Userspace can aggregate if it wishes to do so but kernel side should not.
+
+- drm-purgeable-memory: <uint> [KiB|MiB]
+
+The total size of buffers that are purgeable.
+
+- drm-active-memory: <uint> [KiB|MiB]
+
+The total size of buffers that are active on one or more rings.
+
- drm-cycles-<str> <uint>
Engine identifier string must be the same as the one specified in the
diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c
index 37dfaa6be560..46fdd843bb3a 100644
--- a/drivers/gpu/drm/drm_file.c
+++ b/drivers/gpu/drm/drm_file.c
@@ -42,6 +42,7 @@
#include <drm/drm_client.h>
#include <drm/drm_drv.h>
#include <drm/drm_file.h>
+#include <drm/drm_gem.h>
#include <drm/drm_print.h>
#include "drm_crtc_internal.h"
@@ -871,6 +872,79 @@ void drm_send_event(struct drm_device *dev, struct
drm_pending_event *e)
}
EXPORT_SYMBOL(drm_send_event);
+static void print_size(struct drm_printer *p, const char *stat, size_t sz)
+{
+ const char *units[] = {"", " KiB", " MiB"};
+ unsigned u;
+
+ for (u = 0; u < ARRAY_SIZE(units) - 1; u++) {
+ if (sz < SZ_1K)
+ break;
+ sz = div_u64(sz, SZ_1K);
+ }
+
+ drm_printf(p, "%s:\t%zu%s\n", stat, sz, units[u]);
+}
+
+static void print_memory_stats(struct drm_printer *p, struct drm_file *file)
+{
+ struct drm_gem_object *obj;
+ struct {
+ size_t shared;
+ size_t private;
+ size_t resident;
+ size_t purgeable;
+ size_t active;
+ } size = {0};
+ bool has_status = false;
+ int id;
+
+ spin_lock(&file->table_lock);
+ idr_for_each_entry (&file->object_idr, obj, id) {
+ enum drm_gem_object_status s = 0;
+
+ if (obj->funcs && obj->funcs->status) {
+ s = obj->funcs->status(obj);
+ has_status = true;
+ }
+
+ if (obj->handle_count > 1) {
+ size.shared += obj->size;
+ } else {
+ size.private += obj->size;
+ }
+
+ if (s & DRM_GEM_OBJECT_RESIDENT) {
+ size.resident += obj->size;
+ } else {
+ /* If already purged or not yet backed by pages, don't
+ * count it as purgeable:
+ */
+ s &= ~DRM_GEM_OBJECT_PURGEABLE;
Side question - why couldn't resident buffers be purgeable? Did you mean
for the if branch check to be active here? But then it wouldn't make
sense for a driver to report active _and_ purgeable..
+ }
+
+ if (!dma_resv_test_signaled(obj->resv, dma_resv_usage_rw(true))) {
+ size.active += obj->size;
+
+ /* If still active, don't count as purgeable: */
+ s &= ~DRM_GEM_OBJECT_PURGEABLE;
Another side question - I guess this tidies a race in reporting? If so
not sure it matters given the stats are all rather approximate.
+ }
+
+ if (s & DRM_GEM_OBJECT_PURGEABLE)
+ size.purgeable += obj->size;
+ }
One concern I have here is that it is all based on obj->size. That is,
there is no provision for drivers to implement page level granularity.
So correct reporting in use cases such as VM BIND in the future wouldn't
work unless it was a driver hook to get almost all of the info above. At
which point common code is just a loop. TBF I don't know if any drivers
do sub obj->size backing store granularity today, but I think it is
sometimes to be sure of before proceeding.
Second concern is what I touched upon in the first reply block - if the
common code blindly loops over all objects then on discrete GPUs it
seems we get an 'aggregate' value here which is not what I think we
want. We rather want to have the ability for drivers to list stats per
individual memory region.
+ spin_unlock(&file->table_lock);
+
+ print_size(p, "drm-shared-memory", size.shared);
+ print_size(p, "drm-private-memory", size.private);
+ print_size(p, "drm-active-memory", size.active);
+
+ if (has_status) {
+ print_size(p, "drm-resident-memory", size.resident);
+ print_size(p, "drm-purgeable-memory", size.purgeable);
+ }
+}
+
/**
* drm_fop_show_fdinfo - helper for drm file fops
* @seq_file: output stream
@@ -904,6 +978,8 @@ void drm_fop_show_fdinfo(struct seq_file *m, struct file *f)
if (dev->driver->show_fdinfo)
dev->driver->show_fdinfo(&p, file);
+
+ print_memory_stats(&p, file);
}
EXPORT_SYMBOL(drm_fop_show_fdinfo);
diff --git a/include/drm/drm_file.h b/include/drm/drm_file.h
index dfa995b787e1..e5b40084538f 100644
--- a/include/drm/drm_file.h
+++ b/include/drm/drm_file.h
@@ -41,6 +41,7 @@
struct dma_fence;
struct drm_file;
struct drm_device;
+struct drm_printer;
struct device;
struct file;
diff --git a/include/drm/drm_gem.h b/include/drm/drm_gem.h
index 189fd618ca65..213917bb6b11 100644
--- a/include/drm/drm_gem.h
+++ b/include/drm/drm_gem.h
@@ -42,6 +42,14 @@
struct iosys_map;
struct drm_gem_object;
+/**
+ * enum drm_gem_object_status - bitmask of object state for fdinfo reporting
+ */
+enum drm_gem_object_status {
+ DRM_GEM_OBJECT_RESIDENT = BIT(0),
+ DRM_GEM_OBJECT_PURGEABLE = BIT(1),
+};
+
/**
* struct drm_gem_object_funcs - GEM object functions
*/
@@ -174,6 +182,17 @@ struct drm_gem_object_funcs {
*/
int (*evict)(struct drm_gem_object *obj);
+ /**
+ * @status:
+ *
+ * The optional status callback can return additional object state
+ * which determines which stats the object is counted against. The
+ * callback is called under table_lock. Racing against object status
+ * change is "harmless", and the callback can expect to not race
+ * against object destruction.
+ */
+ enum drm_gem_object_status (*status)(struct drm_gem_object *obj);
Does this needs to be in object funcs and couldn't be consolidated to
driver level?
Regards,
Tvrtko
+
/**
* @vm_ops:
*
