Re: [PATCH] serial: omap: Fix device tree based PM runtime

2013-06-10 Thread Tony Lindgren 
In the runtime_suspend function pdata is not being used, and
also blocks the function in device tree based booting. Fix it
by removing the unused pdata from the runtime_suspend function.

Further, context loss count is not being passed in pdata, so
let's just reinitialize the port every time for those case.
This can be further optimized later on for the device tree
case by adding detection for the hardware state and possibly
by adding a driver specific autosuspend timeout.

And doing this, we can then make the related dev_err into a
dev_dbg message instead of an error.

In order for the wake-up events to work, we also need to set
autosuspend_timeout to -1 if 0, and also device_init_wakeup()
as that's not being done by the platform init code for the
device tree case.

Note that this does not affect legacy booting, and in fact
might make it work for the cases where the context loss info
is not being passed in pdata.

Thanks to Kevin Hilman khil...@linaro.org for debugging
and suggesting fixes for the autosuspend_timeout and
device_init_wakeup() related initializiation.

Reviewed-by: Kevin Hilman khil...@linaro.org
Tested-by: Kevin Hilman khil...@linaro.org
Signed-off-by: Tony Lindgren t...@atomide.com

---

Here's this one updated against Linux next.

--- a/drivers/tty/serial/omap-serial.c
+++ b/drivers/tty/serial/omap-serial.c
@@ -198,7 +198,7 @@ static int serial_omap_get_context_loss_count(struct 
uart_omap_port *up)
struct omap_uart_port_info *pdata = up-dev-platform_data;
 
if (!pdata || !pdata-get_context_loss_count)
-   return 0;
+   return -EINVAL;
 
return pdata-get_context_loss_count(up-dev);
 }
@@ -1502,6 +1502,9 @@ static int serial_omap_probe(struct platform_device *pdev)
 
platform_set_drvdata(pdev, up);
pm_runtime_enable(pdev-dev);
+   if (omap_up_info-autosuspend_timeout == 0)
+   omap_up_info-autosuspend_timeout = -1;
+   device_init_wakeup(up-dev, true);
pm_runtime_use_autosuspend(pdev-dev);
pm_runtime_set_autosuspend_delay(pdev-dev,
omap_up_info-autosuspend_timeout);
@@ -1611,7 +1614,6 @@ static void serial_omap_restore_context(struct 
uart_omap_port *up)
 static int serial_omap_runtime_suspend(struct device *dev)
 {
struct uart_omap_port *up = dev_get_drvdata(dev);
-   struct omap_uart_port_info *pdata = dev-platform_data;
 
if (!up)
return -EINVAL;
@@ -1626,9 +1628,6 @@ static int serial_omap_runtime_suspend(struct device *dev)
uart_console(up-port))
return -EBUSY;
 
-   if (!pdata)
-   return 0;
-
up-context_loss_cnt = serial_omap_get_context_loss_count(up);
 
if (device_may_wakeup(dev)) {
@@ -1656,7 +1655,7 @@ static int serial_omap_runtime_resume(struct device *dev)
int loss_cnt = serial_omap_get_context_loss_count(up);
 
if (loss_cnt  0) {
-   dev_err(dev, serial_omap_get_context_loss_count failed : %d\n,
+   dev_dbg(dev, serial_omap_get_context_loss_count failed : %d\n,
loss_cnt);
serial_omap_restore_context(up);
} else if (up-context_loss_cnt != loss_cnt) {
--
To unsubscribe from this list: send the line unsubscribe linux-omap in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH] serial: omap: Fix device tree based PM runtime

2013-06-08 Thread Greg Kroah-Hartman 
On Fri, Jun 07, 2013 at 04:00:22PM -0700, Tony Lindgren wrote:
 In the runtime_suspend function pdata is not being used, and
 also blocks the function in device tree based booting. Fix it
 by removing the unused pdata from the runtime_suspend function.
 
 Further, context loss count is not being passed in pdata, so
 let's just reinitialize the port every time for those case.
 This can be further optimized later on for the device tree
 case by adding detection for the hardware state and possibly
 by adding a driver specific autosuspend timeout.
 
 And doing this, we can then make the related dev_err into a
 dev_dbg message instead of an error.
 
 In order for the wake-up events to work, we also need to set
 autosuspend_timeout to -1 if 0, and also device_init_wakeup()
 as that's not being done by the platform init code for the
 device tree case.
 
 Note that this does not affect legacy booting, and in fact
 might make it work for the cases where the context loss info
 is not being passed in pdata.
 
 Thanks to Kevin Hilman khil...@linaro.org for debugging
 and suggesting fixes for the autosuspend_timeout and
 device_init_wakeup() related initializiation.
 
 Reviewed-by: Kevin Hilman khil...@linaro.org
 Tested-by: Kevin Hilman khil...@linaro.org
 Signed-off-by: Tony Lindgren t...@atomide.com
 
 ---
 
 Here's an updated version with the white space fixed. Since
 you already acked it, I won't waste the opportunity to keep it
 in a single patch :)

It doesn't apply to my tree, so you'll have to refresh it against my
tty-next tree and resend it.

thanks,

greg k-h
--
To unsubscribe from this list: send the line unsubscribe linux-omap in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH] serial: omap: Fix device tree based PM runtime

2013-06-07 Thread Kevin Hilman 
Tony Lindgren t...@atomide.com writes:

 In the runtime_suspend function pdata is not being used, and
 also blocks the function in device tree based booting. Fix it
 by removing the unused pdata from the runtime_suspend function.

 Further, context loss count is not being passed in pdata, so
 let's just reinitialize the port every time for those case.
 This can be further optimized later on for the device tree
 case by adding detection for the hardware state and possibly
 by adding a driver specific autosuspend timeout.

 And doing this, we can then make the related dev_err into a
 dev_dbg message instead of an error.

 In order for the wake-up events to work, we also need to set
 autosuspend_timeout to -1 if 0, and also device_init_wakeup()
 as that's not being done by the platform init code for the
 device tree case.

 Note that this does not affect legacy booting, and in fact
 might make it work for the cases where the context loss info
 is not being passed in pdata.

 Thanks to Kevin Hilman khil...@linaro.org for debugging
 and suggesting fixes for the autosuspend_timeout and
 device_init_wakeup() related initializiation.

 Cc: Kevin Hilman khil...@linaro.org
 Signed-off-by: Tony Lindgren t...@atomide.com

There's a stray whitespace change in the patch, and also, maybe it
should be broken up into a few different patches:

1) stray pdata
2) context_loss: -EINVAL + dev_dbg change
3) device_init_wakeup
4) autosuspend timeout defaults

but otherwise the content is right.

Reviewed-by: Kevin Hilman khil...@linaro.org

Also, tested on OMAP3/4

Tested-by: Kevin Hilman khil...@linaro.org

Kevin

 ---

 This can wait for v3.11 merge window as the related PM patches
 have not yet been merged.

 --- a/drivers/tty/serial/omap-serial.c
 +++ b/drivers/tty/serial/omap-serial.c
 @@ -197,7 +197,7 @@ static int serial_omap_get_context_loss_count(struct 
 uart_omap_port *up)
   struct omap_uart_port_info *pdata = up-dev-platform_data;
  
   if (!pdata || !pdata-get_context_loss_count)
 - return 0;
 + return -EINVAL;
  
   return pdata-get_context_loss_count(up-dev);
  }
 @@ -1482,6 +1482,9 @@ static int serial_omap_probe(struct platform_device 
 *pdev)
  
   platform_set_drvdata(pdev, up);
   pm_runtime_enable(pdev-dev);
 + if (omap_up_info-autosuspend_timeout == 0)
 + omap_up_info-autosuspend_timeout = -1;
 + device_init_wakeup(up-dev, true);
   pm_runtime_use_autosuspend(pdev-dev);
   pm_runtime_set_autosuspend_delay(pdev-dev,
   omap_up_info-autosuspend_timeout);
 @@ -1500,6 +1503,7 @@ static int serial_omap_probe(struct platform_device 
 *pdev)
  
   pm_runtime_mark_last_busy(up-dev);
   pm_runtime_put_autosuspend(up-dev);
 +
   return 0;
  
  err_add_port:
 @@ -1591,14 +1595,10 @@ static void serial_omap_restore_context(struct 
 uart_omap_port *up)
  static int serial_omap_runtime_suspend(struct device *dev)
  {
   struct uart_omap_port *up = dev_get_drvdata(dev);
 - struct omap_uart_port_info *pdata = dev-platform_data;
  
   if (!up)
   return -EINVAL;
  
 - if (!pdata)
 - return 0;
 -
   up-context_loss_cnt = serial_omap_get_context_loss_count(up);
  
   if (device_may_wakeup(dev)) {
 @@ -1626,7 +1626,7 @@ static int serial_omap_runtime_resume(struct device 
 *dev)
   int loss_cnt = serial_omap_get_context_loss_count(up);
  
   if (loss_cnt  0) {
 - dev_err(dev, serial_omap_get_context_loss_count failed : %d\n,
 + dev_dbg(dev, serial_omap_get_context_loss_count failed : %d\n,
   loss_cnt);
   serial_omap_restore_context(up);
   } else if (up-context_loss_cnt != loss_cnt) {
 --
 To unsubscribe from this list: send the line unsubscribe linux-omap in
 the body of a message to majord...@vger.kernel.org
 More majordomo info at  http://vger.kernel.org/majordomo-info.html
--
To unsubscribe from this list: send the line unsubscribe linux-omap in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH] serial: omap: Fix device tree based PM runtime

2013-06-07 Thread Tony Lindgren 
In the runtime_suspend function pdata is not being used, and
also blocks the function in device tree based booting. Fix it
by removing the unused pdata from the runtime_suspend function.

Further, context loss count is not being passed in pdata, so
let's just reinitialize the port every time for those case.
This can be further optimized later on for the device tree
case by adding detection for the hardware state and possibly
by adding a driver specific autosuspend timeout.

And doing this, we can then make the related dev_err into a
dev_dbg message instead of an error.

In order for the wake-up events to work, we also need to set
autosuspend_timeout to -1 if 0, and also device_init_wakeup()
as that's not being done by the platform init code for the
device tree case.

Note that this does not affect legacy booting, and in fact
might make it work for the cases where the context loss info
is not being passed in pdata.

Thanks to Kevin Hilman khil...@linaro.org for debugging
and suggesting fixes for the autosuspend_timeout and
device_init_wakeup() related initializiation.

Reviewed-by: Kevin Hilman khil...@linaro.org
Tested-by: Kevin Hilman khil...@linaro.org
Signed-off-by: Tony Lindgren t...@atomide.com

---

Here's an updated version with the white space fixed. Since
you already acked it, I won't waste the opportunity to keep it
in a single patch :)

--- a/drivers/tty/serial/omap-serial.c
+++ b/drivers/tty/serial/omap-serial.c
@@ -197,7 +197,7 @@ static int serial_omap_get_context_loss_count(struct 
uart_omap_port *up)
struct omap_uart_port_info *pdata = up-dev-platform_data;
 
if (!pdata || !pdata-get_context_loss_count)
-   return 0;
+   return -EINVAL;
 
return pdata-get_context_loss_count(up-dev);
 }
@@ -1482,6 +1482,9 @@ static int serial_omap_probe(struct platform_device *pdev)
 
platform_set_drvdata(pdev, up);
pm_runtime_enable(pdev-dev);
+   if (omap_up_info-autosuspend_timeout == 0)
+   omap_up_info-autosuspend_timeout = -1;
+   device_init_wakeup(up-dev, true);
pm_runtime_use_autosuspend(pdev-dev);
pm_runtime_set_autosuspend_delay(pdev-dev,
omap_up_info-autosuspend_timeout);
@@ -1591,14 +1594,10 @@ static void serial_omap_restore_context(struct 
uart_omap_port *up)
 static int serial_omap_runtime_suspend(struct device *dev)
 {
struct uart_omap_port *up = dev_get_drvdata(dev);
-   struct omap_uart_port_info *pdata = dev-platform_data;
 
if (!up)
return -EINVAL;
 
-   if (!pdata)
-   return 0;
-
up-context_loss_cnt = serial_omap_get_context_loss_count(up);
 
if (device_may_wakeup(dev)) {
@@ -1626,7 +1625,7 @@ static int serial_omap_runtime_resume(struct device *dev)
int loss_cnt = serial_omap_get_context_loss_count(up);
 
if (loss_cnt  0) {
-   dev_err(dev, serial_omap_get_context_loss_count failed : %d\n,
+   dev_dbg(dev, serial_omap_get_context_loss_count failed : %d\n,
loss_cnt);
serial_omap_restore_context(up);
} else if (up-context_loss_cnt != loss_cnt) {
--
To unsubscribe from this list: send the line unsubscribe linux-omap in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html