1 files changed, 78 insertions, 92 deletions

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 3b6b913bd27a..cf2c01f17da8 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -555,8 +555,9 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream)
 				aging_tail = hw_tail;
 			stream->oa_buffer.aging_timestamp = now;
 		} else {
-			DRM_ERROR("Ignoring spurious out of range OA buffer tail pointer = %x\n",
-				  hw_tail);
+			drm_err(&stream->perf->i915->drm,
+				"Ignoring spurious out of range OA buffer tail pointer = %x\n",
+				hw_tail);
 		}
 	}
 
@@ -686,7 +687,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 	u32 taken;
 	int ret = 0;
 
-	if (WARN_ON(!stream->enabled))
+	if (drm_WARN_ON(&uncore->i915->drm, !stream->enabled))
 		return -EIO;
 
 	spin_lock_irqsave(&stream->oa_buffer.ptr_lock, flags);
@@ -718,10 +719,11 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 	 * only be incremented by multiples of the report size (notably also
 	 * all a power of two).
 	 */
-	if (WARN_ONCE(head > OA_BUFFER_SIZE || head % report_size ||
-		      tail > OA_BUFFER_SIZE || tail % report_size,
-		      "Inconsistent OA buffer pointers: head = %u, tail = %u\n",
-		      head, tail))
+	if (drm_WARN_ONCE(&uncore->i915->drm,
+			  head > OA_BUFFER_SIZE || head % report_size ||
+			  tail > OA_BUFFER_SIZE || tail % report_size,
+			  "Inconsistent OA buffer pointers: head = %u, tail = %u\n",
+			  head, tail))
 		return -EIO;
 
 
@@ -742,8 +744,10 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 		 * here would imply a driver bug that would result
 		 * in an overrun.
 		 */
-		if (WARN_ON((OA_BUFFER_SIZE - head) < report_size)) {
-			DRM_ERROR("Spurious OA head ptr: non-integral report offset\n");
+		if (drm_WARN_ON(&uncore->i915->drm,
+				(OA_BUFFER_SIZE - head) < report_size)) {
+			drm_err(&uncore->i915->drm,
+				"Spurious OA head ptr: non-integral report offset\n");
 			break;
 		}
 
@@ -896,7 +900,7 @@ static int gen8_oa_read(struct i915_perf_stream *stream,
 	i915_reg_t oastatus_reg;
 	int ret;
 
-	if (WARN_ON(!stream->oa_buffer.vaddr))
+	if (drm_WARN_ON(&uncore->i915->drm, !stream->oa_buffer.vaddr))
 		return -EIO;
 
 	oastatus_reg = IS_GEN(stream->perf->i915, 12) ?
@@ -986,7 +990,7 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream,
 	u32 taken;
 	int ret = 0;
 
-	if (WARN_ON(!stream->enabled))
+	if (drm_WARN_ON(&uncore->i915->drm, !stream->enabled))
 		return -EIO;
 
 	spin_lock_irqsave(&stream->oa_buffer.ptr_lock, flags);
@@ -1015,10 +1019,11 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream,
 	 * only be incremented by multiples of the report size (notably also
 	 * all a power of two).
 	 */
-	if (WARN_ONCE(head > OA_BUFFER_SIZE || head % report_size ||
-		      tail > OA_BUFFER_SIZE || tail % report_size,
-		      "Inconsistent OA buffer pointers: head = %u, tail = %u\n",
-		      head, tail))
+	if (drm_WARN_ONCE(&uncore->i915->drm,
+			  head > OA_BUFFER_SIZE || head % report_size ||
+			  tail > OA_BUFFER_SIZE || tail % report_size,
+			  "Inconsistent OA buffer pointers: head = %u, tail = %u\n",
+			  head, tail))
 		return -EIO;
 
 
@@ -1036,8 +1041,10 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream,
 		 * here would imply a driver bug that would result
 		 * in an overrun.
 		 */
-		if (WARN_ON((OA_BUFFER_SIZE - head) < report_size)) {
-			DRM_ERROR("Spurious OA head ptr: non-integral report offset\n");
+		if (drm_WARN_ON(&uncore->i915->drm,
+				(OA_BUFFER_SIZE - head) < report_size)) {
+			drm_err(&uncore->i915->drm,
+				"Spurious OA head ptr: non-integral report offset\n");
 			break;
 		}
 
@@ -1110,7 +1117,7 @@ static int gen7_oa_read(struct i915_perf_stream *stream,
 	u32 oastatus1;
 	int ret;
 
-	if (WARN_ON(!stream->oa_buffer.vaddr))
+	if (drm_WARN_ON(&uncore->i915->drm, !stream->oa_buffer.vaddr))
 		return -EIO;
 
 	oastatus1 = intel_uncore_read(uncore, GEN7_OASTATUS1);
@@ -1303,8 +1310,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 			 * dropped by GuC. They won't be part of the context
 			 * ID in the OA reports, so squash those lower bits.
 			 */
-			stream->specific_ctx_id =
-				lower_32_bits(ce->lrc_desc) >> 12;
+			stream->specific_ctx_id = ce->lrc.lrca >> 12;
 
 			/*
 			 * GuC uses the top bit to signal proxy submission, so
@@ -1319,7 +1325,12 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 	case 12: {
 		stream->specific_ctx_id_mask =
 			((1U << GEN11_SW_CTX_ID_WIDTH) - 1) << (GEN11_SW_CTX_ID_SHIFT - 32);
-		stream->specific_ctx_id = stream->specific_ctx_id_mask;
+		/*
+		 * 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);
 		break;
 	}
 
@@ -1327,11 +1338,12 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 		MISSING_CASE(INTEL_GEN(ce->engine->i915));
 	}
 
-	ce->tag = stream->specific_ctx_id_mask;
+	ce->tag = stream->specific_ctx_id;
 
-	DRM_DEBUG_DRIVER("filtering on ctx_id=0x%x ctx_id_mask=0x%x\n",
-			 stream->specific_ctx_id,
-			 stream->specific_ctx_id_mask);
+	drm_dbg(&stream->perf->i915->drm,
+		"filtering on ctx_id=0x%x ctx_id_mask=0x%x\n",
+		stream->specific_ctx_id,
+		stream->specific_ctx_id_mask);
 
 	return 0;
 }
@@ -1391,8 +1403,10 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream)
 	/*
 	 * Unset exclusive_stream first, it will be checked while disabling
 	 * the metric set on gen8+.
+	 *
+	 * See i915_oa_init_reg_state() and lrc_configure_all_contexts()
 	 */
-	perf->exclusive_stream = NULL;
+	WRITE_ONCE(perf->exclusive_stream, NULL);
 	perf->ops.disable_metric_set(stream);
 
 	free_oa_buffer(stream);
@@ -1575,11 +1589,12 @@ 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 drm_i915_gem_object *bo;
 	struct i915_vma *vma;
 	int ret;
 
-	if (WARN_ON(stream->oa_buffer.vma))
+	if (drm_WARN_ON(&i915->drm, stream->oa_buffer.vma))
 		return -ENODEV;
 
 	BUILD_BUG_ON_NOT_POWER_OF_2(OA_BUFFER_SIZE);
@@ -1587,7 +1602,7 @@ static int alloc_oa_buffer(struct i915_perf_stream *stream)
 
 	bo = i915_gem_object_create_shmem(stream->perf->i915, OA_BUFFER_SIZE);
 	if (IS_ERR(bo)) {
-		DRM_ERROR("Failed to allocate OA buffer\n");
+		drm_err(&i915->drm, "Failed to allocate OA buffer\n");
 		return PTR_ERR(bo);
 	}
 
@@ -1669,7 +1684,8 @@ static int alloc_noa_wait(struct i915_perf_stream *stream)
 
 	bo = i915_gem_object_create_internal(i915, 4096);
 	if (IS_ERR(bo)) {
-		DRM_ERROR("Failed to allocate NOA wait batchbuffer\n");
+		drm_err(&i915->drm,
+			"Failed to allocate NOA wait batchbuffer\n");
 		return PTR_ERR(bo);
 	}
 
@@ -2184,7 +2200,9 @@ static int gen8_modify_self(struct intel_context *ce,
 	struct i915_request *rq;
 	int err;
 
+	intel_engine_pm_get(ce->engine);
 	rq = i915_request_create(ce);
+	intel_engine_pm_put(ce->engine);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
@@ -2653,7 +2671,8 @@ static void gen7_oa_disable(struct i915_perf_stream *stream)
 	if (intel_wait_for_register(uncore,
 				    GEN7_OACONTROL, GEN7_OACONTROL_ENABLE, 0,
 				    50))
-		DRM_ERROR("wait for OA to be disabled timed out\n");
+		drm_err(&stream->perf->i915->drm,
+			"wait for OA to be disabled timed out\n");
 }
 
 static void gen8_oa_disable(struct i915_perf_stream *stream)
@@ -2664,7 +2683,8 @@ static void gen8_oa_disable(struct i915_perf_stream *stream)
 	if (intel_wait_for_register(uncore,
 				    GEN8_OACONTROL, GEN8_OA_COUNTER_ENABLE, 0,
 				    50))
-		DRM_ERROR("wait for OA to be disabled timed out\n");
+		drm_err(&stream->perf->i915->drm,
+			"wait for OA to be disabled timed out\n");
 }
 
 static void gen12_oa_disable(struct i915_perf_stream *stream)
@@ -2676,7 +2696,16 @@ static void gen12_oa_disable(struct i915_perf_stream *stream)
 				    GEN12_OAG_OACONTROL,
 				    GEN12_OAG_OACONTROL_OA_COUNTER_ENABLE, 0,
 				    50))
-		DRM_ERROR("wait for OA to be disabled timed out\n");
+		drm_err(&stream->perf->i915->drm,
+			"wait for OA to be disabled timed out\n");
+
+	intel_uncore_write(uncore, GEN12_OA_TLB_INV_CR, 1);
+	if (intel_wait_for_register(uncore,
+				    GEN12_OA_TLB_INV_CR,
+				    1, 0,
+				    50))
+		drm_err(&stream->perf->i915->drm,
+			"wait for OA tlb invalidate timed out\n");
 }
 
 /**
@@ -2740,6 +2769,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 			       struct drm_i915_perf_open_param *param,
 			       struct perf_open_properties *props)
 {
+	struct drm_i915_private *i915 = stream->perf->i915;
 	struct i915_perf *perf = stream->perf;
 	int format_size;
 	int ret;
@@ -2796,7 +2826,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	stream->sample_size += format_size;
 
 	stream->oa_buffer.format_size = format_size;
-	if (WARN_ON(stream->oa_buffer.format_size == 0))
+	if (drm_WARN_ON(&i915->drm, stream->oa_buffer.format_size == 0))
 		return -EINVAL;
 
 	stream->hold_preemption = props->hold_preemption;
@@ -2849,7 +2879,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 		goto err_oa_buf_alloc;
 
 	stream->ops = &i915_oa_stream_ops;
-	perf->exclusive_stream = stream;
+	WRITE_ONCE(perf->exclusive_stream, stream);
 
 	ret = i915_perf_stream_enable_sync(stream);
 	if (ret) {
@@ -2869,7 +2899,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	return 0;
 
 err_enable:
-	perf->exclusive_stream = NULL;
+	WRITE_ONCE(perf->exclusive_stream, NULL);
 	perf->ops.disable_metric_set(stream);
 
 	free_oa_buffer(stream);
@@ -2895,12 +2925,11 @@ void i915_oa_init_reg_state(const struct intel_context *ce,
 {
 	struct i915_perf_stream *stream;
 
-	/* perf.exclusive_stream serialised by lrc_configure_all_contexts() */
-
 	if (engine->class != RENDER_CLASS)
 		return;
 
-	stream = engine->i915->perf.exclusive_stream;
+	/* perf.exclusive_stream serialised by lrc_configure_all_contexts() */
+	stream = READ_ONCE(engine->i915->perf.exclusive_stream);
 	/*
 	 * For gen12, only CTX_R_PWR_CLK_STATE needs update, but the caller
 	 * is already doing that, so nothing to be done for gen12 here.
@@ -2910,49 +2939,6 @@ void i915_oa_init_reg_state(const struct intel_context *ce,
 }
 
 /**
- * i915_perf_read_locked - &i915_perf_stream_ops->read with error normalisation
- * @stream: An i915 perf stream
- * @file: An i915 perf stream file
- * @buf: destination buffer given by userspace
- * @count: the number of bytes userspace wants to read
- * @ppos: (inout) file seek position (unused)
- *
- * Besides wrapping &i915_perf_stream_ops->read this provides a common place to
- * ensure that if we've successfully copied any data then reporting that takes
- * precedence over any internal error status, so the data isn't lost.
- *
- * For example ret will be -ENOSPC whenever there is more buffered data than
- * can be copied to userspace, but that's only interesting if we weren't able
- * to copy some data because it implies the userspace buffer is too small to
- * receive a single record (and we never split records).
- *
- * Another case with ret == -EFAULT is more of a grey area since it would seem
- * like bad form for userspace to ask us to overrun its buffer, but the user
- * knows best:
- *
- *   http://yarchive.net/comp/linux/partial_reads_writes.html
- *
- * Returns: The number of bytes copied or a negative error code on failure.
- */
-static ssize_t i915_perf_read_locked(struct i915_perf_stream *stream,
-				     struct file *file,
-				     char __user *buf,
-				     size_t count,
-				     loff_t *ppos)
-{
-	/* Note we keep the offset (aka bytes read) separate from any
-	 * error status so that the final check for whether we return
-	 * the bytes read with a higher precedence than any error (see
-	 * comment below) doesn't need to be handled/duplicated in
-	 * stream->ops->read() implementations.
-	 */
-	size_t offset = 0;
-	int ret = stream->ops->read(stream, buf, count, &offset);
-
-	return offset ?: (ret ?: -EAGAIN);
-}
-
-/**
  * i915_perf_read - handles read() FOP for i915 perf stream FDs
  * @file: An i915 perf stream file
  * @buf: destination buffer given by userspace
@@ -2977,7 +2963,8 @@ static ssize_t i915_perf_read(struct file *file,
 {
 	struct i915_perf_stream *stream = file->private_data;
 	struct i915_perf *perf = stream->perf;
-	ssize_t ret;
+	size_t offset = 0;
+	int ret;
 
 	/* To ensure it's handled consistently we simply treat all reads of a
 	 * disabled stream as an error. In particular it might otherwise lead
@@ -3000,13 +2987,12 @@ static ssize_t i915_perf_read(struct file *file,
 				return ret;
 
 			mutex_lock(&perf->lock);
-			ret = i915_perf_read_locked(stream, file,
-						    buf, count, ppos);
+			ret = stream->ops->read(stream, buf, count, &offset);
 			mutex_unlock(&perf->lock);
-		} while (ret == -EAGAIN);
+		} while (!offset && !ret);
 	} else {
 		mutex_lock(&perf->lock);
-		ret = i915_perf_read_locked(stream, file, buf, count, ppos);
+		ret = stream->ops->read(stream, buf, count, &offset);
 		mutex_unlock(&perf->lock);
 	}
 
@@ -3017,15 +3003,15 @@ static ssize_t i915_perf_read(struct file *file,
 	 * and read() returning -EAGAIN. Clearing the oa.pollin state here
 	 * effectively ensures we back off until the next hrtimer callback
 	 * before reporting another EPOLLIN event.
+	 * The exception to this is if ops->read() returned -ENOSPC which means
+	 * that more OA data is available than could fit in the user provided
+	 * buffer. In this case we want the next poll() call to not block.
 	 */
-	if (ret >= 0 || ret == -EAGAIN) {
-		/* Maybe make ->pollin per-stream state if we support multiple
-		 * concurrent streams in the future.
-		 */
+	if (ret != -ENOSPC)
 		stream->pollin = false;
-	}
 
-	return ret;
+	/* Possible values for ret are 0, -EFAULT, -ENOSPC, -EIO, ... */
+	return offset ?: (ret ?: -EAGAIN);
 }
 
 static enum hrtimer_restart oa_poll_check_timer_cb(struct hrtimer *hrtimer)