[PATCH 0/3] slimbus: fixes for 5.10

[PATCH 0/3] slimbus: fixes for 5.10

[Srinivas Kandagatla]

Hi Greg, 

Here are few fixes found recently while testing Qualcomm SSR (SubSystem Restart)
feature on SDM845 SoC. Mostly the fixes are around when device absense is reported.

If its not too late, can you take them for 5.10.

Many thanks,
Srini


Srinivas Kandagatla (3):
  slimbus: core: check get_addr before removing laddr ida
  slimbus: core: do not enter to clock pause mode in core
  slimbus: qcom-ngd-ctrl: disable ngd in qmi server down callback

 drivers/slimbus/core.c          | 6 ++----
 drivers/slimbus/qcom-ngd-ctrl.c | 4 ++++
 2 files changed, 6 insertions(+), 4 deletions(-)

-- 
2.21.0

[PATCH 1/3] slimbus: core: check get_addr before removing laddr ida

[Srinivas Kandagatla]

logical address can be either assigned by the SLIMBus controller or the core.
Core uses IDA in cases where get_addr callback is not provided by the
controller.
Core already has this check while allocating IDR, however during absence
reporting this is not checked. This patch fixes this issue.

Fixes: 46a2bb5a7f7ea("slimbus: core: Add slim controllers support")
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
---
 drivers/slimbus/core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/slimbus/core.c b/drivers/slimbus/core.c
index ae1e248a8fb8..58b63ae0e75a 100644
--- a/drivers/slimbus/core.c
+++ b/drivers/slimbus/core.c
@@ -326,8 +326,8 @@ void slim_report_absent(struct slim_device *sbdev)
 	mutex_lock(&ctrl->lock);
 	sbdev->is_laddr_valid = false;
 	mutex_unlock(&ctrl->lock);
-
-	ida_simple_remove(&ctrl->laddr_ida, sbdev->laddr);
+	if (!ctrl->get_laddr)
+		ida_simple_remove(&ctrl->laddr_ida, sbdev->laddr);
 	slim_device_update_status(sbdev, SLIM_DEVICE_STATUS_DOWN);
 }
 EXPORT_SYMBOL_GPL(slim_report_absent);
-- 
2.21.0

[PATCH 2/3] slimbus: core: do not enter to clock pause mode in core

[Srinivas Kandagatla]

Let the controller logic decide when to enter into clock pause mode!
Entering in to pause mode during unregistration does not really make
sense as the controller is totally going down at that point in time.

Fixes: 4b14e62ad3c9e ("slimbus: Add support for 'clock-pause' feature")
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
---
 drivers/slimbus/core.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/slimbus/core.c b/drivers/slimbus/core.c
index 58b63ae0e75a..1d2bc181da05 100644
--- a/drivers/slimbus/core.c
+++ b/drivers/slimbus/core.c
@@ -301,8 +301,6 @@ int slim_unregister_controller(struct slim_controller *ctrl)
 {
 	/* Remove all clients */
 	device_for_each_child(ctrl->dev, NULL, slim_ctrl_remove_device);
-	/* Enter Clock Pause */
-	slim_ctrl_clk_pause(ctrl, false, 0);
 	ida_simple_remove(&ctrl_ida, ctrl->id);
 
 	return 0;
-- 
2.21.0

[PATCH 3/3] slimbus: qcom-ngd-ctrl: disable ngd in qmi server down callback

[Srinivas Kandagatla]

In QMI new server notification we enable the NGD however during
delete server notification we do not disable the NGD.

This can lead to multiple instances of NGD being enabled, so make
sure that we disable NGD in delete server callback to fix this issue!

Fixes: 917809e2280b ("slimbus: ngd: Add qcom SLIMBus NGD driver")
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
---
 drivers/slimbus/qcom-ngd-ctrl.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/slimbus/qcom-ngd-ctrl.c b/drivers/slimbus/qcom-ngd-ctrl.c
index 743ee7b4e63f..218aefc3531c 100644
--- a/drivers/slimbus/qcom-ngd-ctrl.c
+++ b/drivers/slimbus/qcom-ngd-ctrl.c
@@ -1277,9 +1277,13 @@ static void qcom_slim_ngd_qmi_del_server(struct qmi_handle *hdl,
 {
 	struct qcom_slim_ngd_qmi *qmi =
 		container_of(hdl, struct qcom_slim_ngd_qmi, svc_event_hdl);
+	struct qcom_slim_ngd_ctrl *ctrl =
+		container_of(qmi, struct qcom_slim_ngd_ctrl, qmi);
 
 	qmi->svc_info.sq_node = 0;
 	qmi->svc_info.sq_port = 0;
+
+	qcom_slim_ngd_enable(ctrl, false);
 }
 
 static struct qmi_ops qcom_slim_ngd_qmi_svc_event_ops = {
-- 
2.21.0

Re: [PATCH 1/3] slimbus: core: check get_addr before removing laddr ida

[Greg KH]

On Fri, Sep 25, 2020 at 10:55:18AM +0100, Srinivas Kandagatla wrote:
> logical address can be either assigned by the SLIMBus controller or the core.
> Core uses IDA in cases where get_addr callback is not provided by the
> controller.
> Core already has this check while allocating IDR, however during absence
> reporting this is not checked. This patch fixes this issue.
> 
> Fixes: 46a2bb5a7f7ea("slimbus: core: Add slim controllers support")

Nit, you need a ' ' before the '(' character...

Also, you don't need all of those characters, you have 1 more than
necessary :)

I'll go fix it up.

greg k-h

Re: [PATCH 1/3] slimbus: core: check get_addr before removing laddr ida

[Srinivas Kandagatla]

On 25/09/2020 13:41, Greg KH wrote:
> On Fri, Sep 25, 2020 at 10:55:18AM +0100, Srinivas Kandagatla wrote:
>> logical address can be either assigned by the SLIMBus controller or the core.
>> Core uses IDA in cases where get_addr callback is not provided by the
>> controller.
>> Core already has this check while allocating IDR, however during absence
>> reporting this is not checked. This patch fixes this issue.
>>
>> Fixes: 46a2bb5a7f7ea("slimbus: core: Add slim controllers support")
> 
> Nit, you need a ' ' before the '(' character...
> 
Not sure how I missed that :-)

> Also, you don't need all of those characters, you have 1 more than
> necessary :)
> 
> I'll go fix it up.
Thankyou very much for fixing this up!

--srini
> 
> greg k-h
>