Up to this day, all fdinfo-based GPU profilers must traverse the entire
/proc directory structure to find open DRM clients with fdinfo file
descriptors. This is inefficient and time-consuming.

This patch adds a new DRM ioctl that allows users to obtain a list of PIDs
for clients who have opened the DRM device. Output from the ioctl isn't
human-readable, and it's meant to be retrieved only by GPU profilers like
gputop and nvtop.

Cc: Rob Clark <robdcl...@gmail.com>
Cc: Tvrtko Ursulin <tursu...@ursulin.net>
Signed-off-by: Adrián Larumbe <adrian.laru...@collabora.com>
---
 drivers/gpu/drm/drm_internal.h |  1 +
 drivers/gpu/drm/drm_ioctl.c    | 89 ++++++++++++++++++++++++++++++++++
 include/uapi/drm/drm.h         |  7 +++
 3 files changed, 97 insertions(+)

diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h
index 690505a1f7a5..6f78954cae16 100644
--- a/drivers/gpu/drm/drm_internal.h
+++ b/drivers/gpu/drm/drm_internal.h
@@ -243,6 +243,7 @@ static inline void drm_debugfs_encoder_remove(struct 
drm_encoder *encoder)
 drm_ioctl_t drm_version;
 drm_ioctl_t drm_getunique;
 drm_ioctl_t drm_getclient;
+drm_ioctl_t drm_getclients;
 
 /* drm_syncobj.c */
 void drm_syncobj_open(struct drm_file *file_private);
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index e368fc084c77..da7057376581 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -207,6 +207,93 @@ int drm_getclient(struct drm_device *dev, void *data,
        }
 }
 
+/*
+ * Get list of client PIDs who have opened a DRM file
+ *
+ * \param dev DRM device we are querying
+ * \param data IOCTL command input.
+ * \param file_priv DRM file private.
+ *
+ * \return zero on success or a negative number on failure.
+ *
+ * Traverses list of open clients for the given DRM device, and
+ * copies them into userpace as an array of PIDs
+ */
+int drm_getclients(struct drm_device *dev, void *data,
+                  struct drm_file *file_priv)
+
+{
+       struct drm_get_clients *get_clients = data;
+       ssize_t size = get_clients->len;
+       char __user *pid_buf;
+       ssize_t offset = 0;
+       int ret = 0;
+
+       /*
+        * We do not want to show clients of display only devices so
+        * as to avoid confusing UM GPU profilers
+        */
+       if (!dev->render) {
+               get_clients->len = 0;
+               return 0;
+       }
+
+       /*
+        * An input size of zero means UM wants to know the size of the PID 
buffer
+        * We round it up to the nearest multiple of the page size so that we 
can have
+        * some spare headroom in case more clients came in between successive 
calls
+        * of this ioctl, and also to simplify parsing of the PIDs buffer, 
because
+        * sizeof(pid_t) will hopefully always divide PAGE_SIZE
+        */
+       if (size == 0) {
+               get_clients->len =
+                       roundup(atomic_read(&dev->open_count) * sizeof(pid_t), 
PAGE_SIZE);
+               return 0;
+       }
+
+       pid_buf = (char *)(void *)get_clients->user_data;
+
+       if (!pid_buf)
+               return -EINVAL;
+
+       mutex_lock(&dev->filelist_mutex);
+       list_for_each_entry_reverse(file_priv, &dev->filelist, lhead) {
+               pid_t pid_num;
+
+               if ((size - offset) < sizeof(pid_t))
+                       break;
+
+               rcu_read_lock();
+               pid_num = pid_vnr(rcu_dereference(file_priv->pid));
+               rcu_read_unlock();
+
+               /* We do not want to return the profiler's PID */
+               if (pid_vnr(task_tgid(current)) == pid_num)
+                       continue;
+
+               ret = copy_to_user(pid_buf + offset, &pid_num, sizeof(pid_t));
+               if (ret)
+                       break;
+
+               offset += sizeof(pid_t);
+       }
+       mutex_unlock(&dev->filelist_mutex);
+
+       if (ret)
+               return -EFAULT;
+
+       if ((size - offset) >= sizeof(pid_t)) {
+               pid_t pid_zero = 0;
+
+               ret = copy_to_user(pid_buf + offset,
+                                  &pid_zero, sizeof(pid_t));
+               if (ret)
+                       return -EFAULT;
+       }
+
+       return 0;
+}
+
 /*
  * Get statistics information.
  *
@@ -672,6 +759,8 @@ static const struct drm_ioctl_desc drm_ioctls[] = {
        DRM_IOCTL_DEF(DRM_IOCTL_MODE_LIST_LESSEES, drm_mode_list_lessees_ioctl, 
DRM_MASTER),
        DRM_IOCTL_DEF(DRM_IOCTL_MODE_GET_LEASE, drm_mode_get_lease_ioctl, 
DRM_MASTER),
        DRM_IOCTL_DEF(DRM_IOCTL_MODE_REVOKE_LEASE, drm_mode_revoke_lease_ioctl, 
DRM_MASTER),
+
+       DRM_IOCTL_DEF(DRM_IOCTL_GET_CLIENTS, drm_getclients, DRM_RENDER_ALLOW),
 };
 
 #define DRM_CORE_IOCTL_COUNT   ARRAY_SIZE(drm_ioctls)
diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h
index 16122819edfe..c47aa9de51ab 100644
--- a/include/uapi/drm/drm.h
+++ b/include/uapi/drm/drm.h
@@ -1024,6 +1024,11 @@ struct drm_crtc_queue_sequence {
        __u64 user_data;        /* user data passed to event */
 };
 
+struct drm_get_clients {
+       __u64 user_data;
+       __kernel_size_t len;
+};
+
 #if defined(__cplusplus)
 }
 #endif
@@ -1236,6 +1241,8 @@ extern "C" {
 #define DRM_IOCTL_SYNCOBJ_TRANSFER     DRM_IOWR(0xCC, struct 
drm_syncobj_transfer)
 #define DRM_IOCTL_SYNCOBJ_TIMELINE_SIGNAL      DRM_IOWR(0xCD, struct 
drm_syncobj_timeline_array)
 
+#define DRM_IOCTL_GET_CLIENTS          DRM_IOWR(0xD1, struct drm_get_clients)
+
 /**
  * DRM_IOCTL_MODE_GETFB2 - Get framebuffer metadata.
  *
-- 
2.44.0

Reply via email to