drm/amd: Add detailed GFXOFF stats to debugfs

Add debugfs interface to log GFXOFF statistics:

- Read amdgpu_gfxoff_count to get the total GFXOFF entry count at the
  time of query since system power-up

- Write 1 to amdgpu_gfxoff_residency to start logging, and 0 to stop.
  Read it to get average GFXOFF residency % multiplied by 100
  during the last logging interval.

Both features are designed to be keep the values persistent between
suspends.

Signed-off-by: André Almeida <andrealmeid@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

4 files changed, 215 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index 4e54569fa223..6066aebf491c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -1043,6 +1043,157 @@ err:
 }
 
 /**
+ * amdgpu_debugfs_gfxoff_residency_read - Read GFXOFF residency
+ *
+ * @f: open file handle
+ * @buf: User buffer to store read data in
+ * @size: Number of bytes to read
+ * @pos:  Offset to seek to
+ *
+ * Read the last residency value logged. It doesn't auto update, one needs to
+ * stop logging before getting the current value.
+ */
+static ssize_t amdgpu_debugfs_gfxoff_residency_read(struct file *f, char __user *buf,
+						    size_t size, loff_t *pos)
+{
+	struct amdgpu_device *adev = file_inode(f)->i_private;
+	ssize_t result = 0;
+	int r;
+
+	if (size & 0x3 || *pos & 0x3)
+		return -EINVAL;
+
+	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
+	if (r < 0) {
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
+		return r;
+	}
+
+	while (size) {
+		uint32_t value;
+
+		r = amdgpu_get_gfx_off_residency(adev, &value);
+		if (r)
+			goto out;
+
+		r = put_user(value, (uint32_t *)buf);
+		if (r)
+			goto out;
+
+		result += 4;
+		buf += 4;
+		*pos += 4;
+		size -= 4;
+	}
+
+	r = result;
+out:
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
+
+	return r;
+}
+
+/**
+ * amdgpu_debugfs_gfxoff_residency_write - Log GFXOFF Residency
+ *
+ * @f: open file handle
+ * @buf: User buffer to write data from
+ * @size: Number of bytes to write
+ * @pos:  Offset to seek to
+ *
+ * Write a 32-bit non-zero to start logging; write a 32-bit zero to stop
+ */
+static ssize_t amdgpu_debugfs_gfxoff_residency_write(struct file *f, const char __user *buf,
+						     size_t size, loff_t *pos)
+{
+	struct amdgpu_device *adev = file_inode(f)->i_private;
+	ssize_t result = 0;
+	int r;
+
+	if (size & 0x3 || *pos & 0x3)
+		return -EINVAL;
+
+	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
+	if (r < 0) {
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
+		return r;
+	}
+
+	while (size) {
+		u32 value;
+
+		r = get_user(value, (uint32_t *)buf);
+		if (r)
+			goto out;
+
+		amdgpu_set_gfx_off_residency(adev, value ? true : false);
+
+		result += 4;
+		buf += 4;
+		*pos += 4;
+		size -= 4;
+	}
+
+	r = result;
+out:
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
+
+	return r;
+}
+
+
+/**
+ * amdgpu_debugfs_gfxoff_count_read - Read GFXOFF entry count
+ *
+ * @f: open file handle
+ * @buf: User buffer to store read data in
+ * @size: Number of bytes to read
+ * @pos:  Offset to seek to
+ */
+static ssize_t amdgpu_debugfs_gfxoff_count_read(struct file *f, char __user *buf,
+						size_t size, loff_t *pos)
+{
+	struct amdgpu_device *adev = file_inode(f)->i_private;
+	ssize_t result = 0;
+	int r;
+
+	if (size & 0x3 || *pos & 0x3)
+		return -EINVAL;
+
+	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
+	if (r < 0) {
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
+		return r;
+	}
+
+	while (size) {
+		u64 value = 0;
+
+		r = amdgpu_get_gfx_off_entrycount(adev, &value);
+		if (r)
+			goto out;
+
+		r = put_user(value, (u64 *)buf);
+		if (r)
+			goto out;
+
+		result += 4;
+		buf += 4;
+		*pos += 4;
+		size -= 4;
+	}
+
+	r = result;
+out:
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
+
+	return r;
+}
+
+/**
  * amdgpu_debugfs_gfxoff_write - Enable/disable GFXOFF
  *
  * @f: open file handle
@@ -1249,6 +1400,19 @@ static const struct file_operations amdgpu_debugfs_gfxoff_status_fops = {
 	.llseek = default_llseek
 };
 
+static const struct file_operations amdgpu_debugfs_gfxoff_count_fops = {
+	.owner = THIS_MODULE,
+	.read = amdgpu_debugfs_gfxoff_count_read,
+	.llseek = default_llseek
+};
+
+static const struct file_operations amdgpu_debugfs_gfxoff_residency_fops = {
+	.owner = THIS_MODULE,
+	.read = amdgpu_debugfs_gfxoff_residency_read,
+	.write = amdgpu_debugfs_gfxoff_residency_write,
+	.llseek = default_llseek
+};
+
 static const struct file_operations *debugfs_regs[] = {
 	&amdgpu_debugfs_regs_fops,
 	&amdgpu_debugfs_regs2_fops,
@@ -1261,6 +1425,8 @@ static const struct file_operations *debugfs_regs[] = {
 	&amdgpu_debugfs_gpr_fops,
 	&amdgpu_debugfs_gfxoff_fops,
 	&amdgpu_debugfs_gfxoff_status_fops,
+	&amdgpu_debugfs_gfxoff_count_fops,
+	&amdgpu_debugfs_gfxoff_residency_fops,
 };
 
 static const char *debugfs_regs_names[] = {
@@ -1275,6 +1441,8 @@ static const char *debugfs_regs_names[] = {
 	"amdgpu_gpr",
 	"amdgpu_gfxoff",
 	"amdgpu_gfxoff_status",
+	"amdgpu_gfxoff_count",
+	"amdgpu_gfxoff_residency",
 };
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index c84fdef0ac45..9cb6340c0247 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3577,6 +3577,8 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	INIT_WORK(&adev->xgmi_reset_work, amdgpu_device_xgmi_reset_func);
 
 	adev->gfx.gfx_off_req_count = 1;
+	adev->gfx.gfx_off_residency = 0;
+	adev->gfx.gfx_off_entrycount = 0;
 	adev->pm.ac_power = power_supply_is_system_supplied() > 0;
 
 	atomic_set(&adev->throttling_logging_enabled, 1);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index 454a78ba60d4..ceb91469958a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -610,6 +610,45 @@ unlock:
 	mutex_unlock(&adev->gfx.gfx_off_mutex);
 }
 
+int amdgpu_set_gfx_off_residency(struct amdgpu_device *adev, bool value)
+{
+	int r = 0;
+
+	mutex_lock(&adev->gfx.gfx_off_mutex);
+
+	r = amdgpu_dpm_set_residency_gfxoff(adev, value);
+
+	mutex_unlock(&adev->gfx.gfx_off_mutex);
+
+	return r;
+}
+
+int amdgpu_get_gfx_off_residency(struct amdgpu_device *adev, u32 *value)
+{
+	int r = 0;
+
+	mutex_lock(&adev->gfx.gfx_off_mutex);
+
+	r = amdgpu_dpm_get_residency_gfxoff(adev, value);
+
+	mutex_unlock(&adev->gfx.gfx_off_mutex);
+
+	return r;
+}
+
+int amdgpu_get_gfx_off_entrycount(struct amdgpu_device *adev, u64 *value)
+{
+	int r = 0;
+
+	mutex_lock(&adev->gfx.gfx_off_mutex);
+
+	r = amdgpu_dpm_get_entrycount_gfxoff(adev, value);
+
+	mutex_unlock(&adev->gfx.gfx_off_mutex);
+
+	return r;
+}
+
 int amdgpu_get_gfx_off_status(struct amdgpu_device *adev, uint32_t *value)
 {
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index 23a696d38390..1b8b4a5270c9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -336,6 +336,8 @@ struct amdgpu_gfx {
 	struct mutex                    gfx_off_mutex;
 	uint32_t                        gfx_off_req_count; /* default 1, enable gfx off: dec 1, disable gfx off: add 1 */
 	struct delayed_work             gfx_off_delay_work;
+	uint32_t                        gfx_off_residency;
+	uint64_t                        gfx_off_entrycount;
 
 	/* pipe reservation */
 	struct mutex			pipe_reserve_mutex;
@@ -407,6 +409,10 @@ bool amdgpu_gfx_is_me_queue_enabled(struct amdgpu_device *adev, int me,
 void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable);
 int amdgpu_get_gfx_off_status(struct amdgpu_device *adev, uint32_t *value);
 int amdgpu_gfx_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *ras_block);
+void amdgpu_gfx_ras_fini(struct amdgpu_device *adev);
+int amdgpu_get_gfx_off_entrycount(struct amdgpu_device *adev, u64 *value);
+int amdgpu_get_gfx_off_residency(struct amdgpu_device *adev, u32 *residency);
+int amdgpu_set_gfx_off_residency(struct amdgpu_device *adev, bool value);
 int amdgpu_gfx_process_ras_data_cb(struct amdgpu_device *adev,
 		void *err_data,
 		struct amdgpu_iv_entry *entry);