drm: Add fdinfo memory stats

Add support to dump GEM stats to fdinfo.

v2: Fix typos, change size units to match docs, use div_u64
v3: Do it in core
v4: more kerneldoc
v5: doc fixes
v6: Actually use u64, bit more comment docs

Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Emil Velikov <emil.l.velikov@gmail.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Acked-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Acked-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20230524155956.382440-6-robdclark@gmail.com

4 files changed, 200 insertions, 13 deletions

diff --git a/Documentation/gpu/drm-usage-stats.rst b/Documentation/gpu/drm-usage-stats.rst
index 552195fb1ea3..d012eb56885e 100644
--- a/Documentation/gpu/drm-usage-stats.rst
+++ b/Documentation/gpu/drm-usage-stats.rst
@@ -52,6 +52,9 @@ String shall contain the name this driver registered as via the respective
 Optional fully standardised keys
 --------------------------------
 
+Identification
+^^^^^^^^^^^^^^
+
 - drm-pdev: <aaaa:bb.cc.d>
 
 For PCI devices this should contain the PCI slot address of the device in
@@ -69,6 +72,9 @@ scope of each device, in which case `drm-pdev` shall be present as well.
 Userspace should make sure to not double account any usage statistics by using
 the above described criteria in order to associate data to individual clients.
 
+Utilization
+^^^^^^^^^^^
+
 - drm-engine-<str>: <uint> ns
 
 GPUs usually contain multiple execution engines. Each shall be given a stable
@@ -93,18 +99,6 @@ exported engine corresponds to a group of identical hardware engines.
 In the absence of this tag parser shall assume capacity of one. Zero capacity
 is not allowed.
 
-- drm-memory-<str>: <uint> [KiB|MiB]
-
-Each possible memory type which can be used to store buffer objects by the
-GPU in question shall be given a stable and unique name to be returned as the
-string here.
-
-Value shall reflect the amount of storage currently consumed by the buffer
-object belong to this client, in the respective memory region.
-
-Default unit shall be bytes with optional unit specifiers of 'KiB' or 'MiB'
-indicating kibi- or mebi-bytes.
-
 - drm-cycles-<str>: <uint>
 
 Engine identifier string must be the same as the one specified in the
@@ -126,6 +120,42 @@ percentage utilization of the engine, whereas drm-engine-<str> only reflects
 time active without considering what frequency the engine is operating as a
 percentage of it's maximum frequency.
 
+Memory
+^^^^^^
+
+- drm-memory-<region>: <uint> [KiB|MiB]
+
+Each possible memory type which can be used to store buffer objects by the
+GPU in question shall be given a stable and unique name to be returned as the
+string here.  The name "memory" is reserved to refer to normal system memory.
+
+Value shall reflect the amount of storage currently consumed by the buffer
+objects belong to this client, in the respective memory region.
+
+Default unit shall be bytes with optional unit specifiers of 'KiB' or 'MiB'
+indicating kibi- or mebi-bytes.
+
+- drm-shared-<region>: <uint> [KiB|MiB]
+
+The total size of buffers that are shared with another file (ie. have more
+than a single handle).
+
+- drm-total-<region>: <uint> [KiB|MiB]
+
+The total size of buffers that including shared and private memory.
+
+- drm-resident-<region>: <uint> [KiB|MiB]
+
+The total size of buffers that are resident in the specified region.
+
+- drm-purgeable-<region>: <uint> [KiB|MiB]
+
+The total size of buffers that are purgeable.
+
+- drm-active-<region>: <uint> [KiB|MiB]
+
+The total size of buffers that are active on one or more engines.
+
 Implementation Details
 ======================
 
diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c
index 37b4f76a5191..883d83bc0e3d 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"
@@ -871,9 +872,105 @@ 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,
+		       const char *region, u64 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, "drm-%s-%s:\t%llu%s\n", stat, region, sz, units[u]);
+}
+
+/**
+ * drm_print_memory_stats - A helper to print memory stats
+ * @p: The printer to print output to
+ * @stats: The collected memory stats
+ * @supported_status: Bitmask of optional stats which are available
+ * @region: The memory region
+ *
+ */
+void drm_print_memory_stats(struct drm_printer *p,
+			    const struct drm_memory_stats *stats,
+			    enum drm_gem_object_status supported_status,
+			    const char *region)
+{
+	print_size(p, "total", region, stats->private + stats->shared);
+	print_size(p, "shared", region, stats->shared);
+	print_size(p, "active", region, stats->active);
+
+	if (supported_status & DRM_GEM_OBJECT_RESIDENT)
+		print_size(p, "resident", region, stats->resident);
+
+	if (supported_status & DRM_GEM_OBJECT_PURGEABLE)
+		print_size(p, "purgeable", region, stats->purgeable);
+}
+EXPORT_SYMBOL(drm_print_memory_stats);
+
+/**
+ * drm_show_memory_stats - Helper to collect and show standard fdinfo memory stats
+ * @p: the printer to print output to
+ * @file: the DRM file
+ *
+ * Helper to iterate over GEM objects with a handle allocated in the specified
+ * file.
+ */
+void drm_show_memory_stats(struct drm_printer *p, struct drm_file *file)
+{
+	struct drm_gem_object *obj;
+	struct drm_memory_stats status = {};
+	enum drm_gem_object_status supported_status;
+	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);
+			supported_status = DRM_GEM_OBJECT_RESIDENT |
+					DRM_GEM_OBJECT_PURGEABLE;
+		}
+
+		if (obj->handle_count > 1) {
+			status.shared += obj->size;
+		} else {
+			status.private += obj->size;
+		}
+
+		if (s & DRM_GEM_OBJECT_RESIDENT) {
+			status.resident += obj->size;
+		} else {
+			/* If already purged or not yet backed by pages, don't
+			 * count it as purgeable:
+			 */
+			s &= ~DRM_GEM_OBJECT_PURGEABLE;
+		}
+
+		if (!dma_resv_test_signaled(obj->resv, dma_resv_usage_rw(true))) {
+			status.active += obj->size;
+
+			/* If still active, don't count as purgeable: */
+			s &= ~DRM_GEM_OBJECT_PURGEABLE;
+		}
+
+		if (s & DRM_GEM_OBJECT_PURGEABLE)
+			status.purgeable += obj->size;
+	}
+	spin_unlock(&file->table_lock);
+
+	drm_print_memory_stats(p, &status, supported_status, "memory");
+}
+EXPORT_SYMBOL(drm_show_memory_stats);
+
 /**
  * drm_show_fdinfo - helper for drm file fops
- * @seq_file: output stream
+ * @m: output stream
  * @f: the device file instance
  *
  * Helper to implement fdinfo, for userspace to query usage stats, etc, of a
diff --git a/include/drm/drm_file.h b/include/drm/drm_file.h
index 7d9b3c65cbc1..966912053cb0 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;
 
@@ -441,6 +442,33 @@ void drm_send_event(struct drm_device *dev, struct drm_pending_event *e);
 void drm_send_event_timestamp_locked(struct drm_device *dev,
 				     struct drm_pending_event *e,
 				     ktime_t timestamp);
+
+/**
+ * struct drm_memory_stats - GEM object stats associated
+ * @shared: Total size of GEM objects shared between processes
+ * @private: Total size of GEM objects
+ * @resident: Total size of GEM objects backing pages
+ * @purgeable: Total size of GEM objects that can be purged (resident and not active)
+ * @active: Total size of GEM objects active on one or more engines
+ *
+ * Used by drm_print_memory_stats()
+ */
+struct drm_memory_stats {
+	u64 shared;
+	u64 private;
+	u64 resident;
+	u64 purgeable;
+	u64 active;
+};
+
+enum drm_gem_object_status;
+
+void drm_print_memory_stats(struct drm_printer *p,
+			    const struct drm_memory_stats *stats,
+			    enum drm_gem_object_status supported_status,
+			    const char *region);
+
+void drm_show_memory_stats(struct drm_printer *p, struct drm_file *file);
 void drm_show_fdinfo(struct seq_file *m, struct file *f);
 
 struct file *mock_drm_getfile(struct drm_minor *minor, unsigned int flags);
diff --git a/include/drm/drm_gem.h b/include/drm/drm_gem.h
index b8efd836edef..bbc721870c13 100644
--- a/include/drm/drm_gem.h
+++ b/include/drm/drm_gem.h
@@ -43,6 +43,25 @@ struct iosys_map;
 struct drm_gem_object;
 
 /**
+ * enum drm_gem_object_status - bitmask of object state for fdinfo reporting
+ * @DRM_GEM_OBJECT_RESIDENT: object is resident in memory (ie. not unpinned)
+ * @DRM_GEM_OBJECT_PURGEABLE: object marked as purgeable by userspace
+ *
+ * Bitmask of status used for fdinfo memory stats, see &drm_gem_object_funcs.status
+ * and drm_show_fdinfo().  Note that an object can DRM_GEM_OBJECT_PURGEABLE if
+ * it still active or not resident, in which case drm_show_fdinfo() will not
+ * account for it as purgeable.  So drivers do not need to check if the buffer
+ * is idle and resident to return this bit.  (Ie. userspace can mark a buffer
+ * as purgeable even while it is still busy on the GPU.. it does not _actually_
+ * become puregeable until it becomes idle.  The status gem object func does
+ * not need to consider this.)
+ */
+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
  */
 struct drm_gem_object_funcs {
@@ -175,6 +194,19 @@ 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.
+	 *
+	 * Called by drm_show_memory_stats().
+	 */
+	enum drm_gem_object_status (*status)(struct drm_gem_object *obj);
+
+	/**
 	 * @vm_ops:
 	 *
 	 * Virtual memory operations used with mmap.