[Intel-gfx] [PATCH v4 0/5] fdinfo memory stats

[Intel-gfx] [PATCH v4 0/5] fdinfo memory stats

[Tvrtko Ursulin]

From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

I added tracking of most classes of objects which contribute to client's memory
footprint and accouting along the similar lines as in Rob's msm code. Then
printing it out to fdinfo using the drm helper Rob added.

Accounting by keeping per client lists may not be the most effient method,
perhaps we should simply add and subtract stats directly at convenient sites,
but that too is not straightforward due no existing connection between buffer
objects and clients. Possibly some other tricky bits in the buffer sharing
deparment. So lets see if this works for now. Infrequent reader penalty should
not be too bad (may be even useful to dump the lists in debugfs?) and additional
list_head per object pretty much drowns in the noise.

Example fdinfo with the series applied:

# cat /proc/1383/fdinfo/8
pos:    0
flags:  02100002
mnt_id: 21
ino:    397
drm-driver:     i915
drm-client-id:  18
drm-pdev:       0000:00:02.0
drm-total-system:       125 MiB
drm-shared-system:      16 MiB
drm-active-system:      110 MiB
drm-resident-system:    125 MiB
drm-purgeable-system:   2 MiB
drm-total-stolen-system:        0
drm-shared-stolen-system:       0
drm-active-stolen-system:       0
drm-resident-stolen-system:     0
drm-purgeable-stolen-system:    0
drm-engine-render:      25662044495 ns
drm-engine-copy:        0 ns
drm-engine-video:       0 ns
drm-engine-video-enhance:       0 ns

Example gputop output (local patches currently):

DRM minor 0
 PID     SMEM  SMEMRSS   render     copy     video    NAME
1233     124M     124M |████████||        ||        ||        | neverball
1130      59M      59M |█▌      ||        ||        ||        | Xorg
1207      12M      12M |        ||        ||        ||        | xfwm4

v2:
 * Now actually per client.

v3:
 * Track imported dma-buf objects.

v4:
 * Rely on DRM GEM handles for tracking user objects.
 * Fix internal object accounting (no placements).

Tvrtko Ursulin (5):
  drm/i915: Add ability for tracking buffer objects per client
  drm/i915: Record which client owns a VM
  drm/i915: Track page table backing store usage
  drm/i915: Account ring buffer and context state storage
  drm/i915: Implement fdinfo memory stats printing

 drivers/gpu/drm/i915/gem/i915_gem_context.c   |  11 +-
 .../gpu/drm/i915/gem/i915_gem_context_types.h |   3 +
 drivers/gpu/drm/i915/gem/i915_gem_object.c    |   5 +
 .../gpu/drm/i915/gem/i915_gem_object_types.h  |  12 ++
 .../gpu/drm/i915/gem/selftests/mock_context.c |   4 +-
 drivers/gpu/drm/i915/gt/intel_context.c       |   8 ++
 drivers/gpu/drm/i915/gt/intel_gtt.c           |   6 +
 drivers/gpu/drm/i915/gt/intel_gtt.h           |   1 +
 drivers/gpu/drm/i915/i915_drm_client.c        | 124 +++++++++++++++++-
 drivers/gpu/drm/i915/i915_drm_client.h        |  42 +++++-
 drivers/gpu/drm/i915/i915_gem.c               |   2 +-
 11 files changed, 210 insertions(+), 8 deletions(-)

-- 
2.39.2

[Intel-gfx] [PATCH 1/5] drm/i915: Add ability for tracking buffer objects per client

[Tvrtko Ursulin]

From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

In order to show per client memory usage lets add some infrastructure
which enables tracking buffer objects owned by clients.

We add a per client list protected by a new per client lock and to support
delayed destruction (post client exit) we make tracked objects hold
references to the owning client.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 drivers/gpu/drm/i915/gem/i915_gem_object.c    |  5 +++
 .../gpu/drm/i915/gem/i915_gem_object_types.h  | 12 +++++++
 drivers/gpu/drm/i915/i915_drm_client.c        | 36 ++++++++++++++++++-
 drivers/gpu/drm/i915/i915_drm_client.h        | 34 +++++++++++++++++-
 drivers/gpu/drm/i915/i915_gem.c               |  2 +-
 5 files changed, 86 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c
index 97ac6fb37958..d6961f6818f1 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c
@@ -105,6 +105,10 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj,
 
 	INIT_LIST_HEAD(&obj->mm.link);
 
+#ifdef CONFIG_PROC_FS
+	INIT_LIST_HEAD(&obj->client_link);
+#endif
+
 	INIT_LIST_HEAD(&obj->lut_list);
 	spin_lock_init(&obj->lut_lock);
 
@@ -410,6 +414,7 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915,
 		}
 
 		__i915_gem_object_pages_fini(obj);
+		i915_drm_client_remove_object(obj);
 		__i915_gem_free_object(obj);
 
 		/* But keep the pointer alive for RCU-protected lookups */
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index e72c57716bee..8de2b91b3edf 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -300,6 +300,18 @@ struct drm_i915_gem_object {
 	 */
 	struct i915_address_space *shares_resv_from;
 
+#ifdef CONFIG_PROC_FS
+	/**
+	 * @client: @i915_drm_client which created the object
+	 */
+	struct i915_drm_client *client;
+
+	/**
+	 * @client_link: Link into @i915_drm_client.objects_list
+	 */
+	struct list_head client_link;
+#endif
+
 	union {
 		struct rcu_head rcu;
 		struct llist_node freed;
diff --git a/drivers/gpu/drm/i915/i915_drm_client.c b/drivers/gpu/drm/i915/i915_drm_client.c
index 2a44b3876cb5..3c8d6a46a801 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.c
+++ b/drivers/gpu/drm/i915/i915_drm_client.c
@@ -17,7 +17,8 @@
 #include "i915_gem.h"
 #include "i915_utils.h"
 
-struct i915_drm_client *i915_drm_client_alloc(void)
+struct i915_drm_client *
+i915_drm_client_alloc(struct drm_i915_file_private *fpriv)
 {
 	struct i915_drm_client *client;
 
@@ -28,6 +29,12 @@ struct i915_drm_client *i915_drm_client_alloc(void)
 	kref_init(&client->kref);
 	spin_lock_init(&client->ctx_lock);
 	INIT_LIST_HEAD(&client->ctx_list);
+#ifdef CONFIG_PROC_FS
+	spin_lock_init(&client->objects_lock);
+	INIT_LIST_HEAD(&client->objects_list);
+
+	client->fpriv = fpriv;
+#endif
 
 	return client;
 }
@@ -108,4 +115,31 @@ void i915_drm_client_fdinfo(struct drm_printer *p, struct drm_file *file)
 	for (i = 0; i < ARRAY_SIZE(uabi_class_names); i++)
 		show_client_class(p, i915, file_priv->client, i);
 }
+
+void i915_drm_client_add_object(struct i915_drm_client *client,
+				struct drm_i915_gem_object *obj)
+{
+	GEM_WARN_ON(obj->client);
+	GEM_WARN_ON(!list_empty(&obj->client_link));
+
+	spin_lock(&client->objects_lock);
+	obj->client = i915_drm_client_get(client);
+	list_add_tail(&obj->client_link, &client->objects_list);
+	spin_unlock(&client->objects_lock);
+}
+
+void i915_drm_client_remove_object(struct drm_i915_gem_object *obj)
+{
+	struct i915_drm_client *client = fetch_and_zero(&obj->client);
+
+	/* Object may not be associated with a client. */
+	if (!client || list_empty(&obj->client_link))
+		return;
+
+	spin_lock(&client->objects_lock);
+	list_del(&obj->client_link);
+	spin_unlock(&client->objects_lock);
+
+	i915_drm_client_put(client);
+}
 #endif
diff --git a/drivers/gpu/drm/i915/i915_drm_client.h b/drivers/gpu/drm/i915/i915_drm_client.h
index 4c18b99e10a4..5fc897ab1a6b 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.h
+++ b/drivers/gpu/drm/i915/i915_drm_client.h
@@ -12,6 +12,9 @@
 
 #include <uapi/drm/i915_drm.h>
 
+#include "i915_file_private.h"
+#include "gem/i915_gem_object_types.h"
+
 #define I915_LAST_UABI_ENGINE_CLASS I915_ENGINE_CLASS_COMPUTE
 
 struct drm_file;
@@ -25,6 +28,22 @@ struct i915_drm_client {
 	spinlock_t ctx_lock; /* For add/remove from ctx_list. */
 	struct list_head ctx_list; /* List of contexts belonging to client. */
 
+#ifdef CONFIG_PROC_FS
+	struct drm_i915_file_private *fpriv;
+
+	/**
+	 * @objects_lock: lock protecting @objects_list
+	 */
+	spinlock_t objects_lock;
+
+	/**
+	 * @objects_list: list of objects created by this client
+	 *
+	 * Protected by @objects_lock.
+	 */
+	struct list_head objects_list;
+#endif
+
 	/**
 	 * @past_runtime: Accumulation of pphwsp runtimes from closed contexts.
 	 */
@@ -45,10 +64,23 @@ static inline void i915_drm_client_put(struct i915_drm_client *client)
 	kref_put(&client->kref, __i915_drm_client_free);
 }
 
-struct i915_drm_client *i915_drm_client_alloc(void);
+struct i915_drm_client *i915_drm_client_alloc(struct drm_i915_file_private *fpriv);
 
 #ifdef CONFIG_PROC_FS
 void i915_drm_client_fdinfo(struct drm_printer *p, struct drm_file *file);
+
+void i915_drm_client_add_object(struct i915_drm_client *client,
+				struct drm_i915_gem_object *obj);
+void i915_drm_client_remove_object(struct drm_i915_gem_object *obj);
+#else
+static inline void i915_drm_client_add_object(struct i915_drm_client *client,
+					      struct drm_i915_gem_object *obj)
+{
+}
+
+static inline void i915_drm_client_remove_object(struct drm_i915_gem_object *obj)
+{
+}
 #endif
 
 #endif /* !__I915_DRM_CLIENT_H__ */
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 1f65bb33dd21..7ae42f746cc2 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1325,7 +1325,7 @@ int i915_gem_open(struct drm_i915_private *i915, struct drm_file *file)
 	if (!file_priv)
 		goto err_alloc;
 
-	client = i915_drm_client_alloc();
+	client = i915_drm_client_alloc(file_priv);
 	if (!client)
 		goto err_client;
 
-- 
2.39.2

[Intel-gfx] [PATCH 2/5] drm/i915: Record which client owns a VM

[Tvrtko Ursulin]

From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

To enable accounting of indirect client memory usage (such as page tables)
in the following patch, lets start recording the creator of each PPGTT.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 drivers/gpu/drm/i915/gem/i915_gem_context.c       | 11 ++++++++---
 drivers/gpu/drm/i915/gem/i915_gem_context_types.h |  3 +++
 drivers/gpu/drm/i915/gem/selftests/mock_context.c |  4 ++--
 drivers/gpu/drm/i915/gt/intel_gtt.h               |  1 +
 4 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 9a9ff84c90d7..35cf6608180e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -279,7 +279,8 @@ static int proto_context_set_protected(struct drm_i915_private *i915,
 }
 
 static struct i915_gem_proto_context *
-proto_context_create(struct drm_i915_private *i915, unsigned int flags)
+proto_context_create(struct drm_i915_file_private *fpriv,
+		     struct drm_i915_private *i915, unsigned int flags)
 {
 	struct i915_gem_proto_context *pc, *err;
 
@@ -287,6 +288,7 @@ proto_context_create(struct drm_i915_private *i915, unsigned int flags)
 	if (!pc)
 		return ERR_PTR(-ENOMEM);
 
+	pc->fpriv = fpriv;
 	pc->num_user_engines = -1;
 	pc->user_engines = NULL;
 	pc->user_flags = BIT(UCONTEXT_BANNABLE) |
@@ -1621,6 +1623,7 @@ i915_gem_create_context(struct drm_i915_private *i915,
 			err = PTR_ERR(ppgtt);
 			goto err_ctx;
 		}
+		ppgtt->vm.fpriv = pc->fpriv;
 		vm = &ppgtt->vm;
 	}
 	if (vm)
@@ -1740,7 +1743,7 @@ int i915_gem_context_open(struct drm_i915_private *i915,
 	/* 0 reserved for invalid/unassigned ppgtt */
 	xa_init_flags(&file_priv->vm_xa, XA_FLAGS_ALLOC1);
 
-	pc = proto_context_create(i915, 0);
+	pc = proto_context_create(file_priv, i915, 0);
 	if (IS_ERR(pc)) {
 		err = PTR_ERR(pc);
 		goto err;
@@ -1822,6 +1825,7 @@ int i915_gem_vm_create_ioctl(struct drm_device *dev, void *data,
 
 	GEM_BUG_ON(id == 0); /* reserved for invalid/unassigned ppgtt */
 	args->vm_id = id;
+	ppgtt->vm.fpriv = file_priv;
 	return 0;
 
 err_put:
@@ -2284,7 +2288,8 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
 		return -EIO;
 	}
 
-	ext_data.pc = proto_context_create(i915, args->flags);
+	ext_data.pc = proto_context_create(file->driver_priv, i915,
+					   args->flags);
 	if (IS_ERR(ext_data.pc))
 		return PTR_ERR(ext_data.pc);
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
index cb78214a7dcd..c573c067779f 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
@@ -188,6 +188,9 @@ struct i915_gem_proto_engine {
  * CONTEXT_CREATE_SET_PARAM during GEM_CONTEXT_CREATE.
  */
 struct i915_gem_proto_context {
+	/** @fpriv: Client which creates the context */
+	struct drm_i915_file_private *fpriv;
+
 	/** @vm: See &i915_gem_context.vm */
 	struct i915_address_space *vm;
 
diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_context.c b/drivers/gpu/drm/i915/gem/selftests/mock_context.c
index 8ac6726ec16b..125584ada282 100644
--- a/drivers/gpu/drm/i915/gem/selftests/mock_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/mock_context.c
@@ -83,7 +83,7 @@ live_context(struct drm_i915_private *i915, struct file *file)
 	int err;
 	u32 id;
 
-	pc = proto_context_create(i915, 0);
+	pc = proto_context_create(fpriv, i915, 0);
 	if (IS_ERR(pc))
 		return ERR_CAST(pc);
 
@@ -152,7 +152,7 @@ kernel_context(struct drm_i915_private *i915,
 	struct i915_gem_context *ctx;
 	struct i915_gem_proto_context *pc;
 
-	pc = proto_context_create(i915, 0);
+	pc = proto_context_create(NULL, i915, 0);
 	if (IS_ERR(pc))
 		return ERR_CAST(pc);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h
index 4d6296cdbcfd..7192a534a654 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.h
@@ -248,6 +248,7 @@ struct i915_address_space {
 	struct drm_mm mm;
 	struct intel_gt *gt;
 	struct drm_i915_private *i915;
+	struct drm_i915_file_private *fpriv;
 	struct device *dma;
 	u64 total;		/* size addr space maps (ex. 2GB for ggtt) */
 	u64 reserved;		/* size addr space reserved */
-- 
2.39.2

[Intel-gfx] [PATCH 3/5] drm/i915: Track page table backing store usage

[Tvrtko Ursulin]

From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

Account page table backing store against the owning client memory usage
stats.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_gtt.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c
index 2f6a9be0ffe6..126269a0d728 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.c
@@ -58,6 +58,9 @@ struct drm_i915_gem_object *alloc_pt_lmem(struct i915_address_space *vm, int sz)
 	if (!IS_ERR(obj)) {
 		obj->base.resv = i915_vm_resv_get(vm);
 		obj->shares_resv_from = vm;
+
+		if (vm->fpriv)
+			i915_drm_client_add_object(vm->fpriv->client, obj);
 	}
 
 	return obj;
@@ -79,6 +82,9 @@ struct drm_i915_gem_object *alloc_pt_dma(struct i915_address_space *vm, int sz)
 	if (!IS_ERR(obj)) {
 		obj->base.resv = i915_vm_resv_get(vm);
 		obj->shares_resv_from = vm;
+
+		if (vm->fpriv)
+			i915_drm_client_add_object(vm->fpriv->client, obj);
 	}
 
 	return obj;
-- 
2.39.2

[Intel-gfx] [PATCH 4/5] drm/i915: Account ring buffer and context state storage

[Tvrtko Ursulin]

From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

Account ring buffers and logical context space against the owning client
memory usage stats.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_context.c |  8 ++++++++
 drivers/gpu/drm/i915/i915_drm_client.c  | 10 ++++++++++
 drivers/gpu/drm/i915/i915_drm_client.h  |  8 ++++++++
 3 files changed, 26 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index a53b26178f0a..cb6d8e7cdd9d 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -6,6 +6,7 @@
 #include "gem/i915_gem_context.h"
 #include "gem/i915_gem_pm.h"
 
+#include "i915_drm_client.h"
 #include "i915_drv.h"
 #include "i915_trace.h"
 
@@ -50,6 +51,7 @@ intel_context_create(struct intel_engine_cs *engine)
 
 int intel_context_alloc_state(struct intel_context *ce)
 {
+	struct i915_gem_context *ctx;
 	int err = 0;
 
 	if (mutex_lock_interruptible(&ce->pin_mutex))
@@ -66,6 +68,12 @@ int intel_context_alloc_state(struct intel_context *ce)
 			goto unlock;
 
 		set_bit(CONTEXT_ALLOC_BIT, &ce->flags);
+
+		rcu_read_lock();
+		ctx = rcu_dereference(ce->gem_context);
+		if (ctx && ctx->file_priv)
+			i915_drm_client_add_context(ctx->file_priv->client, ce);
+		rcu_read_unlock();
 	}
 
 unlock:
diff --git a/drivers/gpu/drm/i915/i915_drm_client.c b/drivers/gpu/drm/i915/i915_drm_client.c
index 3c8d6a46a801..da29d01d1c3d 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.c
+++ b/drivers/gpu/drm/i915/i915_drm_client.c
@@ -142,4 +142,14 @@ void i915_drm_client_remove_object(struct drm_i915_gem_object *obj)
 
 	i915_drm_client_put(client);
 }
+
+void i915_drm_client_add_context(struct i915_drm_client *client,
+				 struct intel_context *ce)
+{
+	if (ce->state)
+		i915_drm_client_add_object(client, ce->state->obj);
+
+	if (ce->ring != ce->engine->legacy.ring && ce->ring->vma)
+		i915_drm_client_add_object(client, ce->ring->vma->obj);
+}
 #endif
diff --git a/drivers/gpu/drm/i915/i915_drm_client.h b/drivers/gpu/drm/i915/i915_drm_client.h
index 5fc897ab1a6b..744e48ed133c 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.h
+++ b/drivers/gpu/drm/i915/i915_drm_client.h
@@ -14,6 +14,7 @@
 
 #include "i915_file_private.h"
 #include "gem/i915_gem_object_types.h"
+#include "gt/intel_context_types.h"
 
 #define I915_LAST_UABI_ENGINE_CLASS I915_ENGINE_CLASS_COMPUTE
 
@@ -72,6 +73,8 @@ void i915_drm_client_fdinfo(struct drm_printer *p, struct drm_file *file);
 void i915_drm_client_add_object(struct i915_drm_client *client,
 				struct drm_i915_gem_object *obj);
 void i915_drm_client_remove_object(struct drm_i915_gem_object *obj);
+void i915_drm_client_add_context(struct i915_drm_client *client,
+				 struct intel_context *ce);
 #else
 static inline void i915_drm_client_add_object(struct i915_drm_client *client,
 					      struct drm_i915_gem_object *obj)
@@ -81,6 +84,11 @@ static inline void i915_drm_client_add_object(struct i915_drm_client *client,
 static inline void i915_drm_client_remove_object(struct drm_i915_gem_object *obj)
 {
 }
+
+static inline void i915_drm_client_add_context(struct i915_drm_client *client,
+					       struct intel_context *ce)
+{
+}
 #endif
 
 #endif /* !__I915_DRM_CLIENT_H__ */
-- 
2.39.2

[Intel-gfx] [PATCH 5/5] drm/i915: Implement fdinfo memory stats printing

[Tvrtko Ursulin]

From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

Use the newly added drm_print_memory_stats helper to show memory
utilisation of our objects in drm/driver specific fdinfo output.

To collect the stats we walk the per memory regions object lists
and accumulate object size into the respective drm_memory_stats
categories.

Objects with multiple possible placements are reported in multiple
regions for total and shared sizes, while other categories are
counted only for the currently active region.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Aravind Iddamsetty <aravind.iddamsetty@intel.com>
Cc: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/i915/i915_drm_client.c | 78 ++++++++++++++++++++++++++
 1 file changed, 78 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_drm_client.c b/drivers/gpu/drm/i915/i915_drm_client.c
index da29d01d1c3d..406e5a5c2961 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.c
+++ b/drivers/gpu/drm/i915/i915_drm_client.c
@@ -48,6 +48,82 @@ void __i915_drm_client_free(struct kref *kref)
 }
 
 #ifdef CONFIG_PROC_FS
+static void
+obj_meminfo(struct drm_i915_gem_object *obj,
+	    struct drm_memory_stats stats[INTEL_REGION_UNKNOWN])
+{
+	struct intel_memory_region *mr;
+	u64 sz = obj->base.size;
+	enum intel_region_id id;
+	unsigned int i;
+
+	/* Attribute size and shared to all possible memory regions. */
+	for (i = 0; i < obj->mm.n_placements; i++) {
+		mr = obj->mm.placements[i];
+		id = mr->id;
+
+		if (obj->base.handle_count > 1)
+			stats[id].shared += sz;
+		else
+			stats[id].private += sz;
+	}
+
+	/* Attribute other categories to only the current region. */
+	mr = obj->mm.region;
+	if (mr)
+		id = mr->id;
+	else
+		id = INTEL_REGION_SMEM;
+
+	if (!obj->mm.n_placements) {
+		if (obj->base.handle_count > 1)
+			stats[id].shared += sz;
+		else
+			stats[id].private += sz;
+	}
+
+	if (i915_gem_object_has_pages(obj)) {
+		stats[id].resident += sz;
+
+		if (!dma_resv_test_signaled(obj->base.resv,
+					    dma_resv_usage_rw(true)))
+			stats[id].active += sz;
+		else if (i915_gem_object_is_shrinkable(obj) &&
+			 obj->mm.madv == I915_MADV_DONTNEED)
+			stats[id].purgeable += sz;
+	}
+}
+
+static void show_meminfo(struct drm_printer *p, struct drm_file *file)
+{
+	struct drm_memory_stats stats[INTEL_REGION_UNKNOWN] = {};
+	struct drm_i915_file_private *fpriv = file->driver_priv;
+	struct i915_drm_client *client = fpriv->client;
+	struct drm_i915_private *i915 = fpriv->i915;
+	struct drm_i915_gem_object *obj;
+	struct intel_memory_region *mr;
+	unsigned int id;
+
+	/* Public objects. */
+	spin_lock(&file->table_lock);
+	idr_for_each_entry (&file->object_idr, obj, id)
+		obj_meminfo(obj, stats);
+	spin_unlock(&file->table_lock);
+
+	/* Internal objects. */
+	spin_lock(&client->objects_lock);
+	list_for_each_entry(obj, &client->objects_list, client_link)
+		obj_meminfo(obj, stats);
+	spin_unlock(&client->objects_lock);
+
+	for_each_memory_region(mr, i915, id)
+		drm_print_memory_stats(p,
+				       &stats[id],
+				       DRM_GEM_OBJECT_RESIDENT |
+				       DRM_GEM_OBJECT_PURGEABLE,
+				       mr->name);
+}
+
 static const char * const uabi_class_names[] = {
 	[I915_ENGINE_CLASS_RENDER] = "render",
 	[I915_ENGINE_CLASS_COPY] = "copy",
@@ -109,6 +185,8 @@ void i915_drm_client_fdinfo(struct drm_printer *p, struct drm_file *file)
 	 * ******************************************************************
 	 */
 
+	show_meminfo(p, file);
+
 	if (GRAPHICS_VER(i915) < 8)
 		return;
 
-- 
2.39.2

[Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for fdinfo memory stats (rev3)

[Patchwork]

== Series Details ==

Series: fdinfo memory stats (rev3)
URL   : https://patchwork.freedesktop.org/series/119082/
State : warning

== Summary ==

Error: dim checkpatch failed
0e7a9361b003 drm/i915: Add ability for tracking buffer objects per client
e0e7d111353c drm/i915: Record which client owns a VM
8645bd51fede drm/i915: Track page table backing store usage
eb2fd9e3fbbe drm/i915: Account ring buffer and context state storage
02d2f2e3e48f drm/i915: Implement fdinfo memory stats printing
-:87: WARNING:SPACING: space prohibited between function name and open parenthesis '('
#87: FILE: drivers/gpu/drm/i915/i915_drm_client.c:109:
+	idr_for_each_entry (&file->object_idr, obj, id)

total: 0 errors, 1 warnings, 0 checks, 90 lines checked

[Intel-gfx] ✗ Fi.CI.SPARSE: warning for fdinfo memory stats (rev3)

[Patchwork]

== Series Details ==

Series: fdinfo memory stats (rev3)
URL   : https://patchwork.freedesktop.org/series/119082/
State : warning

== Summary ==

Error: dim sparse failed
Sparse version: v0.6.2
Fast mode used, each commit won't be checked separately.

[Intel-gfx] ✗ Fi.CI.BAT: failure for fdinfo memory stats (rev3)

[Patchwork]

[-- Attachment #1: Type: text/plain, Size: 7425 bytes --]

== Series Details ==

Series: fdinfo memory stats (rev3)
URL   : https://patchwork.freedesktop.org/series/119082/
State : failure

== Summary ==

CI Bug Log - changes from CI_DRM_13262 -> Patchwork_119082v3
====================================================

Summary
-------

  **FAILURE**

  Serious unknown changes coming with Patchwork_119082v3 absolutely need to be
  verified manually.
  
  If you think the reported changes have nothing to do with the changes
  introduced in Patchwork_119082v3, please notify your bug team to allow them
  to document this new failure mode, which will reduce false positives in CI.

  External URL: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_119082v3/index.html

Participating hosts (42 -> 41)
------------------------------

  Missing    (1): fi-snb-2520m 

Possible new issues
-------------------

  Here are the unknown changes that may have been introduced in Patchwork_119082v3:

### IGT changes ###

#### Possible regressions ####

  * igt@gem_busy@busy@all-engines:
    - bat-dg1-5:          [PASS][1] -> [ABORT][2]
   [1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_13262/bat-dg1-5/igt@gem_busy@busy@all-engines.html
   [2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_119082v3/bat-dg1-5/igt@gem_busy@busy@all-engines.html
    - bat-dg1-7:          [PASS][3] -> [ABORT][4]
   [3]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_13262/bat-dg1-7/igt@gem_busy@busy@all-engines.html
   [4]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_119082v3/bat-dg1-7/igt@gem_busy@busy@all-engines.html
    - bat-dg2-9:          [PASS][5] -> [ABORT][6]
   [5]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_13262/bat-dg2-9/igt@gem_busy@busy@all-engines.html
   [6]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_119082v3/bat-dg2-9/igt@gem_busy@busy@all-engines.html
    - bat-atsm-1:         [PASS][7] -> [ABORT][8]
   [7]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_13262/bat-atsm-1/igt@gem_busy@busy@all-engines.html
   [8]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_119082v3/bat-atsm-1/igt@gem_busy@busy@all-engines.html
    - bat-dg2-11:         [PASS][9] -> [ABORT][10]
   [9]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_13262/bat-dg2-11/igt@gem_busy@busy@all-engines.html
   [10]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_119082v3/bat-dg2-11/igt@gem_busy@busy@all-engines.html
    - bat-dg2-8:          [PASS][11] -> [ABORT][12]
   [11]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_13262/bat-dg2-8/igt@gem_busy@busy@all-engines.html
   [12]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_119082v3/bat-dg2-8/igt@gem_busy@busy@all-engines.html

  
Known issues
------------

  Here are the changes found in Patchwork_119082v3 that come from known issues:

### IGT changes ###

#### Issues hit ####

  * igt@i915_selftest@live@gt_heartbeat:
    - fi-kbl-soraka:      [PASS][13] -> [DMESG-FAIL][14] ([i915#5334] / [i915#7872])
   [13]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_13262/fi-kbl-soraka/igt@i915_selftest@live@gt_heartbeat.html
   [14]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_119082v3/fi-kbl-soraka/igt@i915_selftest@live@gt_heartbeat.html

  * igt@i915_selftest@live@reset:
    - bat-rpls-2:         [PASS][15] -> [ABORT][16] ([i915#4983] / [i915#7461] / [i915#7913] / [i915#7981] / [i915#8347])
   [15]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_13262/bat-rpls-2/igt@i915_selftest@live@reset.html
   [16]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_119082v3/bat-rpls-2/igt@i915_selftest@live@reset.html

  * igt@i915_suspend@basic-s3-without-i915:
    - bat-rpls-1:         NOTRUN -> [ABORT][17] ([i915#6687] / [i915#7978])
   [17]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_119082v3/bat-rpls-1/igt@i915_suspend@basic-s3-without-i915.html

  
#### Possible fixes ####

  * igt@i915_selftest@live@reset:
    - bat-rpls-1:         [ABORT][18] ([i915#4983] / [i915#7461] / [i915#8347] / [i915#8384]) -> [PASS][19]
   [18]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_13262/bat-rpls-1/igt@i915_selftest@live@reset.html
   [19]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_119082v3/bat-rpls-1/igt@i915_selftest@live@reset.html

  * igt@i915_selftest@live@slpc:
    - {bat-mtlp-6}:       [DMESG-WARN][20] ([i915#6367]) -> [PASS][21]
   [20]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_13262/bat-mtlp-6/igt@i915_selftest@live@slpc.html
   [21]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_119082v3/bat-mtlp-6/igt@i915_selftest@live@slpc.html

  * igt@kms_psr@cursor_plane_move:
    - fi-kbl-soraka:      [INCOMPLETE][22] -> [PASS][23]
   [22]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_13262/fi-kbl-soraka/igt@kms_psr@cursor_plane_move.html
   [23]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_119082v3/fi-kbl-soraka/igt@kms_psr@cursor_plane_move.html

  
  {name}: This element is suppressed. This means it is ignored when computing
          the status of the difference (SUCCESS, WARNING, or FAILURE).

  [fdo#109285]: https://bugs.freedesktop.org/show_bug.cgi?id=109285
  [i915#3708]: https://gitlab.freedesktop.org/drm/intel/issues/3708
  [i915#4077]: https://gitlab.freedesktop.org/drm/intel/issues/4077
  [i915#4213]: https://gitlab.freedesktop.org/drm/intel/issues/4213
  [i915#4423]: https://gitlab.freedesktop.org/drm/intel/issues/4423
  [i915#4579]: https://gitlab.freedesktop.org/drm/intel/issues/4579
  [i915#4613]: https://gitlab.freedesktop.org/drm/intel/issues/4613
  [i915#4983]: https://gitlab.freedesktop.org/drm/intel/issues/4983
  [i915#5274]: https://gitlab.freedesktop.org/drm/intel/issues/5274
  [i915#5334]: https://gitlab.freedesktop.org/drm/intel/issues/5334
  [i915#6367]: https://gitlab.freedesktop.org/drm/intel/issues/6367
  [i915#6621]: https://gitlab.freedesktop.org/drm/intel/issues/6621
  [i915#6645]: https://gitlab.freedesktop.org/drm/intel/issues/6645
  [i915#6687]: https://gitlab.freedesktop.org/drm/intel/issues/6687
  [i915#7059]: https://gitlab.freedesktop.org/drm/intel/issues/7059
  [i915#7461]: https://gitlab.freedesktop.org/drm/intel/issues/7461
  [i915#7828]: https://gitlab.freedesktop.org/drm/intel/issues/7828
  [i915#7872]: https://gitlab.freedesktop.org/drm/intel/issues/7872
  [i915#7913]: https://gitlab.freedesktop.org/drm/intel/issues/7913
  [i915#7978]: https://gitlab.freedesktop.org/drm/intel/issues/7978
  [i915#7981]: https://gitlab.freedesktop.org/drm/intel/issues/7981
  [i915#8347]: https://gitlab.freedesktop.org/drm/intel/issues/8347
  [i915#8384]: https://gitlab.freedesktop.org/drm/intel/issues/8384


Build changes
-------------

  * Linux: CI_DRM_13262 -> Patchwork_119082v3

  CI-20190529: 20190529
  CI_DRM_13262: 26f62dc5b6119b2fcc3380b76e25dbe3903060a0 @ git://anongit.freedesktop.org/gfx-ci/linux
  IGT_7326: 02c2cf17628b6203d6105d4a91dfe8a101d482ce @ https://gitlab.freedesktop.org/drm/igt-gpu-tools.git
  Patchwork_119082v3: 26f62dc5b6119b2fcc3380b76e25dbe3903060a0 @ git://anongit.freedesktop.org/gfx-ci/linux


### Linux commits

0497e4b1f7c2 drm/i915: Implement fdinfo memory stats printing
942364187b4f drm/i915: Account ring buffer and context state storage
a6a8bce070ce drm/i915: Track page table backing store usage
6eaa9cbe37cb drm/i915: Record which client owns a VM
15570a43e2fe drm/i915: Add ability for tracking buffer objects per client

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_119082v3/index.html

[-- Attachment #2: Type: text/html, Size: 7693 bytes --]

[Intel-gfx] [PATCH v7 0/5] fdinfo memory stats

[Tvrtko Ursulin]

From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

A short series to enable fdinfo memory stats for i915.

I added tracking of most classes of objects (user objects, page tables, context
state, ring buffers) which contribute to client's memory footprint and am
accouting their memory use along the similar lines as in Rob's msm code, just
that with i915 specific code we can show a memory region breakdown and so
support discrete and multi-tile GPUs properly. And also reflect that our objects
can have multiple allowed backing stores.

The existing helper Rob added is then used to dump the per memory region stats
to fdinfo.

The basic objects-per-client infrastructure can later be extended to cover all
objects and so avoid needing to walk the IDR under the client's file table lock,
which would further avoid distburbing the running clients by parallel fdinfo
readers.

Example fdinfo format:

# cat /proc/1383/fdinfo/8
pos:    0
flags:  02100002
mnt_id: 21
ino:    397
drm-driver:     i915
drm-client-id:  18
drm-pdev:       0000:00:02.0
drm-total-system:       125 MiB
drm-shared-system:      16 MiB
drm-active-system:      110 MiB
drm-resident-system:    125 MiB
drm-purgeable-system:   2 MiB
drm-total-stolen-system:        0
drm-shared-stolen-system:       0
drm-active-stolen-system:       0
drm-resident-stolen-system:     0
drm-purgeable-stolen-system:    0
drm-engine-render:      25662044495 ns
drm-engine-copy:        0 ns
drm-engine-video:       0 ns
drm-engine-video-enhance:       0 ns

Example gputop output:

DRM minor 0
 PID     SMEM  SMEMRSS   render     copy     video    NAME
1233     124M     124M |████████||        ||        ||        | neverball
1130      59M      59M |█▌      ||        ||        ||        | Xorg
1207      12M      12M |        ||        ||        ||        | xfwm4

Or with Wayland:

DRM minor 0
 PID      MEM      RSS    render        copy         video    video-enhance NAME
2093     191M     191M |▊          ||           ||           ||           | gnome-shell
DRM minor 128
 PID      MEM      RSS    render        copy         video    video-enhance NAME
2551      71M      71M |██▉        ||           ||           ||           | neverball
2553      50M      50M |           ||           ||           ||           | Xwayland

v2:
 * Now actually per client.

v3:
 * Track imported dma-buf objects.

v4:
 * Rely on DRM GEM handles for tracking user objects.
 * Fix internal object accounting (no placements).

v5:
 * Fixed brain fart of overwriting the loop cursor.
 * Fixed object destruction racing with fdinfo reads.
 * Take reference to GEM context while using it.

v6:
 * Rebase, cover letter update.

v7:
 * Account against active region only.
 * Cover all dma_resv usage when testing for activity.

Test-with: 20230921114557.192629-1-tvrtko.ursulin@linux.intel.com

Tvrtko Ursulin (5):
  drm/i915: Add ability for tracking buffer objects per client
  drm/i915: Record which client owns a VM
  drm/i915: Track page table backing store usage
  drm/i915: Account ring buffer and context state storage
  drm/i915: Implement fdinfo memory stats printing

 drivers/gpu/drm/i915/gem/i915_gem_context.c   |  11 +-
 .../gpu/drm/i915/gem/i915_gem_context_types.h |   3 +
 drivers/gpu/drm/i915/gem/i915_gem_object.c    |  13 ++-
 .../gpu/drm/i915/gem/i915_gem_object_types.h  |  12 ++
 .../gpu/drm/i915/gem/selftests/mock_context.c |   4 +-
 drivers/gpu/drm/i915/gt/intel_context.c       |  14 +++
 drivers/gpu/drm/i915/gt/intel_gtt.c           |   6 +
 drivers/gpu/drm/i915/gt/intel_gtt.h           |   1 +
 drivers/gpu/drm/i915/i915_drm_client.c        | 110 ++++++++++++++++++
 drivers/gpu/drm/i915/i915_drm_client.h        |  41 +++++++
 10 files changed, 207 insertions(+), 8 deletions(-)

-- 
2.39.2

[Intel-gfx] [PATCH 4/5] drm/i915: Account ring buffer and context state storage

[Tvrtko Ursulin]

From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

Account ring buffers and logical context space against the owning client
memory usage stats.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Aravind Iddamsetty <aravind.iddamsetty@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_context.c | 14 ++++++++++++++
 drivers/gpu/drm/i915/i915_drm_client.c  | 10 ++++++++++
 drivers/gpu/drm/i915/i915_drm_client.h  |  9 +++++++++
 3 files changed, 33 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index a53b26178f0a..a2f1245741bb 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -6,6 +6,7 @@
 #include "gem/i915_gem_context.h"
 #include "gem/i915_gem_pm.h"
 
+#include "i915_drm_client.h"
 #include "i915_drv.h"
 #include "i915_trace.h"
 
@@ -50,6 +51,7 @@ intel_context_create(struct intel_engine_cs *engine)
 
 int intel_context_alloc_state(struct intel_context *ce)
 {
+	struct i915_gem_context *ctx;
 	int err = 0;
 
 	if (mutex_lock_interruptible(&ce->pin_mutex))
@@ -66,6 +68,18 @@ int intel_context_alloc_state(struct intel_context *ce)
 			goto unlock;
 
 		set_bit(CONTEXT_ALLOC_BIT, &ce->flags);
+
+		rcu_read_lock();
+		ctx = rcu_dereference(ce->gem_context);
+		if (ctx && !kref_get_unless_zero(&ctx->ref))
+			ctx = NULL;
+		rcu_read_unlock();
+		if (ctx) {
+			if (ctx->client)
+				i915_drm_client_add_context_objects(ctx->client,
+								    ce);
+			i915_gem_context_put(ctx);
+		}
 	}
 
 unlock:
diff --git a/drivers/gpu/drm/i915/i915_drm_client.c b/drivers/gpu/drm/i915/i915_drm_client.c
index 2e5e69edc0f9..a61356012df8 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.c
+++ b/drivers/gpu/drm/i915/i915_drm_client.c
@@ -144,4 +144,14 @@ bool i915_drm_client_remove_object(struct drm_i915_gem_object *obj)
 
 	return true;
 }
+
+void i915_drm_client_add_context_objects(struct i915_drm_client *client,
+					 struct intel_context *ce)
+{
+	if (ce->state)
+		i915_drm_client_add_object(client, ce->state->obj);
+
+	if (ce->ring != ce->engine->legacy.ring && ce->ring->vma)
+		i915_drm_client_add_object(client, ce->ring->vma->obj);
+}
 #endif
diff --git a/drivers/gpu/drm/i915/i915_drm_client.h b/drivers/gpu/drm/i915/i915_drm_client.h
index 5f58fdf7dcb8..69cedfcd3d69 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.h
+++ b/drivers/gpu/drm/i915/i915_drm_client.h
@@ -14,6 +14,7 @@
 
 #include "i915_file_private.h"
 #include "gem/i915_gem_object_types.h"
+#include "gt/intel_context_types.h"
 
 #define I915_LAST_UABI_ENGINE_CLASS I915_ENGINE_CLASS_COMPUTE
 
@@ -70,6 +71,8 @@ void i915_drm_client_fdinfo(struct drm_printer *p, struct drm_file *file);
 void i915_drm_client_add_object(struct i915_drm_client *client,
 				struct drm_i915_gem_object *obj);
 bool i915_drm_client_remove_object(struct drm_i915_gem_object *obj);
+void i915_drm_client_add_context_objects(struct i915_drm_client *client,
+					 struct intel_context *ce);
 #else
 static inline void i915_drm_client_add_object(struct i915_drm_client *client,
 					      struct drm_i915_gem_object *obj)
@@ -79,6 +82,12 @@ static inline void i915_drm_client_add_object(struct i915_drm_client *client,
 static inline bool i915_drm_client_remove_object(struct drm_i915_gem_object *obj)
 {
 }
+
+static inline void
+i915_drm_client_add_context_objects(struct i915_drm_client *client,
+				    struct intel_context *ce)
+{
+}
 #endif
 
 #endif /* !__I915_DRM_CLIENT_H__ */
-- 
2.39.2

[Intel-gfx] [PATCH v6 0/5] fdinfo memory stats

[Tvrtko Ursulin]

From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

A short series to enable fdinfo memory stats for i915.

I added tracking of most classes of objects (user objects, page tables, context
state, ring buffers) which contribute to client's memory footprint and am
accouting their memory use along the similar lines as in Rob's msm code, just
that with i915 specific code we can show a memory region breakdown and so
support discrete and multi-tile GPUs properly. And also reflect that our objects
can have multiple allowed backing stores.

The existing helper Rob added is then used to dump the per memory region stats
to fdinfo.

The basic objects-per-client infrastructure can later be extended to cover all
objects and so avoid needing to walk the IDR under the client's file table lock,
which would further avoid distburbing the running clients by parallel fdinfo
readers.

Example fdinfo format:

# cat /proc/1383/fdinfo/8
pos:    0
flags:  02100002
mnt_id: 21
ino:    397
drm-driver:     i915
drm-client-id:  18
drm-pdev:       0000:00:02.0
drm-total-system:       125 MiB
drm-shared-system:      16 MiB
drm-active-system:      110 MiB
drm-resident-system:    125 MiB
drm-purgeable-system:   2 MiB
drm-total-stolen-system:        0
drm-shared-stolen-system:       0
drm-active-stolen-system:       0
drm-resident-stolen-system:     0
drm-purgeable-stolen-system:    0
drm-engine-render:      25662044495 ns
drm-engine-copy:        0 ns
drm-engine-video:       0 ns
drm-engine-video-enhance:       0 ns

Example gputop output:

DRM minor 0
 PID     SMEM  SMEMRSS   render     copy     video    NAME
1233     124M     124M |████████||        ||        ||        | neverball
1130      59M      59M |█▌      ||        ||        ||        | Xorg
1207      12M      12M |        ||        ||        ||        | xfwm4

Or with Wayland:

DRM minor 0
 PID      MEM      RSS    render        copy         video    video-enhance NAME
2093     191M     191M |▊          ||           ||           ||           | gnome-shell
DRM minor 128
 PID      MEM      RSS    render        copy         video    video-enhance NAME
2551      71M      71M |██▉        ||           ||           ||           | neverball
2553      50M      50M |           ||           ||           ||           | Xwayland

v2:
 * Now actually per client.

v3:
 * Track imported dma-buf objects.

v4:
 * Rely on DRM GEM handles for tracking user objects.
 * Fix internal object accounting (no placements).

v5:
 * Fixed brain fart of overwriting the loop cursor.
 * Fixed object destruction racing with fdinfo reads.
 * Take reference to GEM context while using it.

v6:
 * Rebase, cover letter update.

Tvrtko Ursulin (5):
  drm/i915: Add ability for tracking buffer objects per client
  drm/i915: Record which client owns a VM
  drm/i915: Track page table backing store usage
  drm/i915: Account ring buffer and context state storage
  drm/i915: Implement fdinfo memory stats printing

 drivers/gpu/drm/i915/gem/i915_gem_context.c   |  11 +-
 .../gpu/drm/i915/gem/i915_gem_context_types.h |   3 +
 drivers/gpu/drm/i915/gem/i915_gem_object.c    |  13 +-
 .../gpu/drm/i915/gem/i915_gem_object_types.h  |  12 ++
 .../gpu/drm/i915/gem/selftests/mock_context.c |   4 +-
 drivers/gpu/drm/i915/gt/intel_context.c       |  14 ++
 drivers/gpu/drm/i915/gt/intel_gtt.c           |   6 +
 drivers/gpu/drm/i915/gt/intel_gtt.h           |   1 +
 drivers/gpu/drm/i915/i915_drm_client.c        | 131 ++++++++++++++++++
 drivers/gpu/drm/i915/i915_drm_client.h        |  41 ++++++
 10 files changed, 228 insertions(+), 8 deletions(-)

-- 
2.39.2

[Intel-gfx] [PATCH 4/5] drm/i915: Account ring buffer and context state storage

[Tvrtko Ursulin]

From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

Account ring buffers and logical context space against the owning client
memory usage stats.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Aravind Iddamsetty <aravind.iddamsetty@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_context.c | 14 ++++++++++++++
 drivers/gpu/drm/i915/i915_drm_client.c  | 10 ++++++++++
 drivers/gpu/drm/i915/i915_drm_client.h  |  9 +++++++++
 3 files changed, 33 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index a53b26178f0a..a2f1245741bb 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -6,6 +6,7 @@
 #include "gem/i915_gem_context.h"
 #include "gem/i915_gem_pm.h"
 
+#include "i915_drm_client.h"
 #include "i915_drv.h"
 #include "i915_trace.h"
 
@@ -50,6 +51,7 @@ intel_context_create(struct intel_engine_cs *engine)
 
 int intel_context_alloc_state(struct intel_context *ce)
 {
+	struct i915_gem_context *ctx;
 	int err = 0;
 
 	if (mutex_lock_interruptible(&ce->pin_mutex))
@@ -66,6 +68,18 @@ int intel_context_alloc_state(struct intel_context *ce)
 			goto unlock;
 
 		set_bit(CONTEXT_ALLOC_BIT, &ce->flags);
+
+		rcu_read_lock();
+		ctx = rcu_dereference(ce->gem_context);
+		if (ctx && !kref_get_unless_zero(&ctx->ref))
+			ctx = NULL;
+		rcu_read_unlock();
+		if (ctx) {
+			if (ctx->client)
+				i915_drm_client_add_context_objects(ctx->client,
+								    ce);
+			i915_gem_context_put(ctx);
+		}
 	}
 
 unlock:
diff --git a/drivers/gpu/drm/i915/i915_drm_client.c b/drivers/gpu/drm/i915/i915_drm_client.c
index 2e5e69edc0f9..a61356012df8 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.c
+++ b/drivers/gpu/drm/i915/i915_drm_client.c
@@ -144,4 +144,14 @@ bool i915_drm_client_remove_object(struct drm_i915_gem_object *obj)
 
 	return true;
 }
+
+void i915_drm_client_add_context_objects(struct i915_drm_client *client,
+					 struct intel_context *ce)
+{
+	if (ce->state)
+		i915_drm_client_add_object(client, ce->state->obj);
+
+	if (ce->ring != ce->engine->legacy.ring && ce->ring->vma)
+		i915_drm_client_add_object(client, ce->ring->vma->obj);
+}
 #endif
diff --git a/drivers/gpu/drm/i915/i915_drm_client.h b/drivers/gpu/drm/i915/i915_drm_client.h
index 5f58fdf7dcb8..69cedfcd3d69 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.h
+++ b/drivers/gpu/drm/i915/i915_drm_client.h
@@ -14,6 +14,7 @@
 
 #include "i915_file_private.h"
 #include "gem/i915_gem_object_types.h"
+#include "gt/intel_context_types.h"
 
 #define I915_LAST_UABI_ENGINE_CLASS I915_ENGINE_CLASS_COMPUTE
 
@@ -70,6 +71,8 @@ void i915_drm_client_fdinfo(struct drm_printer *p, struct drm_file *file);
 void i915_drm_client_add_object(struct i915_drm_client *client,
 				struct drm_i915_gem_object *obj);
 bool i915_drm_client_remove_object(struct drm_i915_gem_object *obj);
+void i915_drm_client_add_context_objects(struct i915_drm_client *client,
+					 struct intel_context *ce);
 #else
 static inline void i915_drm_client_add_object(struct i915_drm_client *client,
 					      struct drm_i915_gem_object *obj)
@@ -79,6 +82,12 @@ static inline void i915_drm_client_add_object(struct i915_drm_client *client,
 static inline bool i915_drm_client_remove_object(struct drm_i915_gem_object *obj)
 {
 }
+
+static inline void
+i915_drm_client_add_context_objects(struct i915_drm_client *client,
+				    struct intel_context *ce)
+{
+}
 #endif
 
 #endif /* !__I915_DRM_CLIENT_H__ */
-- 
2.39.2

[Intel-gfx] [PATCH v5 0/5] fdinfo memory stats

[Tvrtko Ursulin]

From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

I added tracking of most classes of objects which contribute to client's memory
footprint and accouting along the similar lines as in Rob's msm code. Then
printing it out to fdinfo using the drm helper Rob added.

Accounting by keeping per client lists may not be the most effient method,
perhaps we should simply add and subtract stats directly at convenient sites,
but that too is not straightforward due no existing connection between buffer
objects and clients. Possibly some other tricky bits in the buffer sharing
deparment. So lets see if this works for now. Infrequent reader penalty should
not be too bad (may be even useful to dump the lists in debugfs?) and additional
list_head per object pretty much drowns in the noise.

Example fdinfo with the series applied:

# cat /proc/1383/fdinfo/8
pos:    0
flags:  02100002
mnt_id: 21
ino:    397
drm-driver:     i915
drm-client-id:  18
drm-pdev:       0000:00:02.0
drm-total-system:       125 MiB
drm-shared-system:      16 MiB
drm-active-system:      110 MiB
drm-resident-system:    125 MiB
drm-purgeable-system:   2 MiB
drm-total-stolen-system:        0
drm-shared-stolen-system:       0
drm-active-stolen-system:       0
drm-resident-stolen-system:     0
drm-purgeable-stolen-system:    0
drm-engine-render:      25662044495 ns
drm-engine-copy:        0 ns
drm-engine-video:       0 ns
drm-engine-video-enhance:       0 ns

Example gputop output (local patches currently):

DRM minor 0
 PID     SMEM  SMEMRSS   render     copy     video    NAME
1233     124M     124M |████████||        ||        ||        | neverball
1130      59M      59M |█▌      ||        ||        ||        | Xorg
1207      12M      12M |        ||        ||        ||        | xfwm4

v2:
 * Now actually per client.

v3:
 * Track imported dma-buf objects.

v4:
 * Rely on DRM GEM handles for tracking user objects.
 * Fix internal object accounting (no placements).

v5:
 * Fixed brain fart of overwriting the loop cursor.
 * Fixed object destruction racing with fdinfo reads.
 * Take reference to GEM context while using it.

Tvrtko Ursulin (5):
  drm/i915: Add ability for tracking buffer objects per client
  drm/i915: Record which client owns a VM
  drm/i915: Track page table backing store usage
  drm/i915: Account ring buffer and context state storage
  drm/i915: Implement fdinfo memory stats printing

 drivers/gpu/drm/i915/gem/i915_gem_context.c   |  11 +-
 .../gpu/drm/i915/gem/i915_gem_context_types.h |   3 +
 drivers/gpu/drm/i915/gem/i915_gem_object.c    |  13 +-
 .../gpu/drm/i915/gem/i915_gem_object_types.h  |  12 ++
 .../gpu/drm/i915/gem/selftests/mock_context.c |   4 +-
 drivers/gpu/drm/i915/gt/intel_context.c       |  13 ++
 drivers/gpu/drm/i915/gt/intel_gtt.c           |   6 +
 drivers/gpu/drm/i915/gt/intel_gtt.h           |   1 +
 drivers/gpu/drm/i915/i915_drm_client.c        | 131 ++++++++++++++++++
 drivers/gpu/drm/i915/i915_drm_client.h        |  40 ++++++
 10 files changed, 226 insertions(+), 8 deletions(-)

-- 
2.39.2

[Intel-gfx] [PATCH 4/5] drm/i915: Account ring buffer and context state storage

[Tvrtko Ursulin]

From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

Account ring buffers and logical context space against the owning client
memory usage stats.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_context.c | 13 +++++++++++++
 drivers/gpu/drm/i915/i915_drm_client.c  | 10 ++++++++++
 drivers/gpu/drm/i915/i915_drm_client.h  |  8 ++++++++
 3 files changed, 31 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index a53b26178f0a..8a395b9201e9 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -6,6 +6,7 @@
 #include "gem/i915_gem_context.h"
 #include "gem/i915_gem_pm.h"
 
+#include "i915_drm_client.h"
 #include "i915_drv.h"
 #include "i915_trace.h"
 
@@ -50,6 +51,7 @@ intel_context_create(struct intel_engine_cs *engine)
 
 int intel_context_alloc_state(struct intel_context *ce)
 {
+	struct i915_gem_context *ctx;
 	int err = 0;
 
 	if (mutex_lock_interruptible(&ce->pin_mutex))
@@ -66,6 +68,17 @@ int intel_context_alloc_state(struct intel_context *ce)
 			goto unlock;
 
 		set_bit(CONTEXT_ALLOC_BIT, &ce->flags);
+
+		rcu_read_lock();
+		ctx = rcu_dereference(ce->gem_context);
+		if (ctx && !kref_get_unless_zero(&ctx->ref))
+			ctx = NULL;
+		rcu_read_unlock();
+		if (ctx) {
+			if (ctx->client)
+				i915_drm_client_add_context(ctx->client, ce);
+			i915_gem_context_put(ctx);
+		}
 	}
 
 unlock:
diff --git a/drivers/gpu/drm/i915/i915_drm_client.c b/drivers/gpu/drm/i915/i915_drm_client.c
index 2e5e69edc0f9..ffccb6239789 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.c
+++ b/drivers/gpu/drm/i915/i915_drm_client.c
@@ -144,4 +144,14 @@ bool i915_drm_client_remove_object(struct drm_i915_gem_object *obj)
 
 	return true;
 }
+
+void i915_drm_client_add_context(struct i915_drm_client *client,
+				 struct intel_context *ce)
+{
+	if (ce->state)
+		i915_drm_client_add_object(client, ce->state->obj);
+
+	if (ce->ring != ce->engine->legacy.ring && ce->ring->vma)
+		i915_drm_client_add_object(client, ce->ring->vma->obj);
+}
 #endif
diff --git a/drivers/gpu/drm/i915/i915_drm_client.h b/drivers/gpu/drm/i915/i915_drm_client.h
index 5f58fdf7dcb8..39616b10a51f 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.h
+++ b/drivers/gpu/drm/i915/i915_drm_client.h
@@ -14,6 +14,7 @@
 
 #include "i915_file_private.h"
 #include "gem/i915_gem_object_types.h"
+#include "gt/intel_context_types.h"
 
 #define I915_LAST_UABI_ENGINE_CLASS I915_ENGINE_CLASS_COMPUTE
 
@@ -70,6 +71,8 @@ void i915_drm_client_fdinfo(struct drm_printer *p, struct drm_file *file);
 void i915_drm_client_add_object(struct i915_drm_client *client,
 				struct drm_i915_gem_object *obj);
 bool i915_drm_client_remove_object(struct drm_i915_gem_object *obj);
+void i915_drm_client_add_context(struct i915_drm_client *client,
+				 struct intel_context *ce);
 #else
 static inline void i915_drm_client_add_object(struct i915_drm_client *client,
 					      struct drm_i915_gem_object *obj)
@@ -79,6 +82,11 @@ static inline void i915_drm_client_add_object(struct i915_drm_client *client,
 static inline bool i915_drm_client_remove_object(struct drm_i915_gem_object *obj)
 {
 }
+
+static inline void i915_drm_client_add_context(struct i915_drm_client *client,
+					       struct intel_context *ce)
+{
+}
 #endif
 
 #endif /* !__I915_DRM_CLIENT_H__ */
-- 
2.39.2

Re: [Intel-gfx] [PATCH 4/5] drm/i915: Account ring buffer and context state storage

[Iddamsetty, Aravind]

On 07-07-2023 18:32, Tvrtko Ursulin wrote:
> From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
> 
> Account ring buffers and logical context space against the owning client
> memory usage stats.
> 
> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
> ---
>  drivers/gpu/drm/i915/gt/intel_context.c | 13 +++++++++++++
>  drivers/gpu/drm/i915/i915_drm_client.c  | 10 ++++++++++
>  drivers/gpu/drm/i915/i915_drm_client.h  |  8 ++++++++
>  3 files changed, 31 insertions(+)
> 
> diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
> index a53b26178f0a..8a395b9201e9 100644
> --- a/drivers/gpu/drm/i915/gt/intel_context.c
> +++ b/drivers/gpu/drm/i915/gt/intel_context.c
> @@ -6,6 +6,7 @@
>  #include "gem/i915_gem_context.h"
>  #include "gem/i915_gem_pm.h"
>  
> +#include "i915_drm_client.h"
>  #include "i915_drv.h"
>  #include "i915_trace.h"
>  
> @@ -50,6 +51,7 @@ intel_context_create(struct intel_engine_cs *engine)
>  
>  int intel_context_alloc_state(struct intel_context *ce)
>  {
> +	struct i915_gem_context *ctx;
>  	int err = 0;
>  
>  	if (mutex_lock_interruptible(&ce->pin_mutex))
> @@ -66,6 +68,17 @@ int intel_context_alloc_state(struct intel_context *ce)
>  			goto unlock;
>  
>  		set_bit(CONTEXT_ALLOC_BIT, &ce->flags);
> +
> +		rcu_read_lock();
> +		ctx = rcu_dereference(ce->gem_context);
> +		if (ctx && !kref_get_unless_zero(&ctx->ref))
> +			ctx = NULL;
> +		rcu_read_unlock();
> +		if (ctx) {
> +			if (ctx->client)
> +				i915_drm_client_add_context(ctx->client, ce);
> +			i915_gem_context_put(ctx);
> +		}
>  	}
>  
>  unlock:
> diff --git a/drivers/gpu/drm/i915/i915_drm_client.c b/drivers/gpu/drm/i915/i915_drm_client.c
> index 2e5e69edc0f9..ffccb6239789 100644
> --- a/drivers/gpu/drm/i915/i915_drm_client.c
> +++ b/drivers/gpu/drm/i915/i915_drm_client.c
> @@ -144,4 +144,14 @@ bool i915_drm_client_remove_object(struct drm_i915_gem_object *obj)
>  
>  	return true;
>  }
> +
> +void i915_drm_client_add_context(struct i915_drm_client *client,
> +				 struct intel_context *ce)

do you think we can rename to i915_drm_client_add_context_objects?

> +{
> +	if (ce->state)
> +		i915_drm_client_add_object(client, ce->state->obj);
> +
> +	if (ce->ring != ce->engine->legacy.ring && ce->ring->vma)
> +		i915_drm_client_add_object(client, ce->ring->vma->obj);
> +}
>  #endif
> diff --git a/drivers/gpu/drm/i915/i915_drm_client.h b/drivers/gpu/drm/i915/i915_drm_client.h
> index 5f58fdf7dcb8..39616b10a51f 100644
> --- a/drivers/gpu/drm/i915/i915_drm_client.h
> +++ b/drivers/gpu/drm/i915/i915_drm_client.h
> @@ -14,6 +14,7 @@
>  
>  #include "i915_file_private.h"
>  #include "gem/i915_gem_object_types.h"
> +#include "gt/intel_context_types.h"
>  
>  #define I915_LAST_UABI_ENGINE_CLASS I915_ENGINE_CLASS_COMPUTE
>  
> @@ -70,6 +71,8 @@ void i915_drm_client_fdinfo(struct drm_printer *p, struct drm_file *file);
>  void i915_drm_client_add_object(struct i915_drm_client *client,
>  				struct drm_i915_gem_object *obj);
>  bool i915_drm_client_remove_object(struct drm_i915_gem_object *obj);
> +void i915_drm_client_add_context(struct i915_drm_client *client,
> +				 struct intel_context *ce);
>  #else
>  static inline void i915_drm_client_add_object(struct i915_drm_client *client,
>  					      struct drm_i915_gem_object *obj)
> @@ -79,6 +82,11 @@ static inline void i915_drm_client_add_object(struct i915_drm_client *client,
>  static inline bool i915_drm_client_remove_object(struct drm_i915_gem_object *obj)
>  {
>  }
> +
> +static inline void i915_drm_client_add_context(struct i915_drm_client *client,
> +					       struct intel_context *ce)
> +{
> +}
>  #endif
>  
>  #endif /* !__I915_DRM_CLIENT_H__ */

Reviewed-by: Aravind Iddamsetty <aravind.iddamsetty@intel.com>

Thanks,
Aravind.

Re: [Intel-gfx] [PATCH 4/5] drm/i915: Account ring buffer and context state storage

[Tvrtko Ursulin]

On 11/07/2023 10:29, Iddamsetty, Aravind wrote:
> 
> 
> On 07-07-2023 18:32, Tvrtko Ursulin wrote:
>> From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
>>
>> Account ring buffers and logical context space against the owning client
>> memory usage stats.
>>
>> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
>> ---
>>   drivers/gpu/drm/i915/gt/intel_context.c | 13 +++++++++++++
>>   drivers/gpu/drm/i915/i915_drm_client.c  | 10 ++++++++++
>>   drivers/gpu/drm/i915/i915_drm_client.h  |  8 ++++++++
>>   3 files changed, 31 insertions(+)
>>
>> diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
>> index a53b26178f0a..8a395b9201e9 100644
>> --- a/drivers/gpu/drm/i915/gt/intel_context.c
>> +++ b/drivers/gpu/drm/i915/gt/intel_context.c
>> @@ -6,6 +6,7 @@
>>   #include "gem/i915_gem_context.h"
>>   #include "gem/i915_gem_pm.h"
>>   
>> +#include "i915_drm_client.h"
>>   #include "i915_drv.h"
>>   #include "i915_trace.h"
>>   
>> @@ -50,6 +51,7 @@ intel_context_create(struct intel_engine_cs *engine)
>>   
>>   int intel_context_alloc_state(struct intel_context *ce)
>>   {
>> +	struct i915_gem_context *ctx;
>>   	int err = 0;
>>   
>>   	if (mutex_lock_interruptible(&ce->pin_mutex))
>> @@ -66,6 +68,17 @@ int intel_context_alloc_state(struct intel_context *ce)
>>   			goto unlock;
>>   
>>   		set_bit(CONTEXT_ALLOC_BIT, &ce->flags);
>> +
>> +		rcu_read_lock();
>> +		ctx = rcu_dereference(ce->gem_context);
>> +		if (ctx && !kref_get_unless_zero(&ctx->ref))
>> +			ctx = NULL;
>> +		rcu_read_unlock();
>> +		if (ctx) {
>> +			if (ctx->client)
>> +				i915_drm_client_add_context(ctx->client, ce);
>> +			i915_gem_context_put(ctx);
>> +		}
>>   	}
>>   
>>   unlock:
>> diff --git a/drivers/gpu/drm/i915/i915_drm_client.c b/drivers/gpu/drm/i915/i915_drm_client.c
>> index 2e5e69edc0f9..ffccb6239789 100644
>> --- a/drivers/gpu/drm/i915/i915_drm_client.c
>> +++ b/drivers/gpu/drm/i915/i915_drm_client.c
>> @@ -144,4 +144,14 @@ bool i915_drm_client_remove_object(struct drm_i915_gem_object *obj)
>>   
>>   	return true;
>>   }
>> +
>> +void i915_drm_client_add_context(struct i915_drm_client *client,
>> +				 struct intel_context *ce)
> 
> do you think we can rename to i915_drm_client_add_context_objects?

I like it, will do, thanks!

Regards,

Tvrtko

> 
>> +{
>> +	if (ce->state)
>> +		i915_drm_client_add_object(client, ce->state->obj);
>> +
>> +	if (ce->ring != ce->engine->legacy.ring && ce->ring->vma)
>> +		i915_drm_client_add_object(client, ce->ring->vma->obj);
>> +}
>>   #endif
>> diff --git a/drivers/gpu/drm/i915/i915_drm_client.h b/drivers/gpu/drm/i915/i915_drm_client.h
>> index 5f58fdf7dcb8..39616b10a51f 100644
>> --- a/drivers/gpu/drm/i915/i915_drm_client.h
>> +++ b/drivers/gpu/drm/i915/i915_drm_client.h
>> @@ -14,6 +14,7 @@
>>   
>>   #include "i915_file_private.h"
>>   #include "gem/i915_gem_object_types.h"
>> +#include "gt/intel_context_types.h"
>>   
>>   #define I915_LAST_UABI_ENGINE_CLASS I915_ENGINE_CLASS_COMPUTE
>>   
>> @@ -70,6 +71,8 @@ void i915_drm_client_fdinfo(struct drm_printer *p, struct drm_file *file);
>>   void i915_drm_client_add_object(struct i915_drm_client *client,
>>   				struct drm_i915_gem_object *obj);
>>   bool i915_drm_client_remove_object(struct drm_i915_gem_object *obj);
>> +void i915_drm_client_add_context(struct i915_drm_client *client,
>> +				 struct intel_context *ce);
>>   #else
>>   static inline void i915_drm_client_add_object(struct i915_drm_client *client,
>>   					      struct drm_i915_gem_object *obj)
>> @@ -79,6 +82,11 @@ static inline void i915_drm_client_add_object(struct i915_drm_client *client,
>>   static inline bool i915_drm_client_remove_object(struct drm_i915_gem_object *obj)
>>   {
>>   }
>> +
>> +static inline void i915_drm_client_add_context(struct i915_drm_client *client,
>> +					       struct intel_context *ce)
>> +{
>> +}
>>   #endif
>>   
>>   #endif /* !__I915_DRM_CLIENT_H__ */
> 
> Reviewed-by: Aravind Iddamsetty <aravind.iddamsetty@intel.com>
> 
> Thanks,
> Aravind.

[Intel-gfx] [PATCH v2 0/5] fdinfo memory stats

[Tvrtko Ursulin]

From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

Second try, this time actually per client! :)

I added tracking of most classes of objects which contribute to clients memory
footprint and accouting along the similar lines as in Rob's msm code. Then
printing it out to fdinfo using the drm helper Rob added.

Example fdinfo with the series applied:

# cat /proc/1383/fdinfo/8
pos:    0
flags:  02100002
mnt_id: 21
ino:    397
drm-driver:     i915
drm-client-id:  18
drm-pdev:       0000:00:02.0
drm-total-system:       125 MiB
drm-shared-system:      16 MiB
drm-active-system:      110 MiB
drm-resident-system:    125 MiB
drm-purgeable-system:   2 MiB
drm-total-stolen-system:        0
drm-shared-stolen-system:       0
drm-active-stolen-system:       0
drm-resident-stolen-system:     0
drm-purgeable-stolen-system:    0
drm-engine-render:      25662044495 ns
drm-engine-copy:        0 ns
drm-engine-video:       0 ns
drm-engine-video-enhance:       0 ns

Tvrtko Ursulin (5):
  drm/i915: Track buffer objects belonging to clients
  drm/i915: Record which clients own a VM
  drm/i915: Track page table backing store usage
  drm/i915: Account ring buffer and context state storage
  drm/i915: Implement fdinfo memory stats printing

 drivers/gpu/drm/i915/gem/i915_gem_context.c   |  17 ++-
 .../gpu/drm/i915/gem/i915_gem_context_types.h |   3 +
 drivers/gpu/drm/i915/gem/i915_gem_create.c    |  32 ++++-
 drivers/gpu/drm/i915/gem/i915_gem_object.c    |   6 +
 .../gpu/drm/i915/gem/i915_gem_object_types.h  |  12 ++
 drivers/gpu/drm/i915/gt/intel_gtt.c           |   6 +
 drivers/gpu/drm/i915/gt/intel_gtt.h           |   1 +
 drivers/gpu/drm/i915/i915_drm_client.c        | 110 +++++++++++++++++-
 drivers/gpu/drm/i915/i915_drm_client.h        |  46 +++++++-
 drivers/gpu/drm/i915/i915_gem.c               |   2 +-
 10 files changed, 226 insertions(+), 9 deletions(-)

-- 
2.39.2

[Intel-gfx] [PATCH 4/5] drm/i915: Account ring buffer and context state storage

[Tvrtko Ursulin]

From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

Account ring buffers and logical context space against the owning client
memory usage stats.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 drivers/gpu/drm/i915/gem/i915_gem_context.c |  6 ++++++
 drivers/gpu/drm/i915/i915_drm_client.c      | 10 ++++++++++
 drivers/gpu/drm/i915/i915_drm_client.h      |  9 +++++++++
 3 files changed, 25 insertions(+)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 35cf6608180e..3f4c74aed3c5 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -1703,6 +1703,8 @@ static void gem_context_register(struct i915_gem_context *ctx,
 				 u32 id)
 {
 	struct drm_i915_private *i915 = ctx->i915;
+	struct i915_gem_engines_iter it;
+	struct intel_context *ce;
 	void *old;
 
 	ctx->file_priv = fpriv;
@@ -1721,6 +1723,10 @@ static void gem_context_register(struct i915_gem_context *ctx,
 	list_add_tail(&ctx->link, &i915->gem.contexts.list);
 	spin_unlock(&i915->gem.contexts.lock);
 
+	for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it)
+		i915_drm_client_add_context(fpriv->client, ce);
+	i915_gem_context_unlock_engines(ctx);
+
 	/* And finally expose ourselves to userspace via the idr */
 	old = xa_store(&fpriv->context_xa, id, ctx, GFP_KERNEL);
 	WARN_ON(old);
diff --git a/drivers/gpu/drm/i915/i915_drm_client.c b/drivers/gpu/drm/i915/i915_drm_client.c
index 4cacca568375..777930f4995f 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.c
+++ b/drivers/gpu/drm/i915/i915_drm_client.c
@@ -142,4 +142,14 @@ void i915_drm_client_remove_object(struct drm_i915_gem_object *obj)
 
 	i915_drm_client_put(client);
 }
+
+void i915_drm_client_add_context(struct i915_drm_client *client,
+				 struct intel_context *ce)
+{
+	if (ce->state)
+		i915_drm_client_add_object(client, ce->state->obj);
+
+	if (ce->ring != ce->engine->legacy.ring && ce->ring->vma)
+		i915_drm_client_add_object(client, ce->ring->vma->obj);
+}
 #endif
diff --git a/drivers/gpu/drm/i915/i915_drm_client.h b/drivers/gpu/drm/i915/i915_drm_client.h
index 0db68b4d7a4f..a5c29a105af3 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.h
+++ b/drivers/gpu/drm/i915/i915_drm_client.h
@@ -15,6 +15,7 @@
 
 #include "i915_file_private.h"
 #include "gem/i915_gem_object_types.h"
+#include "gt/intel_context_types.h"
 
 #define I915_LAST_UABI_ENGINE_CLASS I915_ENGINE_CLASS_COMPUTE
 
@@ -73,6 +74,8 @@ void i915_drm_client_fdinfo(struct drm_printer *p, struct drm_file *file);
 void i915_drm_client_add_object(struct i915_drm_client *client,
 				struct drm_i915_gem_object *obj);
 void i915_drm_client_remove_object(struct drm_i915_gem_object *obj);
+void i915_drm_client_add_context(struct i915_drm_client *client,
+				 struct intel_context *ce);
 #else
 static inline void i915_drm_client_add_object(struct i915_drm_client *client,
 					      struct drm_i915_gem_object *obj)
@@ -83,6 +86,12 @@ static inline void i915_drm_client_add_object(struct i915_drm_client *client,
 static inline void i915_drm_client_remove_object(struct drm_i915_gem_object *obj)
 {
 
+}
+
+static inline void i915_drm_client_add_context(struct i915_drm_client *client,
+					       struct intel_context *ce)
+{
+
 }
 #endif
 
-- 
2.39.2