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