diff mbox series

[v2] drm/msm: Check for powered down HW in the devfreq callbacks

Message ID 20200501190320.17681-1-jcrouse@codeaurora.org
State Superseded
Headers show
Series [v2] drm/msm: Check for powered down HW in the devfreq callbacks | expand

Commit Message

Jordan Crouse May 1, 2020, 7:03 p.m. UTC
Writing to the devfreq sysfs nodes while the GPU is powered down can
result in a system crash (on a5xx) or a nasty GMU error (on a6xx):

 $ /sys/class/devfreq/5000000.gpu# echo 500000000 > min_freq
  [  104.841625] platform 506a000.gmu: [drm:a6xx_gmu_set_oob]
	*ERROR* Timeout waiting for GMU OOB set GPU_DCVS: 0x0

Despite the fact that we carefully try to suspend the devfreq device when
the hardware is powered down there are lots of holes in the governors that
don't check for the suspend state and blindly call into the devfreq
callbacks that end up triggering hardware reads in the GPU driver.

Call pm_runtime_get_if_in_use() in the gpu_busy() and gpu_set_freq()
callbacks to skip the hardware access if it isn't active.

v2: Use pm_runtime_get_if_in_use() per Eric Anholt

Cc: stable@vger.kernel.org
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
---

 drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 6 ++++++
 drivers/gpu/drm/msm/adreno/a6xx_gmu.c | 8 ++++++++
 drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 7 +++++++
 3 files changed, 21 insertions(+)

Comments

Eric Anholt May 1, 2020, 7:26 p.m. UTC | #1
On Fri, May 1, 2020 at 12:03 PM Jordan Crouse <jcrouse@codeaurora.org> wrote:
>
> Writing to the devfreq sysfs nodes while the GPU is powered down can
> result in a system crash (on a5xx) or a nasty GMU error (on a6xx):
>
>  $ /sys/class/devfreq/5000000.gpu# echo 500000000 > min_freq
>   [  104.841625] platform 506a000.gmu: [drm:a6xx_gmu_set_oob]
>         *ERROR* Timeout waiting for GMU OOB set GPU_DCVS: 0x0
>
> Despite the fact that we carefully try to suspend the devfreq device when
> the hardware is powered down there are lots of holes in the governors that
> don't check for the suspend state and blindly call into the devfreq
> callbacks that end up triggering hardware reads in the GPU driver.
>
> Call pm_runtime_get_if_in_use() in the gpu_busy() and gpu_set_freq()
> callbacks to skip the hardware access if it isn't active.
>
> v2: Use pm_runtime_get_if_in_use() per Eric Anholt
>
> Cc: stable@vger.kernel.org
> Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
> ---
>
>  drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 6 ++++++
>  drivers/gpu/drm/msm/adreno/a6xx_gmu.c | 8 ++++++++
>  drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 7 +++++++
>  3 files changed, 21 insertions(+)
>
> diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
> index 724024a2243a..4d7f269edfcc 100644
> --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
> +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
> @@ -1404,6 +1404,10 @@ static unsigned long a5xx_gpu_busy(struct msm_gpu *gpu)
>  {
>         u64 busy_cycles, busy_time;
>
> +       /* Only read the gpu busy if the hardware is already active */
> +       if (pm_runtime_get_if_in_use(&gpu->pdev->dev) <= 0)
> +               return 0;
> +

RPM's APIs are a bit of a trap and will return a negative errno for
the get functions if runtime PM is disabled in kconfig, even though
usually that would mean that the power domain is not ever disabled by
RPM.  I think in these checks you want "if (pm_runtime_get_if_in_use()
== 0)", and that seems to be a common pattern in other drivers.  With
that,

Reviewed-by: Eric Anholt <eric@anholt.net>

(and tested, too)
diff mbox series

Patch

diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index 724024a2243a..4d7f269edfcc 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -1404,6 +1404,10 @@  static unsigned long a5xx_gpu_busy(struct msm_gpu *gpu)
 {
 	u64 busy_cycles, busy_time;
 
+	/* Only read the gpu busy if the hardware is already active */
+	if (pm_runtime_get_if_in_use(&gpu->pdev->dev) <= 0)
+		return 0;
+
 	busy_cycles = gpu_read64(gpu, REG_A5XX_RBBM_PERFCTR_RBBM_0_LO,
 			REG_A5XX_RBBM_PERFCTR_RBBM_0_HI);
 
@@ -1412,6 +1416,8 @@  static unsigned long a5xx_gpu_busy(struct msm_gpu *gpu)
 
 	gpu->devfreq.busy_cycles = busy_cycles;
 
+	pm_runtime_put(&gpu->pdev->dev);
+
 	if (WARN_ON(busy_time > ~0LU))
 		return ~0LU;
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index c4e71abbdd53..8ace989b11db 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -108,6 +108,13 @@  static void __a6xx_gmu_set_freq(struct a6xx_gmu *gmu, int index)
 	struct msm_gpu *gpu = &adreno_gpu->base;
 	int ret;
 
+	/*
+	 * This can get called from devfreq while the hardware is idle. Don't
+	 * bring up the power if it isn't already active
+	 */
+	if (pm_runtime_get_if_in_use(gmu->dev) <= 0)
+		return;
+
 	gmu_write(gmu, REG_A6XX_GMU_DCVS_ACK_OPTION, 0);
 
 	gmu_write(gmu, REG_A6XX_GMU_DCVS_PERF_SETTING,
@@ -134,6 +141,7 @@  static void __a6xx_gmu_set_freq(struct a6xx_gmu *gmu, int index)
 	 * for now leave it at max so that the performance is nominal.
 	 */
 	icc_set_bw(gpu->icc_path, 0, MBps_to_icc(7216));
+	pm_runtime_put(gmu->dev);
 }
 
 void a6xx_gmu_set_freq(struct msm_gpu *gpu, unsigned long freq)
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 68af24150de5..bf43eb2fb078 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -810,6 +810,11 @@  static unsigned long a6xx_gpu_busy(struct msm_gpu *gpu)
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
 	u64 busy_cycles, busy_time;
 
+
+	/* Only read the gpu busy if the hardware is already active */
+	if (pm_runtime_get_if_in_use(a6xx_gpu->gmu.dev) <= 0)
+		return 0;
+
 	busy_cycles = gmu_read64(&a6xx_gpu->gmu,
 			REG_A6XX_GMU_CX_GMU_POWER_COUNTER_XOCLK_0_L,
 			REG_A6XX_GMU_CX_GMU_POWER_COUNTER_XOCLK_0_H);
@@ -819,6 +824,8 @@  static unsigned long a6xx_gpu_busy(struct msm_gpu *gpu)
 
 	gpu->devfreq.busy_cycles = busy_cycles;
 
+	pm_runtime_put(a6xx_gpu->gmu.dev);
+
 	if (WARN_ON(busy_time > ~0LU))
 		return ~0LU;