drm/i915/perf: allow for CS OA configs to be created lazily

Here we introduce a mechanism by which the execbuf part of the i915
driver will be able to request that a batch buffer containing the
programming for a particular OA config be created.

We'll execute these OA configuration buffers right before executing a
set of userspace commands so that a particular user batchbuffer be
executed with a given OA configuration.

This mechanism essentially allows the userspace driver to go through
several OA configuration without having to open/close the i915/perf
stream.

v2: No need for locking on object OA config object creation (Chris)
    Flush cpu mapping of OA config (Chris)

v3: Properly deal with the perf_metric lock (Chris/Lionel)

v4: Fix oa config unref/put when not found (Lionel)

v5: Allocate BOs for configurations on the stream instead of globally
    (Lionel)

v6: Fix 64bit division (Chris)

v7: Store allocated config BOs into the stream (Lionel)
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191012072308.30312-1-chris@chris-wilson.co.uk

drivers/gpu/drm/i915/gt/intel_gpu_commands.h

@@ -138,6 +138,7 @@
 /* Gen11+. addr = base + (ctx_restore ? offset & GENMASK(12,2) : offset) */
 #define   MI_LRI_CS_MMIO		(1<<19)
 #define   MI_LRI_FORCE_POSTED		(1<<12)
+#define MI_LOAD_REGISTER_IMM_MAX_REGS (126)
 #define MI_STORE_REGISTER_MEM        MI_INSTR(0x24, 1)
 #define MI_STORE_REGISTER_MEM_GEN8   MI_INSTR(0x24, 2)
 #define   MI_SRM_LRM_GLOBAL_GTT		(1<<22)

drivers/gpu/drm/i915/i915_perf.c

@@ -369,52 +369,52 @@ struct perf_open_properties {
 	struct intel_engine_cs *engine;
 };
 
+struct i915_oa_config_bo {
+	struct llist_node node;
+
+	struct i915_oa_config *oa_config;
+	struct i915_vma *vma;
+};
+
 static enum hrtimer_restart oa_poll_check_timer_cb(struct hrtimer *hrtimer);
 
-static void free_oa_config(struct i915_oa_config *oa_config)
+void i915_oa_config_release(struct kref *ref)
 {
+	struct i915_oa_config *oa_config =
+		container_of(ref, typeof(*oa_config), ref);
+
 	if (!PTR_ERR(oa_config->flex_regs))
 		kfree(oa_config->flex_regs);
 	if (!PTR_ERR(oa_config->b_counter_regs))
 		kfree(oa_config->b_counter_regs);
 	if (!PTR_ERR(oa_config->mux_regs))
 		kfree(oa_config->mux_regs);
-	kfree(oa_config);
-}
-
-static void put_oa_config(struct i915_oa_config *oa_config)
-{
-	if (!atomic_dec_and_test(&oa_config->ref_count))
-		return;
 
-	free_oa_config(oa_config);
+	kfree_rcu(oa_config, rcu);
 }
 
-static int get_oa_config(struct i915_perf *perf,
-			 int metrics_set,
-			 struct i915_oa_config **out_config)
+struct i915_oa_config *
+i915_perf_get_oa_config(struct i915_perf *perf, int metrics_set)
 {
-	int ret;
-
-	if (metrics_set == 1) {
-		*out_config = &perf->test_config;
-		atomic_inc(&perf->test_config.ref_count);
-		return 0;
-	}
-
-	ret = mutex_lock_interruptible(&perf->metrics_lock);
-	if (ret)
-		return ret;
+	struct i915_oa_config *oa_config;
 
-	*out_config = idr_find(&perf->metrics_idr, metrics_set);
-	if (!*out_config)
-		ret = -EINVAL;
+	rcu_read_lock();
+	if (metrics_set == 1)
+		oa_config = &perf->test_config;
 	else
-		atomic_inc(&(*out_config)->ref_count);
+		oa_config = idr_find(&perf->metrics_idr, metrics_set);
+	if (oa_config)
+		oa_config = i915_oa_config_get(oa_config);
+	rcu_read_unlock();
 
-	mutex_unlock(&perf->metrics_lock);
+	return oa_config;
+}
 
-	return ret;
+static void free_oa_config_bo(struct i915_oa_config_bo *oa_bo)
+{
+	i915_oa_config_put(oa_bo->oa_config);
+	i915_vma_put(oa_bo->vma);
+	kfree(oa_bo);
 }
 
 static u32 gen8_oa_hw_tail_read(struct i915_perf_stream *stream)
@@ -1337,6 +1337,16 @@ free_oa_buffer(struct i915_perf_stream *stream)
 	stream->oa_buffer.vaddr = NULL;
 }
 
+static void
+free_oa_configs(struct i915_perf_stream *stream)
+{
+	struct i915_oa_config_bo *oa_bo, *tmp;
+
+	i915_oa_config_put(stream->oa_config);
+	llist_for_each_entry_safe(oa_bo, tmp, stream->oa_config_bos.first, node)
+		free_oa_config_bo(oa_bo);
+}
+
 static void i915_oa_stream_destroy(struct i915_perf_stream *stream)
 {
 	struct i915_perf *perf = stream->perf;
@@ -1358,7 +1368,7 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream)
 	if (stream->ctx)
 		oa_put_render_ctx_id(stream);
 
-	put_oa_config(stream->oa_config);
+	free_oa_configs(stream);
 
 	if (perf->spurious_report_rs.missed) {
 		DRM_NOTE("%d spurious OA report notices suppressed due to ratelimiting\n",
@@ -1505,10 +1515,6 @@ static int alloc_oa_buffer(struct i915_perf_stream *stream)
 		goto err_unpin;
 	}
 
-	DRM_DEBUG_DRIVER("OA Buffer initialized, gtt offset = 0x%x, vaddr = %p\n",
-			 i915_ggtt_offset(stream->oa_buffer.vma),
-			 stream->oa_buffer.vaddr);
-
 	return 0;
 
 err_unpin:
@@ -2200,9 +2206,10 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 		}
 	}
 
-	ret = get_oa_config(perf, props->metrics_set, &stream->oa_config);
-	if (ret) {
+	stream->oa_config = i915_perf_get_oa_config(perf, props->metrics_set);
+	if (!stream->oa_config) {
 		DRM_DEBUG("Invalid OA config id=%i\n", props->metrics_set);
+		ret = -EINVAL;
 		goto err_config;
 	}
 
@@ -2234,6 +2241,9 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 		goto err_enable;
 	}
 
+	DRM_DEBUG("opening stream oa config uuid=%s\n",
+		  stream->oa_config->uuid);
+
 	hrtimer_init(&stream->poll_check_timer,
 		     CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	stream->poll_check_timer.function = oa_poll_check_timer_cb;
@@ -2249,7 +2259,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	free_oa_buffer(stream);
 
 err_oa_buf_alloc:
-	put_oa_config(stream->oa_config);
+	free_oa_configs(stream);
 
 	intel_uncore_forcewake_put(stream->uncore, FORCEWAKE_ALL);
 	intel_engine_pm_put(stream->engine);
@@ -3057,7 +3067,8 @@ void i915_perf_register(struct drm_i915_private *i915)
 	if (ret)
 		goto sysfs_error;
 
-	atomic_set(&perf->test_config.ref_count, 1);
+	perf->test_config.perf = perf;
+	kref_init(&perf->test_config.ref);
 
 	goto exit;
 
@@ -3315,7 +3326,8 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,
 		return -ENOMEM;
 	}
 
-	atomic_set(&oa_config->ref_count, 1);
+	oa_config->perf = perf;
+	kref_init(&oa_config->ref);
 
 	if (!uuid_is_valid(args->uuid)) {
 		DRM_DEBUG("Invalid uuid format for OA config\n");
@@ -3414,7 +3426,7 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,
 sysfs_err:
 	mutex_unlock(&perf->metrics_lock);
 reg_err:
-	put_oa_config(oa_config);
+	i915_oa_config_put(oa_config);
 	DRM_DEBUG("Failed to add new OA config\n");
 	return err;
 }
@@ -3450,13 +3462,13 @@ int i915_perf_remove_config_ioctl(struct drm_device *dev, void *data,
 
 	ret = mutex_lock_interruptible(&perf->metrics_lock);
 	if (ret)
-		goto lock_err;
+		return ret;
 
 	oa_config = idr_find(&perf->metrics_idr, *arg);
 	if (!oa_config) {
 		DRM_DEBUG("Failed to remove unknown OA config\n");
 		ret = -ENOENT;
-		goto config_err;
+		goto err_unlock;
 	}
 
 	GEM_BUG_ON(*arg != oa_config->id);
@@ -3466,13 +3478,16 @@ int i915_perf_remove_config_ioctl(struct drm_device *dev, void *data,
 
 	idr_remove(&perf->metrics_idr, *arg);
 
+	mutex_unlock(&perf->metrics_lock);
+
 	DRM_DEBUG("Removed config %s id=%i\n", oa_config->uuid, oa_config->id);
 
-	put_oa_config(oa_config);
+	i915_oa_config_put(oa_config);
+
+	return 0;
 
-config_err:
+err_unlock:
 	mutex_unlock(&perf->metrics_lock);
-lock_err:
 	return ret;
 }
 
@@ -3642,7 +3657,7 @@ void i915_perf_init(struct drm_i915_private *i915)
 
 static int destroy_config(int id, void *p, void *data)
 {
-	put_oa_config(p);
+	i915_oa_config_put(p);
 	return 0;
 }
 

drivers/gpu/drm/i915/i915_perf.h

@@ -6,6 +6,7 @@
 #ifndef __I915_PERF_H__
 #define __I915_PERF_H__
 
+#include <linux/kref.h>
 #include <linux/types.h>
 
 #include "i915_perf_types.h"
@@ -13,6 +14,7 @@
 struct drm_device;
 struct drm_file;
 struct drm_i915_private;
+struct i915_oa_config;
 struct intel_context;
 struct intel_engine_cs;
 
@@ -27,7 +29,29 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,
 			       struct drm_file *file);
 int i915_perf_remove_config_ioctl(struct drm_device *dev, void *data,
 				  struct drm_file *file);
+
 void i915_oa_init_reg_state(const struct intel_context *ce,
 			    const struct intel_engine_cs *engine);
 
+struct i915_oa_config *
+i915_perf_get_oa_config(struct i915_perf *perf, int metrics_set);
+
+static inline struct i915_oa_config *
+i915_oa_config_get(struct i915_oa_config *oa_config)
+{
+	if (kref_get_unless_zero(&oa_config->ref))
+		return oa_config;
+	else
+		return NULL;
+}
+
+void i915_oa_config_release(struct kref *ref);
+static inline void i915_oa_config_put(struct i915_oa_config *oa_config)
+{
+	if (!oa_config)
+		return;
+
+	kref_put(&oa_config->ref, i915_oa_config_release);
+}
+
 #endif /* __I915_PERF_H__ */

drivers/gpu/drm/i915/i915_perf_types.h

@@ -9,7 +9,7 @@
 #include <linux/atomic.h>
 #include <linux/device.h>
 #include <linux/hrtimer.h>
-#include <linux/list.h>
+#include <linux/llist.h>
 #include <linux/poll.h>
 #include <linux/sysfs.h>
 #include <linux/types.h>
@@ -22,6 +22,7 @@
 struct drm_i915_private;
 struct file;
 struct i915_gem_context;
+struct i915_perf;
 struct i915_vma;
 struct intel_context;
 struct intel_engine_cs;
@@ -37,6 +38,8 @@ struct i915_oa_reg {
 };
 
 struct i915_oa_config {
+	struct i915_perf *perf;
+
 	char uuid[UUID_STRING_LEN + 1];
 	int id;
 
@@ -51,7 +54,8 @@ struct i915_oa_config {
 	struct attribute *attrs[2];
 	struct device_attribute sysfs_metric_id;
 
-	atomic_t ref_count;
+	struct kref ref;
+	struct rcu_head rcu;
 };
 
 struct i915_perf_stream;
@@ -177,6 +181,12 @@ struct i915_perf_stream {
 	 */
 	struct i915_oa_config *oa_config;
 
+	/**
+	 * @oa_config_bos: A list of struct i915_oa_config_bo allocated lazily
+	 * each time @oa_config changes.
+	 */
+	struct llist_head oa_config_bos;
+
 	/**
 	 * @pinned_ctx: The OA context specific information.
 	 */
@@ -331,13 +341,13 @@ struct i915_perf {
 
 	/*
 	 * Lock associated with adding/modifying/removing OA configs
-	 * in dev_priv->perf.metrics_idr.
+	 * in perf->metrics_idr.
 	 */
 	struct mutex metrics_lock;
 
 	/*
-	 * List of dynamic configurations, you need to hold
-	 * dev_priv->perf.metrics_lock to access it.
+	 * List of dynamic configurations (struct i915_oa_config), you
+	 * need to hold perf->metrics_lock to access it.
 	 */
 	struct idr metrics_idr;
 
@@ -350,8 +360,7 @@ struct i915_perf {
 	/*
 	 * The stream currently using the OA unit. If accessed
 	 * outside a syscall associated to its file
-	 * descriptor, you need to hold
-	 * dev_priv->drm.struct_mutex.
+	 * descriptor.
 	 */
 	struct i915_perf_stream *exclusive_stream;