drm/msm: Add GPU memory traces

Perfetto can use these traces to track global and per-process GPU memory
usage.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Patchwork: https://patchwork.freedesktop.org/patch/580854/

4 files changed, 51 insertions, 0 deletions

diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig
index 1931ecf73e32..26a4c71da63a 100644
--- a/drivers/gpu/drm/msm/Kconfig
+++ b/drivers/gpu/drm/msm/Kconfig
@@ -33,6 +33,7 @@ config DRM_MSM
 	select PM_OPP
 	select NVMEM
 	select PM_GENERIC_DOMAINS
+	select TRACE_GPU_MEM
 	help
 	  DRM/KMS driver for MSM/snapdragon.
 
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index 912ebaa5df84..e256d72adddd 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -128,6 +128,11 @@ struct msm_drm_private {
 	struct msm_perf_state *perf;
 
 	/**
+	 * total_mem: Total/global amount of memory backing GEM objects.
+	 */
+	atomic64_t total_mem;
+
+	/**
 	 * List of all GEM objects (mainly for debugfs, protected by obj_lock
 	 * (acquire before per GEM object lock)
 	 */
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index a5c6498a43f0..ddc6a131c041 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -12,6 +12,9 @@
 #include <linux/pfn_t.h>
 
 #include <drm/drm_prime.h>
+#include <drm/drm_file.h>
+
+#include <trace/events/gpu_mem.h>
 
 #include "msm_drv.h"
 #include "msm_fence.h"
@@ -33,6 +36,34 @@ static bool use_pages(struct drm_gem_object *obj)
 	return !msm_obj->vram_node;
 }
 
+static void update_device_mem(struct msm_drm_private *priv, ssize_t size)
+{
+	uint64_t total_mem = atomic64_add_return(size, &priv->total_mem);
+	trace_gpu_mem_total(0, 0, total_mem);
+}
+
+static void update_ctx_mem(struct drm_file *file, ssize_t size)
+{
+	struct msm_file_private *ctx = file->driver_priv;
+	uint64_t ctx_mem = atomic64_add_return(size, &ctx->ctx_mem);
+
+	rcu_read_lock(); /* Locks file->pid! */
+	trace_gpu_mem_total(0, pid_nr(file->pid), ctx_mem);
+	rcu_read_unlock();
+
+}
+
+static int msm_gem_open(struct drm_gem_object *obj, struct drm_file *file)
+{
+	update_ctx_mem(file, obj->size);
+	return 0;
+}
+
+static void msm_gem_close(struct drm_gem_object *obj, struct drm_file *file)
+{
+	update_ctx_mem(file, -obj->size);
+}
+
 /*
  * Cache sync.. this is a bit over-complicated, to fit dma-mapping
  * API.  Really GPU cache is out of scope here (handled on cmdstream)
@@ -156,6 +187,8 @@ static struct page **get_pages(struct drm_gem_object *obj)
 			return p;
 		}
 
+		update_device_mem(dev->dev_private, obj->size);
+
 		msm_obj->pages = p;
 
 		msm_obj->sgt = drm_prime_pages_to_sg(obj->dev, p, npages);
@@ -209,6 +242,8 @@ static void put_pages(struct drm_gem_object *obj)
 			msm_obj->sgt = NULL;
 		}
 
+		update_device_mem(obj->dev->dev_private, -obj->size);
+
 		if (use_pages(obj))
 			drm_gem_put_pages(obj, msm_obj->pages, true, false);
 		else
@@ -1118,6 +1153,8 @@ static const struct vm_operations_struct vm_ops = {
 
 static const struct drm_gem_object_funcs msm_gem_object_funcs = {
 	.free = msm_gem_free_object,
+	.open = msm_gem_open,
+	.close = msm_gem_close,
 	.pin = msm_gem_prime_pin,
 	.unpin = msm_gem_prime_unpin,
 	.get_sg_table = msm_gem_prime_get_sg_table,
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index a0c1bd6d1d5b..0c2c574b76fd 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -428,6 +428,14 @@ struct msm_file_private {
 	 * level.
 	 */
 	struct drm_sched_entity *entities[NR_SCHED_PRIORITIES * MSM_GPU_MAX_RINGS];
+
+	/**
+	 * ctx_mem:
+	 *
+	 * Total amount of memory of GEM buffers with handles attached for
+	 * this context.
+	 */
+	atomic64_t ctx_mem;
 };
 
 /**