Skip to contentSkip to conversation

drm/msm/dsi: add protection against NULL dsi device

PATCH Superseded Abhinav Kumar 3 participants 5 messages Mar 7, 2019 – May 29, 2019

Subsystems (3)

v1 of 2 Superseded Latest is v2 →

lore
Share & tools
lore
#0 lore raw

PATCH 1/1 drm/msm/dsi: add protection against NULL dsi device

When panel probe happens after DSI probe, the DSI probe is deferred as per current design. In the probe defer path dsi device is destroyed. This NULL dsi device could be deferenced by the panel probe in the mipi_dsi_attach path.

Check for NULL dsi device before accessing it.

---
 drivers/gpu/drm/msm/dsi/dsi_manager.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/gpu/drm/msm/dsi/dsi_manager.c +1 -1
index 80aa634..cc2569d 100644
@@ -769,7 +769,7 @@ bool msm_dsi_manager_cmd_xfer_trigger(int id, u32 dma_base, u32 len)
 void msm_dsi_manager_attach_dsi_device(int id, u32 device_flags)
 {
 	struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id);
-	struct drm_device *dev = msm_dsi->dev;
+	struct drm_device *dev = msm_dsi ? msm_dsi->dev : NULL;
 	struct msm_drm_private *priv;
 	struct msm_kms *kms;
 	struct drm_encoder *encoder;
Signature · 7 lines
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project

_______________________________________________
dri-devel mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/dri-devel
reviewer
#1 lore raw
Quoted 6 lines · Abhinav Kumar

When panel probe happens after DSI probe, the DSI probe is deferred as per current design. In the probe defer path dsi device is destroyed. This NULL dsi device could be deferenced by the panel probe in the mipi_dsi_attach path.

Check for NULL dsi device before accessing it.

It would be really nice to sort all of this out in a manner that's not sprinkling NULL checks around the driver. I spent 5 minutes looking around and couldn't really make sense of how all of these pieces interact, but this seems like it might be an architectural problem (perhaps since dpu was using its own panel stuff instead of drm_panel?).

Anyways, it'd be nice to fix that.

In the meantime, could you please add a big comment like the !dev check in this function explaining how this situation can come to pass? That way the knowledge isn't lost and whoever comes along to clean up all of these probe checks will have some clue as to what's going on.

Sean

Quoted 25 lines
---
 drivers/gpu/drm/msm/dsi/dsi_manager.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/gpu/drm/msm/dsi/dsi_manager.c +1 -1
index 80aa634..cc2569d 100644
@@ -769,7 +769,7 @@ bool msm_dsi_manager_cmd_xfer_trigger(int id, u32 dma_base, u32 len)
 void msm_dsi_manager_attach_dsi_device(int id, u32 device_flags)
 {
 	struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id);
-	struct drm_device *dev = msm_dsi->dev;
+	struct drm_device *dev = msm_dsi ? msm_dsi->dev : NULL;
 	struct msm_drm_private *priv;
 	struct msm_kms *kms;
 	struct drm_encoder *encoder;
Signature · 2 lines
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project
Signature · 5 lines
Sean Paul, Software Engineer, Google / Chromium OS
_______________________________________________
dri-devel mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/dri-devel
#2 lore raw
Quoted 14 lines · Sean Paul
Quoted 6 lines · Abhinav Kumar

When panel probe happens after DSI probe, the DSI probe is deferred as per current design. In the probe defer path dsi device is destroyed. This NULL dsi device could be deferenced by the panel probe in the mipi_dsi_attach path.

Check for NULL dsi device before accessing it.

It would be really nice to sort all of this out in a manner that's not sprinkling NULL checks around the driver. I spent 5 minutes looking around and couldn't really make sense of how all of these pieces interact, but this seems like it might be an architectural problem (perhaps since dpu was using its own panel stuff instead of drm_panel?).

Quoted 8 lines

Anyways, it'd be nice to fix that.

In the meantime, could you please add a big comment like the !dev check in this function explaining how this situation can come to pass? That way the knowledge isn't lost and whoever comes along to clean up all of these probe checks will have some clue as to what's going on.

Sean

[Abhinav] Sure Sean, will add a detailed comment to explain the scenario

Quoted 19 lines
Quoted 19 lines
---
 drivers/gpu/drm/msm/dsi/dsi_manager.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/gpu/drm/msm/dsi/dsi_manager.c +0 -1
index 80aa634..cc2569d 100644
@@ -769,7 +769,7 @@ bool msm_dsi_manager_cmd_xfer_trigger(int id, u32 
 dma_base, u32 len)
 void msm_dsi_manager_attach_dsi_device(int id, u32 device_flags)
 {
 	struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id);
-	struct drm_device *dev = msm_dsi->dev;
Quoted 8 lines
Quoted 8 lines
drivers/gpu/drm/msm/dsi/dsi_manager.c +1 -0
+	struct drm_device *dev = msm_dsi ? msm_dsi->dev : NULL;
 	struct msm_drm_private *priv;
 	struct msm_kms *kms;

struct drm_encoder *encoder;
--
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum, a Linux Foundation Collaborative Project

_______________________________________________
dri-devel mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/dri-devel

#3 lore raw
Quoted 17 lines · Abhinav Kumar
Quoted 16 lines · Sean Paul
Quoted 6 lines · Abhinav Kumar

When panel probe happens after DSI probe, the DSI probe is deferred as per current design. In the probe defer path dsi device is destroyed. This NULL dsi device could be deferenced by the panel probe in the mipi_dsi_attach path.

Check for NULL dsi device before accessing it.

It would be really nice to sort all of this out in a manner that's not sprinkling NULL checks around the driver. I spent 5 minutes looking around and couldn't really make sense of how all of these pieces interact, but this seems like it might be an architectural problem (perhaps since dpu was using its own panel stuff instead of drm_panel?).

Anyways, it'd be nice to fix that.

Quoted 7 lines
Quoted 6 lines

In the meantime, could you please add a big comment like the !dev check in this function explaining how this situation can come to pass? That way the knowledge isn't lost and whoever comes along to clean up all of these probe checks will have some clue as to what's going on.

Sean

[Abhinav] Sure Sean, will add a detailed comment to explain the scenario

Abhinav, it looks like this may have dropped off your radar. Do you know when you'll come back to it?

Quoted 27 lines
Quoted 27 lines
Quoted 27 lines

---
 drivers/gpu/drm/msm/dsi/dsi_manager.c | 2 +-

 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/gpu/drm/msm/dsi/dsi_manager.c +1 -1
index 80aa634..cc2569d 100644
@@ -769,7 +769,7 @@ bool msm_dsi_manager_cmd_xfer_trigger(int id, u32 
 dma_base, u32 len)
  void msm_dsi_manager_attach_dsi_device(int id, u32 device_flags)
  {
      struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id);
-    struct drm_device *dev = msm_dsi->dev;
+    struct drm_device *dev = msm_dsi ? msm_dsi->dev : NULL;
      struct msm_drm_private *priv;
      struct msm_kms *kms;

     struct drm_encoder *encoder;

Signature · 2 lines
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project
Signature · 8 lines
Jeffrey Hugo
Qualcomm Datacenter Technologies as an affiliate of Qualcomm Technologies, Inc.
Qualcomm Technologies, Inc. is a member of the
Code Aurora Forum, a Linux Foundation Collaborative Project.
_______________________________________________
dri-devel mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/dri-devel
#4 lore raw
Quoted 23 lines · Jeffrey Hugo
Quoted 22 lines · Abhinav Kumar
Quoted 21 lines · Sean Paul
Quoted 6 lines · Abhinav Kumar

When panel probe happens after DSI probe, the DSI probe is deferred as per current design. In the probe defer path dsi device is destroyed. This NULL dsi device could be deferenced by the panel probe in the mipi_dsi_attach path.

Check for NULL dsi device before accessing it.

It would be really nice to sort all of this out in a manner that's not sprinkling NULL checks around the driver. I spent 5 minutes looking around and couldn't really make sense of how all of these pieces interact, but this seems like it might be an architectural problem (perhaps since dpu was using its own panel stuff instead of drm_panel?).

Anyways, it'd be nice to fix that.

In the meantime, could you please add a big comment like the !dev check in this function explaining how this situation can come to pass? That way the knowledge isn't lost and whoever comes along to clean up all of these probe checks will have some clue as to what's going on.

Quoted 5 lines
Quoted 2 lines
Quoted 1 line

Sean

[Abhinav] Sure Sean, will add a detailed comment to explain the scenario

Abhinav, it looks like this may have dropped off your radar. Do you know when you'll come back to it?

Hi Jeff, Yes i will upload a v2 with a detailed comment as sean requested within this week.

Quoted 20 lines
Quoted 20 lines
Quoted 20 lines
Quoted 20 lines

---
 drivers/gpu/drm/msm/dsi/dsi_manager.c | 2 +-

 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/gpu/drm/msm/dsi/dsi_manager.c +0 -1
index 80aa634..cc2569d 100644
@@ -769,7 +769,7 @@ bool msm_dsi_manager_cmd_xfer_trigger(int id, 
 u32 dma_base, u32 len)
  void msm_dsi_manager_attach_dsi_device(int id, u32 device_flags)
  {
      struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id);
-    struct drm_device *dev = msm_dsi->dev;
Quoted 8 lines
Quoted 8 lines
Quoted 8 lines
Quoted 8 lines
drivers/gpu/drm/msm/dsi/dsi_manager.c +1 -0
+    struct drm_device *dev = msm_dsi ? msm_dsi->dev : NULL;
      struct msm_drm_private *priv;
      struct msm_kms *kms;

     struct drm_encoder *encoder;
-- The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project

_______________________________________________
dri-devel mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/dri-devel