexts(struct i915_perf_stream *stream,
 			   const struct i915_oa_config *oa_config,
 			   struct i915_active *active)
 {
+	u32 ctx_oactxctrl = stream->perf->ctx_oactxctrl_offset;
 	/* The MMIO offsets for Flex EU registers aren't contiguous */
 	const u32 ctx_flexeu0 = stream->perf->ctx_flexeu0_offset;
 #define ctx_flexeuN(N) (ctx_flexeu0 + 2 * (N) + 1)
@@ -2574,7 +2660,7 @@ lrc_configure_all_contexts(struct i915_perf_stream *stream,
 		},
 		{
 			GEN8_OACTXCONTROL,
-			stream->perf->ctx_oactxctrl_offset + 1,
+			ctx_oactxctrl + 1,
 		},
 		{ EU_PERF_CNTL0, ctx_flexeuN(0) },
 		{ EU_PERF_CNTL1, ctx_flexeuN(1) },
@@ -4543,6 +4629,37 @@ static void oa_init_supported_formats(struct i915_perf *perf)
 	}
 }
 
+static void i915_perf_init_info(struct drm_i915_private *i915)
+{
+	struct i915_perf *perf = &i915->perf;
+
+	switch (GRAPHICS_VER(i915)) {
+	case 8:
+		perf->ctx_oactxctrl_offset = 0x120;
+		perf->ctx_flexeu0_offset = 0x2ce;
+		perf->gen8_valid_ctx_bit = BIT(25);
+		break;
+	case 9:
+		perf->ctx_oactxctrl_offset = 0x128;
+		perf->ctx_flexeu0_offset = 0x3de;
+		perf->gen8_valid_ctx_bit = BIT(16);
+		break;
+	case 11:
+		perf->ctx_oactxctrl_offset = 0x124;
+		perf->ctx_flexeu0_offset = 0x78e;
+		perf->gen8_valid_ctx_bit = BIT(16);
+		break;
+	case 12:
+		/*
+		 * Calculate offset at runtime in oa_pin_context for gen12 and
+		 * cache the value in perf->ctx_oactxctrl_offset.
+		 */
+		break;
+	default:
+		MISSING_CASE(GRAPHICS_VER(i915));
+	}
+}
+
 /**
  * i915_perf_init - initialize i915-perf state on module bind
  * @i915: i915 device instance
@@ -4581,6 +4698,7 @@ void i915_perf_init(struct drm_i915_private *i915)
 		 * execlist mode by default.
 		 */
 		perf->ops.read = gen8_oa_read;
+		i915_perf_init_info(i915);
 
 		if (IS_GRAPHICS_VER(i915, 8, 9)) {
 			perf->ops.is_valid_b_counter_reg =
@@ -4600,18 +4718,6 @@ void i915_perf_init(struct drm_i915_private *i915)
 			perf->ops.enable_metric_set = gen8_enable_metric_set;
 			perf->ops.disable_metric_set = gen8_disable_metric_set;
 			perf->ops.oa_hw_tail_read = gen8_oa_hw_tail_read;
-
-			if (GRAPHICS_VER(i915) == 8) {
-				perf->ctx_oactxctrl_offset = 0x120;
-				perf->ctx_flexeu0_offset = 0x2ce;
-
-				perf->gen8_valid_ctx_bit = BIT(25);
-			} else {
-				perf->ctx_oactxctrl_offset = 0x128;
-				perf->ctx_flexeu0_offset = 0x3de;
-
-				perf->gen8_valid_ctx_bit = BIT(16);
-			}
 		} else if (GRAPHICS_VER(i915) == 11) {
 			perf->ops.is_valid_b_counter_reg =
 				gen7_is_valid_b_counter_addr;
@@ -4625,11 +4731,6 @@ void i915_perf_init(struct drm_i915_private *i915)
 			perf->ops.enable_metric_set = gen8_enable_metric_set;
 			perf->ops.disable_metric_set = gen11_disable_metric_set;
 			perf->ops.oa_hw_tail_read = gen8_oa_hw_tail_read;
-
-			perf->ctx_oactxctrl_offset = 0x124;
-			perf->ctx_flexeu0_offset = 0x78e;
-
-			perf->gen8_valid_ctx_bit = BIT(16);
 		} else if (GRAPHICS_VER(i915) == 12) {
 			perf->ops.is_valid_b_counter_reg =
 				gen12_is_valid_b_counter_addr;
@@ -4643,9 +4744,6 @@ void i915_perf_init(struct drm_i915_private *i915)
 			perf->ops.enable_metric_set = gen12_enable_metric_set;
 			perf->ops.disable_metric_set = gen12_disable_metric_set;
 			perf->ops.oa_hw_tail_read = gen12_oa_hw_tail_read;
-
-			perf->ctx_flexeu0_offset = 0;
-			perf->ctx_oactxctrl_offset = 0x144;
 		}
 	}
 
diff --git a/drivers/gpu/drm/i915/i915_perf_oa_regs.h b/drivers/gpu/drm/i915/i915_perf_oa_regs.h
index f31c9f13a9fc..0ef3562ff4aa 100644
--- a/drivers/gpu/drm/i915/i915_perf_oa_regs.h
+++ b/drivers/gpu/drm/i915/i915_perf_oa_regs.h
@@ -97,7 +97,7 @@
 #define  GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT 1
 #define  GEN12_OAR_OACONTROL_COUNTER_ENABLE       (1 << 0)
 
-#define GEN12_OACTXCONTROL _MMIO(0x2360)
+#define GEN12_OACTXCONTROL(base) _MMIO((base) + 0x360)
 #define GEN12_OAR_OASTATUS _MMIO(0x2968)
 
 /* Gen12 OAG unit */
-- 
cgit v1.2.3


From cceb084905285dcf56912336c9f4f4e7ac334d9f Mon Sep 17 00:00:00 2001
From: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Date: Wed, 26 Oct 2022 22:20:51 +0000
Subject: drm/i915/perf: Enable bytes per clock reporting in OA

XEHPSDV and DG2 provide a way to configure bytes per clock vs commands
per clock reporting. Enable bytes per clock setting on enabling OA.

Bspec: 51762
Bspec: 52201

v2:
- Fix commit msg (Ashutosh)
- Fix checkpatch issues

v3:
- s/commands/bytes/ in code comment and commmit msg

Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221026222102.5526-6-umesh.nerlige.ramappa@intel.com
---
 drivers/gpu/drm/i915/i915_drv.h          |  3 +++
 drivers/gpu/drm/i915/i915_pci.c          |  1 +
 drivers/gpu/drm/i915/i915_perf.c         | 20 ++++++++++++++++++++
 drivers/gpu/drm/i915/i915_perf_oa_regs.h |  4 ++++
 drivers/gpu/drm/i915/intel_device_info.h |  1 +
 5 files changed, 29 insertions(+)

(limited to 'drivers/gpu/drm/i915/i915_perf.c')

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 28ee5ac166db..34f0bcc36671 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -901,6 +901,9 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 #define HAS_RUNTIME_PM(dev_priv) (INTEL_INFO(dev_priv)->has_runtime_pm)
 #define HAS_64BIT_RELOC(dev_priv) (INTEL_INFO(dev_priv)->has_64bit_reloc)
 
+#define HAS_OA_BPC_REPORTING(dev_priv) \
+	(INTEL_INFO(dev_priv)->has_oa_bpc_reporting)
+
 /*
  * Set this flag, when platform requires 64K GTT page sizes or larger for
  * device local memory access.
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 53c6b7cf7879..7b751bf4be21 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -1023,6 +1023,7 @@ static const struct intel_device_info adl_p_info = {
 	.has_logical_ring_contexts = 1, \
 	.has_logical_ring_elsq = 1, \
 	.has_mslice_steering = 1, \
+	.has_oa_bpc_reporting = 1, \
 	.has_rc6 = 1, \
 	.has_reset_engine = 1, \
 	.has_rps = 1, \
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index b71b5cf21176..d11cc949c9be 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -2748,10 +2748,12 @@ static int
 gen12_enable_metric_set(struct i915_perf_stream *stream,
 			struct i915_active *active)
 {
+	struct drm_i915_private *i915 = stream->perf->i915;
 	struct intel_uncore *uncore = stream->uncore;
 	struct i915_oa_config *oa_config = stream->oa_config;
 	bool periodic = stream->periodic;
 	u32 period_exponent = stream->period_exponent;
+	u32 sqcnt1;
 	int ret;
 
 	intel_uncore_write(uncore, GEN12_OAG_OA_DEBUG,
@@ -2770,6 +2772,16 @@ gen12_enable_metric_set(struct i915_perf_stream *stream,
 			    (period_exponent << GEN12_OAG_OAGLBCTXCTRL_TIMER_PERIOD_SHIFT))
 			    : 0);
 
+	/*
+	 * Initialize Super Queue Internal Cnt Register
+	 * Set PMON Enable in order to collect valid metrics.
+	 * Enable byets per clock reporting in OA for XEHPSDV onward.
+	 */
+	sqcnt1 = GEN12_SQCNT1_PMON_ENABLE |
+		 (HAS_OA_BPC_REPORTING(i915) ? GEN12_SQCNT1_OABPC : 0);
+
+	intel_uncore_rmw(uncore, GEN12_SQCNT1, 0, sqcnt1);
+
 	/*
 	 * Update all contexts prior writing the mux configurations as we need
 	 * to make sure all slices/subslices are ON before writing to NOA
@@ -2819,6 +2831,8 @@ static void gen11_disable_metric_set(struct i915_perf_stream *stream)
 static void gen12_disable_metric_set(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
+	struct drm_i915_private *i915 = stream->perf->i915;
+	u32 sqcnt1;
 
 	/* Reset all contexts' slices/subslices configurations. */
 	gen12_configure_all_contexts(stream, NULL, NULL);
@@ -2829,6 +2843,12 @@ static void gen12_disable_metric_set(struct i915_perf_stream *stream)
 
 	/* Make sure we disable noa to save power. */
 	intel_uncore_rmw(uncore, RPM_CONFIG1, GEN10_GT_NOA_ENABLE, 0);
+
+	sqcnt1 = GEN12_SQCNT1_PMON_ENABLE |
+		 (HAS_OA_BPC_REPORTING(i915) ? GEN12_SQCNT1_OABPC : 0);
+
+	/* Reset PMON Enable to save power. */
+	intel_uncore_rmw(uncore, GEN12_SQCNT1, sqcnt1, 0);
 }
 
 static void gen7_oa_enable(struct i915_perf_stream *stream)
diff --git a/drivers/gpu/drm/i915/i915_perf_oa_regs.h b/drivers/gpu/drm/i915/i915_perf_oa_regs.h
index 0ef3562ff4aa..381d94101610 100644
--- a/drivers/gpu/drm/i915/i915_perf_oa_regs.h
+++ b/drivers/gpu/drm/i915/i915_perf_oa_regs.h
@@ -134,4 +134,8 @@
 #define GDT_CHICKEN_BITS    _MMIO(0x9840)
 #define   GT_NOA_ENABLE	    0x00000080
 
+#define GEN12_SQCNT1				_MMIO(0x8718)
+#define   GEN12_SQCNT1_PMON_ENABLE		REG_BIT(30)
+#define   GEN12_SQCNT1_OABPC			REG_BIT(29)
+
 #endif /* __INTEL_PERF_OA_REGS__ */
diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
index da833267a782..d11546d87fe7 100644
--- a/drivers/gpu/drm/i915/intel_device_info.h
+++ b/drivers/gpu/drm/i915/intel_device_info.h
@@ -163,6 +163,7 @@ enum intel_ppgtt_type {
 	func(has_logical_ring_elsq); \
 	func(has_media_ratio_mode); \
 	func(has_mslice_steering); \
+	func(has_oa_bpc_reporting); \
 	func(has_one_eu_per_fuse_bit); \
 	func(has_pxp); \
 	func(has_rc6); \
-- 
cgit v1.2.3


From a5a6d92f77ffde188ce3aa4ccec21fac5b00c6e8 Mon Sep 17 00:00:00 2001
From: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Date: Wed, 26 Oct 2022 22:20:52 +0000
Subject: drm/i915/perf: Simply use stream->ctx

Earlier code used exclusive_stream to check for user passed context.
Simplify this by accessing stream->ctx.

Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221026222102.5526-7-umesh.nerlige.ramappa@intel.com
---
 drivers/gpu/drm/i915/i915_perf.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/gpu/drm/i915/i915_perf.c')

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index d11cc949c9be..75d320b2c1f8 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -776,7 +776,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 		 * switches since it's not-uncommon for periodic samples to
 		 * identify a switch before any 'context switch' report.
 		 */
-		if (!stream->perf->exclusive_stream->ctx ||
+		if (!stream->ctx ||
 		    stream->specific_ctx_id == ctx_id ||
 		    stream->oa_buffer.last_ctx_id == stream->specific_ctx_id ||
 		    reason & OAREPORT_REASON_CTX_SWITCH) {
@@ -785,7 +785,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 			 * While filtering for a single context we avoid
 			 * leaking the IDs of other contexts.
 			 */
-			if (stream->perf->exclusive_stream->ctx &&
+			if (stream->ctx &&
 			    stream->specific_ctx_id != ctx_id) {
 				report32[2] = INVALID_CTX_ID;
 			}
-- 
cgit v1.2.3


From 9677a9f3b1ad3537bc945e7c7e54778632ee2d0f Mon Sep 17 00:00:00 2001
From: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Date: Wed, 26 Oct 2022 22:20:53 +0000
Subject: drm/i915/perf: Move gt-specific data from i915->perf to gt->perf

Make perf part of gt as the OAG buffer is specific to a gt. The refactor
eventually simplifies programming the right OA buffer and the right HW
registers when supporting multiple gts.

Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221026222102.5526-8-umesh.nerlige.ramappa@intel.com
---
 drivers/gpu/drm/i915/gt/intel_gt_types.h   |  3 ++
 drivers/gpu/drm/i915/gt/intel_sseu.c       |  4 +-
 drivers/gpu/drm/i915/i915_perf.c           | 75 ++++++++++++++++++------------
 drivers/gpu/drm/i915/i915_perf_types.h     | 39 ++++++++--------
 drivers/gpu/drm/i915/selftests/i915_perf.c | 16 +++++--
 5 files changed, 80 insertions(+), 57 deletions(-)

(limited to 'drivers/gpu/drm/i915/i915_perf.c')

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index 64aa2ba624fc..6f686a4244f0 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
@@ -20,6 +20,7 @@
 #include "intel_gsc.h"
 
 #include "i915_vma.h"
+#include "i915_perf_types.h"
 #include "intel_engine_types.h"
 #include "intel_gt_buffer_pool_types.h"
 #include "intel_hwconfig.h"
@@ -289,6 +290,8 @@ struct intel_gt {
 	/* sysfs defaults per gt */
 	struct gt_defaults defaults;
 	struct kobject *sysfs_defaults;
+
+	struct i915_perf_gt perf;
 };
 
 struct intel_gt_definition {
diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.c b/drivers/gpu/drm/i915/gt/intel_sseu.c
index 66f21c735d54..6c6198a257ac 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.c
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.c
@@ -677,8 +677,8 @@ u32 intel_sseu_make_rpcs(struct intel_gt *gt,
 	 * If i915/perf is active, we want a stable powergating configuration
 	 * on the system. Use the configuration pinned by i915/perf.
 	 */
-	if (i915->perf.exclusive_stream)
-		req_sseu = &i915->perf.sseu;
+	if (gt->perf.exclusive_stream)
+		req_sseu = &gt->perf.sseu;
 
 	slices = hweight8(req_sseu->slice_mask);
 	subslices = hweight8(req_sseu->subslice_mask);
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 75d320b2c1f8..83c5dc043261 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1565,8 +1565,9 @@ free_noa_wait(struct i915_perf_stream *stream)
 static void i915_oa_stream_destroy(struct i915_perf_stream *stream)
 {
 	struct i915_perf *perf = stream->perf;
+	struct intel_gt *gt = stream->engine->gt;
 
-	if (WARN_ON(stream != perf->exclusive_stream))
+	if (WARN_ON(stream != gt->perf.exclusive_stream))
 		return;
 
 	/*
@@ -1575,7 +1576,7 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream)
 	 *
 	 * See i915_oa_init_reg_state() and lrc_configure_all_contexts()
 	 */
-	WRITE_ONCE(perf->exclusive_stream, NULL);
+	WRITE_ONCE(gt->perf.exclusive_stream, NULL);
 	perf->ops.disable_metric_set(stream);
 
 	free_oa_buffer(stream);
@@ -2566,10 +2567,11 @@ oa_configure_all_contexts(struct i915_perf_stream *stream,
 {
 	struct drm_i915_private *i915 = stream->perf->i915;
 	struct intel_engine_cs *engine;
+	struct intel_gt *gt = stream->engine->gt;
 	struct i915_gem_context *ctx, *cn;
 	int err;
 
-	lockdep_assert_held(&stream->perf->lock);
+	lockdep_assert_held(&gt->perf.lock);
 
 	/*
 	 * The OA register config is setup through the context image. This image
@@ -3090,6 +3092,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 {
 	struct drm_i915_private *i915 = stream->perf->i915;
 	struct i915_perf *perf = stream->perf;
+	struct intel_gt *gt;
 	int format_size;
 	int ret;
 
@@ -3098,6 +3101,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 			"OA engine not specified\n");
 		return -EINVAL;
 	}
+	gt = props->engine->gt;
 
 	/*
 	 * If the sysfs metrics/ directory wasn't registered for some
@@ -3128,7 +3132,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	 * counter reports and marshal to the appropriate client
 	 * we currently only allow exclusive access
 	 */
-	if (perf->exclusive_stream) {
+	if (gt->perf.exclusive_stream) {
 		drm_dbg(&stream->perf->i915->drm,
 			"OA unit already in use\n");
 		return -EBUSY;
@@ -3208,8 +3212,8 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 
 	stream->ops = &i915_oa_stream_ops;
 
-	perf->sseu = props->sseu;
-	WRITE_ONCE(perf->exclusive_stream, stream);
+	stream->engine->gt->perf.sseu = props->sseu;
+	WRITE_ONCE(gt->perf.exclusive_stream, stream);
 
 	ret = i915_perf_stream_enable_sync(stream);
 	if (ret) {
@@ -3231,7 +3235,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	return 0;
 
 err_enable:
-	WRITE_ONCE(perf->exclusive_stream, NULL);
+	WRITE_ONCE(gt->perf.exclusive_stream, NULL);
 	perf->ops.disable_metric_set(stream);
 
 	free_oa_buffer(stream);
@@ -3261,7 +3265,7 @@ void i915_oa_init_reg_state(const struct intel_context *ce,
 		return;
 
 	/* perf.exclusive_stream serialised by lrc_configure_all_contexts() */
-	stream = READ_ONCE(engine->i915->perf.exclusive_stream);
+	stream = READ_ONCE(engine->gt->perf.exclusive_stream);
 	if (stream && GRAPHICS_VER(stream->perf->i915) < 12)
 		gen8_update_reg_state_unlocked(ce, stream);
 }
@@ -3290,7 +3294,7 @@ static ssize_t i915_perf_read(struct file *file,
 			      loff_t *ppos)
 {
 	struct i915_perf_stream *stream = file->private_data;
-	struct i915_perf *perf = stream->perf;
+	struct intel_gt *gt = stream->engine->gt;
 	size_t offset = 0;
 	int ret;
 
@@ -3314,14 +3318,14 @@ static ssize_t i915_perf_read(struct file *file,
 			if (ret)
 				return ret;
 
-			mutex_lock(&perf->lock);
+			mutex_lock(&gt->perf.lock);
 			ret = stream->ops->read(stream, buf, count, &offset);
-			mutex_unlock(&perf->lock);
+			mutex_unlock(&gt->perf.lock);
 		} while (!offset && !ret);
 	} else {
-		mutex_lock(&perf->lock);
+		mutex_lock(&gt->perf.lock);
 		ret = stream->ops->read(stream, buf, count, &offset);
-		mutex_unlock(&perf->lock);
+		mutex_unlock(&gt->perf.lock);
 	}
 
 	/* We allow the poll checking to sometimes report false positive EPOLLIN
@@ -3368,7 +3372,7 @@ static enum hrtimer_restart oa_poll_check_timer_cb(struct hrtimer *hrtimer)
  * &i915_perf_stream_ops->poll_wait to call poll_wait() with a wait queue that
  * will be woken for new stream data.
  *
- * Note: The &perf->lock mutex has been taken to serialize
+ * Note: The &gt->perf.lock mutex has been taken to serialize
  * with any non-file-operation driver hooks.
  *
  * Returns: any poll events that are ready without sleeping
@@ -3409,12 +3413,12 @@ static __poll_t i915_perf_poll_locked(struct i915_perf_stream *stream,
 static __poll_t i915_perf_poll(struct file *file, poll_table *wait)
 {
 	struct i915_perf_stream *stream = file->private_data;
-	struct i915_perf *perf = stream->perf;
+	struct intel_gt *gt = stream->engine->gt;
 	__poll_t ret;
 
-	mutex_lock(&perf->lock);
+	mutex_lock(&gt->perf.lock);
 	ret = i915_perf_poll_locked(stream, file, wait);
-	mutex_unlock(&perf->lock);
+	mutex_unlock(&gt->perf.lock);
 
 	return ret;
 }
@@ -3513,7 +3517,7 @@ static long i915_perf_config_locked(struct i915_perf_stream *stream,
  * @cmd: the ioctl request
  * @arg: the ioctl data
  *
- * Note: The &perf->lock mutex has been taken to serialize
+ * Note: The &gt->perf.lock mutex has been taken to serialize
  * with any non-file-operation driver hooks.
  *
  * Returns: zero on success or a negative error code. Returns -EINVAL for
@@ -3553,12 +3557,12 @@ static long i915_perf_ioctl(struct file *file,
 			    unsigned long arg)
 {
 	struct i915_perf_stream *stream = file->private_data;
-	struct i915_perf *perf = stream->perf;
+	struct intel_gt *gt = stream->engine->gt;
 	long ret;
 
-	mutex_lock(&perf->lock);
+	mutex_lock(&gt->perf.lock);
 	ret = i915_perf_ioctl_locked(stream, cmd, arg);
-	mutex_unlock(&perf->lock);
+	mutex_unlock(&gt->perf.lock);
 
 	return ret;
 }
@@ -3570,7 +3574,7 @@ static long i915_perf_ioctl(struct file *file,
  * Frees all resources associated with the given i915 perf @stream, disabling
  * any associated data capture in the process.
  *
- * Note: The &perf->lock mutex has been taken to serialize
+ * Note: The &gt->perf.lock mutex has been taken to serialize
  * with any non-file-operation driver hooks.
  */
 static void i915_perf_destroy_locked(struct i915_perf_stream *stream)
@@ -3602,10 +3606,11 @@ static int i915_perf_release(struct inode *inode, struct file *file)
 {
 	struct i915_perf_stream *stream = file->private_data;
 	struct i915_perf *perf = stream->perf;
+	struct intel_gt *gt = stream->engine->gt;
 
-	mutex_lock(&perf->lock);
+	mutex_lock(&gt->perf.lock);
 	i915_perf_destroy_locked(stream);
-	mutex_unlock(&perf->lock);
+	mutex_unlock(&gt->perf.lock);
 
 	/* Release the reference the perf stream kept on the driver. */
 	drm_dev_put(&perf->i915->drm);
@@ -3638,7 +3643,7 @@ static const struct file_operations fops = {
  * See i915_perf_ioctl_open() for interface details.
  *
  * Implements further stream config validation and stream initialization on
- * behalf of i915_perf_open_ioctl() with the &perf->lock mutex
+ * behalf of i915_perf_open_ioctl() with the &gt->perf.lock mutex
  * taken to serialize with any non-file-operation driver hooks.
  *
  * Note: at this point the @props have only been validated in isolation and
@@ -4022,7 +4027,7 @@ static int read_properties_unlocked(struct i915_perf *perf,
  * mutex to avoid an awkward lockdep with mmap_lock.
  *
  * Most of the implementation details are handled by
- * i915_perf_open_ioctl_locked() after taking the &perf->lock
+ * i915_perf_open_ioctl_locked() after taking the &gt->perf.lock
  * mutex for serializing with any non-file-operation driver hooks.
  *
  * Return: A newly opened i915 Perf stream file descriptor or negative
@@ -4033,6 +4038,7 @@ int i915_perf_open_ioctl(struct drm_device *dev, void *data,
 {
 	struct i915_perf *perf = &to_i915(dev)->perf;
 	struct drm_i915_perf_open_param *param = data;
+	struct intel_gt *gt;
 	struct perf_open_properties props;
 	u32 known_open_flags;
 	int ret;
@@ -4059,9 +4065,11 @@ int i915_perf_open_ioctl(struct drm_device *dev, void *data,
 	if (ret)
 		return ret;
 
-	mutex_lock(&perf->lock);
+	gt = props.engine->gt;
+
+	mutex_lock(&gt->perf.lock);
 	ret = i915_perf_open_ioctl_locked(perf, param, &props, file);
-	mutex_unlock(&perf->lock);
+	mutex_unlock(&gt->perf.lock);
 
 	return ret;
 }
@@ -4077,6 +4085,7 @@ int i915_perf_open_ioctl(struct drm_device *dev, void *data,
 void i915_perf_register(struct drm_i915_private *i915)
 {
 	struct i915_perf *perf = &i915->perf;
+	struct intel_gt *gt = to_gt(i915);
 
 	if (!perf->i915)
 		return;
@@ -4085,13 +4094,13 @@ void i915_perf_register(struct drm_i915_private *i915)
 	 * i915_perf_open_ioctl(); considering that we register after
 	 * being exposed to userspace.
 	 */
-	mutex_lock(&perf->lock);
+	mutex_lock(&gt->perf.lock);
 
 	perf->metrics_kobj =
 		kobject_create_and_add("metrics",
 				       &i915->drm.primary->kdev->kobj);
 
-	mutex_unlock(&perf->lock);
+	mutex_unlock(&gt->perf.lock);
 }
 
 /**
@@ -4768,7 +4777,11 @@ void i915_perf_init(struct drm_i915_private *i915)
 	}
 
 	if (perf->ops.enable_metric_set) {
-		mutex_init(&perf->lock);
+		struct intel_gt *gt;
+		int i;
+
+		for_each_gt(gt, i915, i)
+			mutex_init(&gt->perf.lock);
 
 		/* Choose a representative limit */
 		oa_sample_rate_hard_limit = to_gt(i915)->clock_frequency / 2;
diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h
index 05cb9a335a97..e888bfab478f 100644
--- a/drivers/gpu/drm/i915/i915_perf_types.h
+++ b/drivers/gpu/drm/i915/i915_perf_types.h
@@ -380,6 +380,26 @@ struct i915_oa_ops {
 	u32 (*oa_hw_tail_read)(struct i915_perf_stream *stream);
 };
 
+struct i915_perf_gt {
+	/*
+	 * Lock associated with anything below within this structure.
+	 */
+	struct mutex lock;
+
+	/**
+	 * @sseu: sseu configuration selected to run while perf is active,
+	 * applies to all contexts.
+	 */
+	struct intel_sseu sseu;
+
+	/*
+	 * @exclusive_stream: The stream currently using the OA unit. This is
+	 * sometimes accessed outside a syscall associated to its file
+	 * descriptor.
+	 */
+	struct i915_perf_stream *exclusive_stream;
+};
+
 struct i915_perf {
 	struct drm_i915_private *i915;
 
@@ -397,25 +417,6 @@ struct i915_perf {
 	 */
 	struct idr metrics_idr;
 
-	/*
-	 * Lock associated with anything below within this structure
-	 * except exclusive_stream.
-	 */
-	struct mutex lock;
-
-	/*
-	 * The stream currently using the OA unit. If accessed
-	 * outside a syscall associated to its file
-	 * descriptor.
-	 */
-	struct i915_perf_stream *exclusive_stream;
-
-	/**
-	 * @sseu: sseu configuration selected to run while perf is active,
-	 * applies to all contexts.
-	 */
-	struct intel_sseu sseu;
-
 	/**
 	 * For rate limiting any notifications of spurious
 	 * invalid OA reports
diff --git a/drivers/gpu/drm/i915/selftests/i915_perf.c b/drivers/gpu/drm/i915/selftests/i915_perf.c
index 429c6d73b159..24dde5531423 100644
--- a/drivers/gpu/drm/i915/selftests/i915_perf.c
+++ b/drivers/gpu/drm/i915/selftests/i915_perf.c
@@ -102,6 +102,12 @@ test_stream(struct i915_perf *perf)
 		I915_OA_FORMAT_A32u40_A4u32_B8_C8 : I915_OA_FORMAT_C4_B8,
 	};
 	struct i915_perf_stream *stream;
+	struct intel_gt *gt;
+
+	if (!props.engine)
+		return NULL;
+
+	gt = props.engine->gt;
 
 	if (!oa_config)
 		return NULL;
@@ -116,12 +122,12 @@ test_stream(struct i915_perf *perf)
 
 	stream->perf = perf;
 
-	mutex_lock(&perf->lock);
+	mutex_lock(&gt->perf.lock);
 	if (i915_oa_stream_init(stream, &param, &props)) {
 		kfree(stream);
 		stream =  NULL;
 	}
-	mutex_unlock(&perf->lock);
+	mutex_unlock(&gt->perf.lock);
 
 	i915_oa_config_put(oa_config);
 
@@ -130,11 +136,11 @@ test_stream(struct i915_perf *perf)
 
 static void stream_destroy(struct i915_perf_stream *stream)
 {
-	struct i915_perf *perf = stream->perf;
+	struct intel_gt *gt = stream->engine->gt;
 
-	mutex_lock(&perf->lock);
+	mutex_lock(&gt->perf.lock);
 	i915_perf_destroy_locked(stream);
-	mutex_unlock(&perf->lock);
+	mutex_unlock(&gt->perf.lock);
 }
 
 static int live_sanitycheck(void *arg)
-- 
cgit v1.2.3


From 2db609c014958202e067678758c2a5291a28bae5 Mon Sep 17 00:00:00 2001
From: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Date: Wed, 26 Oct 2022 22:20:54 +0000
Subject: drm/i915/perf: Replace gt->perf.lock with stream->lock for file ops

With multi-gt, user can access multiple OA buffers concurrently. Use
stream->lock instead of gt->perf.lock to serialize file operations.

Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221026222102.5526-9-umesh.nerlige.ramappa@intel.com
---
 drivers/gpu/drm/i915/i915_perf.c       | 31 ++++++++++++++-----------------
 drivers/gpu/drm/i915/i915_perf_types.h |  5 +++++
 2 files changed, 19 insertions(+), 17 deletions(-)

(limited to 'drivers/gpu/drm/i915/i915_perf.c')

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 83c5dc043261..9a00398ae25f 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -3231,6 +3231,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	stream->poll_check_timer.function = oa_poll_check_timer_cb;
 	init_waitqueue_head(&stream->poll_wq);
 	spin_lock_init(&stream->oa_buffer.ptr_lock);
+	mutex_init(&stream->lock);
 
 	return 0;
 
@@ -3294,7 +3295,6 @@ static ssize_t i915_perf_read(struct file *file,
 			      loff_t *ppos)
 {
 	struct i915_perf_stream *stream = file->private_data;
-	struct intel_gt *gt = stream->engine->gt;
 	size_t offset = 0;
 	int ret;
 
@@ -3318,14 +3318,14 @@ static ssize_t i915_perf_read(struct file *file,
 			if (ret)
 				return ret;
 
-			mutex_lock(&gt->perf.lock);
+			mutex_lock(&stream->lock);
 			ret = stream->ops->read(stream, buf, count, &offset);
-			mutex_unlock(&gt->perf.lock);
+			mutex_unlock(&stream->lock);
 		} while (!offset && !ret);
 	} else {
-		mutex_lock(&gt->perf.lock);
+		mutex_lock(&stream->lock);
 		ret = stream->ops->read(stream, buf, count, &offset);
-		mutex_unlock(&gt->perf.lock);
+		mutex_unlock(&stream->lock);
 	}
 
 	/* We allow the poll checking to sometimes report false positive EPOLLIN
@@ -3372,9 +3372,6 @@ static enum hrtimer_restart oa_poll_check_timer_cb(struct hrtimer *hrtimer)
  * &i915_perf_stream_ops->poll_wait to call poll_wait() with a wait queue that
  * will be woken for new stream data.
  *
- * Note: The &gt->perf.lock mutex has been taken to serialize
- * with any non-file-operation driver hooks.
- *
  * Returns: any poll events that are ready without sleeping
  */
 static __poll_t i915_perf_poll_locked(struct i915_perf_stream *stream,
@@ -3413,12 +3410,11 @@ static __poll_t i915_perf_poll_locked(struct i915_perf_stream *stream,
 static __poll_t i915_perf_poll(struct file *file, poll_table *wait)
 {
 	struct i915_perf_stream *stream = file->private_data;
-	struct intel_gt *gt = stream->engine->gt;
 	__poll_t ret;
 
-	mutex_lock(&gt->perf.lock);
+	mutex_lock(&stream->lock);
 	ret = i915_perf_poll_locked(stream, file, wait);
-	mutex_unlock(&gt->perf.lock);
+	mutex_unlock(&stream->lock);
 
 	return ret;
 }
@@ -3517,9 +3513,6 @@ static long i915_perf_config_locked(struct i915_perf_stream *stream,
  * @cmd: the ioctl request
  * @arg: the ioctl data
  *
- * Note: The &gt->perf.lock mutex has been taken to serialize
- * with any non-file-operation driver hooks.
- *
  * Returns: zero on success or a negative error code. Returns -EINVAL for
  * an unknown ioctl request.
  */
@@ -3557,12 +3550,11 @@ static long i915_perf_ioctl(struct file *file,
 			    unsigned long arg)
 {
 	struct i915_perf_stream *stream = file->private_data;
-	struct intel_gt *gt = stream->engine->gt;
 	long ret;
 
-	mutex_lock(&gt->perf.lock);
+	mutex_lock(&stream->lock);
 	ret = i915_perf_ioctl_locked(stream, cmd, arg);
-	mutex_unlock(&gt->perf.lock);
+	mutex_unlock(&stream->lock);
 
 	return ret;
 }
@@ -3608,6 +3600,11 @@ static int i915_perf_release(struct inode *inode, struct file *file)
 	struct i915_perf *perf = stream->perf;
 	struct intel_gt *gt = stream->engine->gt;
 
+	/*
+	 * Within this call, we know that the fd is being closed and we have no
+	 * other user of stream->lock. Use the perf lock to destroy the stream
+	 * here.
+	 */
 	mutex_lock(&gt->perf.lock);
 	i915_perf_destroy_locked(stream);
 	mutex_unlock(&gt->perf.lock);
diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h
index e888bfab478f..dc9bfd8086cf 100644
--- a/drivers/gpu/drm/i915/i915_perf_types.h
+++ b/drivers/gpu/drm/i915/i915_perf_types.h
@@ -146,6 +146,11 @@ struct i915_perf_stream {
 	 */
 	struct intel_engine_cs *engine;
 
+	/*
+	 * Lock associated with operations on stream
+	 */
+	struct mutex lock;
+
 	/**
 	 * @sample_flags: Flags representing the `DRM_I915_PERF_PROP_SAMPLE_*`
 	 * properties given when opening a stream, representing the contents
-- 
cgit v1.2.3


From cc85345dc804f9fbe39ca2727e63058595b01e0f Mon Sep 17 00:00:00 2001
From: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Date: Wed, 26 Oct 2022 22:20:55 +0000
Subject: drm/i915/perf: Use gt-specific ggtt for OA and noa-wait buffers

User passes uabi engine class and instance to the perf OA interface. Use
gt corresponding to the engine to pin the buffers to the right ggtt.

Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221026222102.5526-10-umesh.nerlige.ramappa@intel.com
---
 drivers/gpu/drm/i915/i915_perf.c | 21 +++++++++++++++++++--
 1 file changed, 19 insertions(+), 2 deletions(-)

(limited to 'drivers/gpu/drm/i915/i915_perf.c')

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 9a00398ae25f..2c8727253f0d 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1754,6 +1754,7 @@ static void gen12_init_oa_buffer(struct i915_perf_stream *stream)
 static int alloc_oa_buffer(struct i915_perf_stream *stream)
 {
 	struct drm_i915_private *i915 = stream->perf->i915;
+	struct intel_gt *gt = stream->engine->gt;
 	struct drm_i915_gem_object *bo;
 	struct i915_vma *vma;
 	int ret;
@@ -1773,11 +1774,22 @@ static int alloc_oa_buffer(struct i915_perf_stream *stream)
 	i915_gem_object_set_cache_coherency(bo, I915_CACHE_LLC);
 
 	/* PreHSW required 512K alignment, HSW requires 16M */
-	vma = i915_gem_object_ggtt_pin(bo, NULL, 0, SZ_16M, 0);
+	vma = i915_vma_instance(bo, &gt->ggtt->vm, NULL);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		goto err_unref;
 	}
+
+	/*
+	 * PreHSW required 512K alignment.
+	 * HSW and onwards, align to requested size of OA buffer.
+	 */
+	ret = i915_vma_pin(vma, 0, SZ_16M, PIN_GLOBAL | PIN_HIGH);
+	if (ret) {
+		drm_err(&gt->i915->drm, "Failed to pin OA buffer %d\n", ret);
+		goto err_unref;
+	}
+
 	stream->oa_buffer.vma = vma;
 
 	stream->oa_buffer.vaddr =
@@ -1827,6 +1839,7 @@ static u32 *save_restore_register(struct i915_perf_stream *stream, u32 *cs,
 static int alloc_noa_wait(struct i915_perf_stream *stream)
 {
 	struct drm_i915_private *i915 = stream->perf->i915;
+	struct intel_gt *gt = stream->engine->gt;
 	struct drm_i915_gem_object *bo;
 	struct i915_vma *vma;
 	const u64 delay_ticks = 0xffffffffffffffff -
@@ -1867,12 +1880,16 @@ retry:
 	 * multiple OA config BOs will have a jump to this address and it
 	 * needs to be fixed during the lifetime of the i915/perf stream.
 	 */
-	vma = i915_gem_object_ggtt_pin_ww(bo, &ww, NULL, 0, 0, PIN_HIGH);
+	vma = i915_vma_instance(bo, &gt->ggtt->vm, NULL);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		goto out_ww;
 	}
 
+	ret = i915_vma_pin_ww(vma, &ww, 0, 0, PIN_GLOBAL | PIN_HIGH);
+	if (ret)
+		goto out_ww;
+
 	batch = cs = i915_gem_object_pin_map(bo, I915_MAP_WB);
 	if (IS_ERR(batch)) {
 		ret = PTR_ERR(batch);
-- 
cgit v1.2.3


From 90981da6da8ce333c49d2748f925fc4ef566785f Mon Sep 17 00:00:00 2001
From: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Date: Wed, 26 Oct 2022 22:20:56 +0000
Subject: drm/i915/perf: Store a pointer to oa_format in oa_buffer

DG2 introduces OA reports with 64 bit report header fields. Perf OA
would need more information about the OA format in order to process such
reports. Store all OA format info in oa_buffer instead of just the size
and format-id.

v2: Drop format_size variable (Ashutosh)

Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221026222102.5526-11-umesh.nerlige.ramappa@intel.com
---
 drivers/gpu/drm/i915/i915_perf.c       | 30 ++++++++++++------------------
 drivers/gpu/drm/i915/i915_perf_types.h |  3 +--
 2 files changed, 13 insertions(+), 20 deletions(-)

(limited to 'drivers/gpu/drm/i915/i915_perf.c')

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 2c8727253f0d..585079ae5f03 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -465,7 +465,7 @@ static u32 gen7_oa_hw_tail_read(struct i915_perf_stream *stream)
 static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream)
 {
 	u32 gtt_offset = i915_ggtt_offset(stream->oa_buffer.vma);
-	int report_size = stream->oa_buffer.format_size;
+	int report_size = stream->oa_buffer.format->size;
 	unsigned long flags;
 	bool pollin;
 	u32 hw_tail;
@@ -602,7 +602,7 @@ static int append_oa_sample(struct i915_perf_stream *stream,
 			    size_t *offset,
 			    const u8 *report)
 {
-	int report_size = stream->oa_buffer.format_size;
+	int report_size = stream->oa_buffer.format->size;
 	struct drm_i915_perf_record_header header;
 
 	header.type = DRM_I915_PERF_RECORD_SAMPLE;
@@ -652,7 +652,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 				  size_t *offset)
 {
 	struct intel_uncore *uncore = stream->uncore;
-	int report_size = stream->oa_buffer.format_size;
+	int report_size = stream->oa_buffer.format->size;
 	u8 *oa_buf_base = stream->oa_buffer.vaddr;
 	u32 gtt_offset = i915_ggtt_offset(stream->oa_buffer.vma);
 	u32 mask = (OA_BUFFER_SIZE - 1);
@@ -945,7 +945,7 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream,
 				  size_t *offset)
 {
 	struct intel_uncore *uncore = stream->uncore;
-	int report_size = stream->oa_buffer.format_size;
+	int report_size = stream->oa_buffer.format->size;
 	u8 *oa_buf_base = stream->oa_buffer.vaddr;
 	u32 gtt_offset = i915_ggtt_offset(stream->oa_buffer.vma);
 	u32 mask = (OA_BUFFER_SIZE - 1);
@@ -2506,7 +2506,7 @@ static int gen12_configure_oar_context(struct i915_perf_stream *stream,
 {
 	int err;
 	struct intel_context *ce = stream->pinned_ctx;
-	u32 format = stream->oa_buffer.format;
+	u32 format = stream->oa_buffer.format->format;
 	u32 offset = stream->perf->ctx_oactxctrl_offset;
 	struct flex regs_context[] = {
 		{
@@ -2877,7 +2877,7 @@ static void gen7_oa_enable(struct i915_perf_stream *stream)
 	u32 ctx_id = stream->specific_ctx_id;
 	bool periodic = stream->periodic;
 	u32 period_exponent = stream->period_exponent;
-	u32 report_format = stream->oa_buffer.format;
+	u32 report_format = stream->oa_buffer.format->format;
 
 	/*
 	 * Reset buf pointers so we don't forward reports from before now.
@@ -2903,7 +2903,7 @@ static void gen7_oa_enable(struct i915_perf_stream *stream)
 static void gen8_oa_enable(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
-	u32 report_format = stream->oa_buffer.format;
+	u32 report_format = stream->oa_buffer.format->format;
 
 	/*
 	 * Reset buf pointers so we don't forward reports from before now.
@@ -2929,7 +2929,7 @@ static void gen8_oa_enable(struct i915_perf_stream *stream)
 static void gen12_oa_enable(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
-	u32 report_format = stream->oa_buffer.format;
+	u32 report_format = stream->oa_buffer.format->format;
 
 	/*
 	 * If we don't want OA reports from the OA buffer, then we don't even
@@ -3110,7 +3110,6 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	struct drm_i915_private *i915 = stream->perf->i915;
 	struct i915_perf *perf = stream->perf;
 	struct intel_gt *gt;
-	int format_size;
 	int ret;
 
 	if (!props->engine) {
@@ -3166,20 +3165,15 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 
 	stream->sample_size = sizeof(struct drm_i915_perf_record_header);
 
-	format_size = perf->oa_formats[props->oa_format].size;
+	stream->oa_buffer.format = &perf->oa_formats[props->oa_format];
+	if (drm_WARN_ON(&i915->drm, stream->oa_buffer.format->size == 0))
+		return -EINVAL;
 
 	stream->sample_flags = props->sample_flags;
-	stream->sample_size += format_size;
-
-	stream->oa_buffer.format_size = format_size;
-	if (drm_WARN_ON(&i915->drm, stream->oa_buffer.format_size == 0))
-		return -EINVAL;
+	stream->sample_size += stream->oa_buffer.format->size;
 
 	stream->hold_preemption = props->hold_preemption;
 
-	stream->oa_buffer.format =
-		perf->oa_formats[props->oa_format].format;
-
 	stream->periodic = props->oa_periodic;
 	if (stream->periodic)
 		stream->period_exponent = props->oa_period_exponent;
diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h
index dc9bfd8086cf..e0c96b44eda8 100644
--- a/drivers/gpu/drm/i915/i915_perf_types.h
+++ b/drivers/gpu/drm/i915/i915_perf_types.h
@@ -250,11 +250,10 @@ struct i915_perf_stream {
 	 * @oa_buffer: State of the OA buffer.
 	 */
 	struct {
+		const struct i915_oa_format *format;
 		struct i915_vma *vma;
 		u8 *vaddr;
 		u32 last_ctx_id;
-		int format;
-		int format_size;
 		int size_exponent;
 
 		/**
-- 
cgit v1.2.3


From ed6b25aa6fbf8855446efc7125e6b5d912b36ed3 Mon Sep 17 00:00:00 2001
From: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Date: Wed, 26 Oct 2022 22:20:57 +0000
Subject: drm/i915/perf: Add Wa_1508761755:dg2

Disable Clock gating in EU when gathering the events so that EU events
are not lost.

v2: Fix checkpatch issues
v3: User MCR helpers to write to MC reg
v4: Indent correctly (checkpatch)

Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221026222102.5526-12-umesh.nerlige.ramappa@intel.com
---
 drivers/gpu/drm/i915/gt/intel_gt_regs.h |  1 +
 drivers/gpu/drm/i915/i915_perf.c        | 24 ++++++++++++++++++++++++
 2 files changed, 25 insertions(+)

(limited to 'drivers/gpu/drm/i915/i915_perf.c')

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
index a9c409eb131c..1b901970cfa4 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
@@ -1162,6 +1162,7 @@
 #define   GEN12_DISABLE_EARLY_READ		REG_BIT(14)
 #define   GEN12_ENABLE_LARGE_GRF_MODE		REG_BIT(12)
 #define   GEN12_PUSH_CONST_DEREF_HOLD_DIS	REG_BIT(8)
+#define   GEN12_DISABLE_DOP_GATING              REG_BIT(0)
 
 #define RT_CTRL					MCR_REG(0xe530)
 #define   DIS_NULL_QUERY			REG_BIT(10)
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 585079ae5f03..e14d16ac47de 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -204,6 +204,7 @@
 #include "gt/intel_gpu_commands.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_clock_utils.h"
+#include "gt/intel_gt_mcr.h"
 #include "gt/intel_gt_regs.h"
 #include "gt/intel_lrc.h"
 #include "gt/intel_lrc_reg.h"
@@ -2775,6 +2776,18 @@ gen12_enable_metric_set(struct i915_perf_stream *stream,
 	u32 sqcnt1;
 	int ret;
 
+	/*
+	 * Wa_1508761755:xehpsdv, dg2
+	 * EU NOA signals behave incorrectly if EU clock gating is enabled.
+	 * Disable thread stall DOP gating and EU DOP gating.
+	 */
+	if (IS_XEHPSDV(i915) || IS_DG2(i915)) {
+		intel_gt_mcr_multicast_write(uncore->gt, GEN8_ROW_CHICKEN,
+					     _MASKED_BIT_ENABLE(STALL_DOP_GATING_DISABLE));
+		intel_uncore_write(uncore, GEN7_ROW_CHICKEN2,
+				   _MASKED_BIT_ENABLE(GEN12_DISABLE_DOP_GATING));
+	}
+
 	intel_uncore_write(uncore, GEN12_OAG_OA_DEBUG,
 			   /* Disable clk ratio reports, like previous Gens. */
 			   _MASKED_BIT_ENABLE(GEN12_OAG_OA_DEBUG_DISABLE_CLK_RATIO_REPORTS |
@@ -2853,6 +2866,17 @@ static void gen12_disable_metric_set(struct i915_perf_stream *stream)
 	struct drm_i915_private *i915 = stream->perf->i915;
 	u32 sqcnt1;
 
+	/*
+	 * Wa_1508761755:xehpsdv, dg2
+	 * Enable thread stall DOP gating and EU DOP gating.
+	 */
+	if (IS_XEHPSDV(i915) || IS_DG2(i915)) {
+		intel_gt_mcr_multicast_write(uncore->gt, GEN8_ROW_CHICKEN,
+					     _MASKED_BIT_DISABLE(STALL_DOP_GATING_DISABLE));
+		intel_uncore_write(uncore, GEN7_ROW_CHICKEN2,
+				   _MASKED_BIT_DISABLE(GEN12_DISABLE_DOP_GATING));
+	}
+
 	/* Reset all contexts' slices/subslices configurations. */
 	gen12_configure_all_contexts(stream, NULL, NULL);
 
-- 
cgit v1.2.3


From bc7ed4d30815bc434c1e49dc6784164b352d167c Mon Sep 17 00:00:00 2001
From: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Date: Wed, 26 Oct 2022 22:20:58 +0000
Subject: drm/i915/perf: Apply Wa_18013179988

OA reports in the OA buffer contain an OA timestamp field that helps
user calculate delta between 2 OA reports. The calculation relies on the
CS timestamp frequency to convert the timestamp value to nanoseconds.
The CS timestamp frequency is a function of the CTC_SHIFT value in
RPM_CONFIG0.

In DG2, OA unit assumes that the CTC_SHIFT is 3, instead of using the
actual value from RPM_CONFIG0. At the user level, this results in an
error in calculating delta between 2 OA reports since the OA timestamp
is not shifted in the same manner as CS timestamp. Also the periodicity
of the reports is different from what the user configured because of
mismatch in the CS and OA frequencies.

The issue also affects MI_REPORT_PERF_COUNT command.

To resolve this, return actual OA timestamp frequency to the user in
i915_getparam_ioctl, so that user can calculate the right OA exponent as
well as interpret the reports correctly.

MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18893

v2:
- Use REG_FIELD_GET (Ashutosh)
- Update commit msg

Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221026222102.5526-13-umesh.nerlige.ramappa@intel.com
---
 drivers/gpu/drm/i915/i915_getparam.c |  3 +++
 drivers/gpu/drm/i915/i915_perf.c     | 30 ++++++++++++++++++++++++++++--
 drivers/gpu/drm/i915/i915_perf.h     |  2 ++
 include/uapi/drm/i915_drm.h          |  6 ++++++
 4 files changed, 39 insertions(+), 2 deletions(-)

(limited to 'drivers/gpu/drm/i915/i915_perf.c')

diff --git a/drivers/gpu/drm/i915/i915_getparam.c b/drivers/gpu/drm/i915/i915_getparam.c
index 342c8ca6414e..3047e80e1163 100644
--- a/drivers/gpu/drm/i915/i915_getparam.c
+++ b/drivers/gpu/drm/i915/i915_getparam.c
@@ -175,6 +175,9 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data,
 	case I915_PARAM_PERF_REVISION:
 		value = i915_perf_ioctl_version();
 		break;
+	case I915_PARAM_OA_TIMESTAMP_FREQUENCY:
+		value = i915_perf_oa_timestamp_frequency(i915);
+		break;
 	default:
 		DRM_DEBUG("Unknown parameter %d\n", param->param);
 		return -EINVAL;
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index e14d16ac47de..b73d91b792df 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -3109,6 +3109,30 @@ get_sseu_config(struct intel_sseu *out_sseu,
 	return i915_gem_user_to_context_sseu(engine->gt, drm_sseu, out_sseu);
 }
 
+/*
+ * OA timestamp frequency = CS timestamp frequency in most platforms. On some
+ * platforms OA unit ignores the CTC_SHIFT and the 2 timestamps differ. In such
+ * cases, return the adjusted CS timestamp frequency to the user.
+ */
+u32 i915_perf_oa_timestamp_frequency(struct drm_i915_private *i915)
+{
+	/* Wa_18013179988:dg2 */
+	if (IS_DG2(i915)) {
+		intel_wakeref_t wakeref;
+		u32 reg, shift;
+
+		with_intel_runtime_pm(to_gt(i915)->uncore->rpm, wakeref)
+			reg = intel_uncore_read(to_gt(i915)->uncore, RPM_CONFIG0);
+
+		shift = REG_FIELD_GET(GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_MASK,
+				      reg);
+
+		return to_gt(i915)->clock_frequency << (3 - shift);
+	}
+
+	return to_gt(i915)->clock_frequency;
+}
+
 /**
  * i915_oa_stream_init - validate combined props for OA stream and init
  * @stream: An i915 perf stream
@@ -3830,8 +3854,10 @@ err:
 
 static u64 oa_exponent_to_ns(struct i915_perf *perf, int exponent)
 {
-	return intel_gt_clock_interval_to_ns(to_gt(perf->i915),
-					     2ULL << exponent);
+	u64 nom = (2ULL << exponent) * NSEC_PER_SEC;
+	u32 den = i915_perf_oa_timestamp_frequency(perf->i915);
+
+	return div_u64(nom + den - 1, den);
 }
 
 static __always_inline bool
diff --git a/drivers/gpu/drm/i915/i915_perf.h b/drivers/gpu/drm/i915/i915_perf.h
index 1d1329e5af3a..f96e09a4af04 100644
--- a/drivers/gpu/drm/i915/i915_perf.h
+++ b/drivers/gpu/drm/i915/i915_perf.h
@@ -57,4 +57,6 @@ static inline void i915_oa_config_put(struct i915_oa_config *oa_config)
 	kref_put(&oa_config->ref, i915_oa_config_release);
 }
 
+u32 i915_perf_oa_timestamp_frequency(struct drm_i915_private *i915);
+
 #endif /* __I915_PERF_H__ */
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index b946674c68cc..8df261c5ab9b 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -765,6 +765,12 @@ typedef struct drm_i915_irq_wait {
 /* Query if the kernel supports the I915_USERPTR_PROBE flag. */
 #define I915_PARAM_HAS_USERPTR_PROBE 56
 
+/*
+ * Frequency of the timestamps in OA reports. This used to be the same as the CS
+ * timestamp frequency, but differs on some platforms.
+ */
+#define I915_PARAM_OA_TIMESTAMP_FREQUENCY 57
+
 /* Must be kept compact -- no holes and well documented */
 
 /**
-- 
cgit v1.2.3


From 01e7427467857861d1aaa7cd05598dfcb631c5b5 Mon Sep 17 00:00:00 2001
From: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Date: Wed, 26 Oct 2022 22:21:00 +0000
Subject: drm/i915/guc: Support OA when Wa_16011777198 is enabled

On DG2, a w/a resets RCS/CCS before it goes into RC6. This breaks OA
since OA does not expect engine resets during its use. Fix it by
disabling RC6.

v2: (Ashutosh)
- Bring back slpc_unset_param helper
- Update commit msg
- Use with_intel_runtime_pm helper for set/unset

v3: (Ashutosh)
- Just use intel_uc_uses_guc_rc

Signed-off-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221026222102.5526-15-umesh.nerlige.ramappa@intel.com
---
 .../gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h  |  9 +++
 drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c        | 66 ++++++++++++++++++++++
 drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h        |  2 +
 drivers/gpu/drm/i915/i915_perf.c                   | 27 +++++++++
 4 files changed, 104 insertions(+)

(limited to 'drivers/gpu/drm/i915/i915_perf.c')

diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h
index 4c840a2639dc..811add10c30d 100644
--- a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h
+++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h
@@ -128,6 +128,15 @@ enum slpc_media_ratio_mode {
 	SLPC_MEDIA_RATIO_MODE_FIXED_ONE_TO_TWO = 2,
 };
 
+enum slpc_gucrc_mode {
+	SLPC_GUCRC_MODE_HW = 0,
+	SLPC_GUCRC_MODE_GUCRC_NO_RC6 = 1,
+	SLPC_GUCRC_MODE_GUCRC_STATIC_TIMEOUT = 2,
+	SLPC_GUCRC_MODE_GUCRC_DYNAMIC_HYSTERESIS = 3,
+
+	SLPC_GUCRC_MODE_MAX,
+};
+
 enum slpc_event_id {
 	SLPC_EVENT_RESET = 0,
 	SLPC_EVENT_SHUTDOWN = 1,
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c
index c7e568af1e9c..63464933cbce 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c
@@ -137,6 +137,17 @@ static int guc_action_slpc_set_param(struct intel_guc *guc, u8 id, u32 value)
 	return ret > 0 ? -EPROTO : ret;
 }
 
+static int guc_action_slpc_unset_param(struct intel_guc *guc, u8 id)
+{
+	u32 request[] = {
+		GUC_ACTION_HOST2GUC_PC_SLPC_REQUEST,
+		SLPC_EVENT(SLPC_EVENT_PARAMETER_UNSET, 1),
+		id,
+	};
+
+	return intel_guc_send(guc, request, ARRAY_SIZE(request));
+}
+
 static bool slpc_is_running(struct intel_guc_slpc *slpc)
 {
 	return slpc_get_state(slpc) == SLPC_GLOBAL_STATE_RUNNING;
@@ -190,6 +201,15 @@ static int slpc_set_param(struct intel_guc_slpc *slpc, u8 id, u32 value)
 	return ret;
 }
 
+static int slpc_unset_param(struct intel_guc_slpc *slpc, u8 id)
+{
+	struct intel_guc *guc = slpc_to_guc(slpc);
+
+	GEM_BUG_ON(id >= SLPC_MAX_PARAM);
+
+	return guc_action_slpc_unset_param(guc, id);
+}
+
 static int slpc_force_min_freq(struct intel_guc_slpc *slpc, u32 freq)
 {
 	struct drm_i915_private *i915 = slpc_to_i915(slpc);
@@ -644,6 +664,52 @@ static void slpc_get_rp_values(struct intel_guc_slpc *slpc)
 		slpc->boost_freq = slpc->rp0_freq;
 }
 
+/**
+ * intel_guc_slpc_override_gucrc_mode() - override GUCRC mode
+ * @slpc: pointer to intel_guc_slpc.
+ * @mode: new value of the mode.
+ *
+ * This function will override the GUCRC mode.
+ *
+ * Return: 0 on success, non-zero error code on failure.
+ */
+int intel_guc_slpc_override_gucrc_mode(struct intel_guc_slpc *slpc, u32 mode)
+{
+	int ret;
+	struct drm_i915_private *i915 = slpc_to_i915(slpc);
+	intel_wakeref_t wakeref;
+
+	if (mode >= SLPC_GUCRC_MODE_MAX)
+		return -EINVAL;
+
+	with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
+		ret = slpc_set_param(slpc, SLPC_PARAM_PWRGATE_RC_MODE, mode);
+		if (ret)
+			drm_err(&i915->drm,
+				"Override gucrc mode %d failed %d\n",
+				mode, ret);
+	}
+
+	return ret;
+}
+
+int intel_guc_slpc_unset_gucrc_mode(struct intel_guc_slpc *slpc)
+{
+	struct drm_i915_private *i915 = slpc_to_i915(slpc);
+	intel_wakeref_t wakeref;
+	int ret = 0;
+
+	with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
+		ret = slpc_unset_param(slpc, SLPC_PARAM_PWRGATE_RC_MODE);
+		if (ret)
+			drm_err(&i915->drm,
+				"Unsetting gucrc mode failed %d\n",
+				ret);
+	}
+
+	return ret;
+}
+
 /*
  * intel_guc_slpc_enable() - Start SLPC
  * @slpc: pointer to intel_guc_slpc.
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h
index 11975a31c9d0..17ed515f6a85 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h
@@ -44,5 +44,7 @@ int intel_guc_slpc_set_media_ratio_mode(struct intel_guc_slpc *slpc, u32 val);
 void intel_guc_pm_intrmsk_enable(struct intel_gt *gt);
 void intel_guc_slpc_boost(struct intel_guc_slpc *slpc);
 void intel_guc_slpc_dec_waiters(struct intel_guc_slpc *slpc);
+int intel_guc_slpc_unset_gucrc_mode(struct intel_guc_slpc *slpc);
+int intel_guc_slpc_override_gucrc_mode(struct intel_guc_slpc *slpc, u32 mode);
 
 #endif
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index b73d91b792df..b2766485888f 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -209,6 +209,7 @@
 #include "gt/intel_lrc.h"
 #include "gt/intel_lrc_reg.h"
 #include "gt/intel_ring.h"
+#include "gt/uc/intel_guc_slpc.h"
 
 #include "i915_drv.h"
 #include "i915_file_private.h"
@@ -1582,6 +1583,15 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream)
 
 	free_oa_buffer(stream);
 
+	/*
+	 * Wa_16011777198:dg2: Unset the override of GUCRC mode to enable rc6.
+	 */
+	if (intel_uc_uses_guc_rc(&gt->uc) &&
+	    (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_C0) ||
+	     IS_DG2_GRAPHICS_STEP(gt->i915, G11, STEP_A0, STEP_B0)))
+		drm_WARN_ON(&gt->i915->drm,
+			    intel_guc_slpc_unset_gucrc_mode(&gt->uc.guc.slpc));
+
 	intel_uncore_forcewake_put(stream->uncore, FORCEWAKE_ALL);
 	intel_engine_pm_put(stream->engine);
 
@@ -3265,6 +3275,23 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	intel_engine_pm_get(stream->engine);
 	intel_uncore_forcewake_get(stream->uncore, FORCEWAKE_ALL);
 
+	/*
+	 * Wa_16011777198:dg2: GuC resets render as part of the Wa. This causes
+	 * OA to lose the configuration state. Prevent this by overriding GUCRC
+	 * mode.
+	 */
+	if (intel_uc_uses_guc_rc(&gt->uc) &&
+	    (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_C0) ||
+	     IS_DG2_GRAPHICS_STEP(gt->i915, G11, STEP_A0, STEP_B0))) {
+		ret = intel_guc_slpc_override_gucrc_mode(&gt->uc.guc.slpc,
+							 SLPC_GUCRC_MODE_GUCRC_NO_RC6);
+		if (ret) {
+			drm_dbg(&stream->perf->i915->drm,
+				"Unable to override gucrc mode\n");
+			goto err_config;
+		}
+	}
+
 	ret = alloc_oa_buffer(stream);
 	if (ret)
 		goto err_oa_buf_alloc;
-- 
cgit v1.2.3


From 0fa9349dda030fa847b36f880a5eea25c3202b66 Mon Sep 17 00:00:00 2001
From: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Date: Wed, 26 Oct 2022 22:21:01 +0000
Subject: drm/i915/perf: complete programming whitelisting for XEHPSDV

We have an additional register to select which slices contribute to
OAG/OAG counter increments.

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221026222102.5526-16-umesh.nerlige.ramappa@intel.com
---
 drivers/gpu/drm/i915/i915_drv.h          |  2 ++
 drivers/gpu/drm/i915/i915_pci.c          |  1 +
 drivers/gpu/drm/i915/i915_perf.c         | 13 +++++++++++++
 drivers/gpu/drm/i915/intel_device_info.h |  1 +
 4 files changed, 17 insertions(+)

(limited to 'drivers/gpu/drm/i915/i915_perf.c')

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 34f0bcc36671..b1c4e924d883 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -903,6 +903,8 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 
 #define HAS_OA_BPC_REPORTING(dev_priv) \
 	(INTEL_INFO(dev_priv)->has_oa_bpc_reporting)
+#define HAS_OA_SLICE_CONTRIB_LIMITS(dev_priv) \
+	(INTEL_INFO(dev_priv)->has_oa_slice_contrib_limits)
 
 /*
  * Set this flag, when platform requires 64K GTT page sizes or larger for
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 7b751bf4be21..6b22fb506aa9 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -1024,6 +1024,7 @@ static const struct intel_device_info adl_p_info = {
 	.has_logical_ring_elsq = 1, \
 	.has_mslice_steering = 1, \
 	.has_oa_bpc_reporting = 1, \
+	.has_oa_slice_contrib_limits = 1, \
 	.has_rc6 = 1, \
 	.has_reset_engine = 1, \
 	.has_rps = 1, \
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index b2766485888f..2db74b5a54cd 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -4261,6 +4261,11 @@ static const struct i915_range gen12_oa_b_counters[] = {
 	{}
 };
 
+static const struct i915_range xehp_oa_b_counters[] = {
+	{ .start = 0xdc48, .end = 0xdc48 },	/* OAA_ENABLE_REG */
+	{ .start = 0xdd00, .end = 0xdd48 },	/* OAG_LCE0_0 - OAA_LENABLE_REG */
+};
+
 static const struct i915_range gen7_oa_mux_regs[] = {
 	{ .start = 0x91b8, .end = 0x91cc },	/* OA_PERFCNT[1-2], OA_PERFMATRIX */
 	{ .start = 0x9800, .end = 0x9888 },	/* MICRO_BP0_0 - NOA_WRITE */
@@ -4335,6 +4340,12 @@ static bool gen12_is_valid_b_counter_addr(struct i915_perf *perf, u32 addr)
 	return reg_in_range_table(addr, gen12_oa_b_counters);
 }
 
+static bool xehp_is_valid_b_counter_addr(struct i915_perf *perf, u32 addr)
+{
+	return reg_in_range_table(addr, xehp_oa_b_counters) ||
+		reg_in_range_table(addr, gen12_oa_b_counters);
+}
+
 static bool gen12_is_valid_mux_addr(struct i915_perf *perf, u32 addr)
 {
 	return reg_in_range_table(addr, gen12_oa_mux_regs);
@@ -4847,6 +4858,8 @@ void i915_perf_init(struct drm_i915_private *i915)
 			perf->ops.oa_hw_tail_read = gen8_oa_hw_tail_read;
 		} else if (GRAPHICS_VER(i915) == 12) {
 			perf->ops.is_valid_b_counter_reg =
+				HAS_OA_SLICE_CONTRIB_LIMITS(i915) ?
+				xehp_is_valid_b_counter_addr :
 				gen12_is_valid_b_counter_addr;
 			perf->ops.is_valid_mux_reg =
 				gen12_is_valid_mux_addr;
diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
index d11546d87fe7..4ee6074955ef 100644
--- a/drivers/gpu/drm/i915/intel_device_info.h
+++ b/drivers/gpu/drm/i915/intel_device_info.h
@@ -164,6 +164,7 @@ enum intel_ppgtt_type {
 	func(has_media_ratio_mode); \
 	func(has_mslice_steering); \
 	func(has_oa_bpc_reporting); \
+	func(has_oa_slice_contrib_limits); \
 	func(has_one_eu_per_fuse_bit); \
 	func(has_pxp); \
 	func(has_rc6); \
-- 
cgit v1.2.3


From 07b444f57f12177e5df639f55dc1d747f4a635c8 Mon Sep 17 00:00:00 2001
From: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Date: Wed, 26 Oct 2022 22:21:02 +0000
Subject: drm/i915/perf: Enable OA for DG2

OA was disabled for DG2 as support was missing. Enable it back now.

Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221026222102.5526-17-umesh.nerlige.ramappa@intel.com
---
 drivers/gpu/drm/i915/i915_perf.c | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'drivers/gpu/drm/i915/i915_perf.c')

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 2db74b5a54cd..0dd597a7a11f 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -4798,12 +4798,6 @@ void i915_perf_init(struct drm_i915_private *i915)
 {
 	struct i915_perf *perf = &i915->perf;
 
-	/* XXX const struct i915_perf_ops! */
-
-	/* i915_perf is not enabled for DG2 yet */
-	if (IS_DG2(i915))
-		return;
-
 	perf->oa_formats = oa_formats;
 	if (IS_HASWELL(i915)) {
 		perf->ops.is_valid_b_counter_reg = gen7_is_valid_b_counter_addr;
-- 
cgit v1.2.3