From: Oleksij Rempel <[email protected]>
Documentation/timers/timers-howto.txt recommends to use
usleep_range on delays > 10usec. According to my test results
with Neonode zForce touchscreen driver, usleep_range indeed
reduces CPU load.
Stats collected with "./perf record -a -g -F 1000 sleep 10"
i2c-imx with udelay(50):
34.19% 0.00% irq/220-Neonode [kernel.kallsyms] [k] irq_thread
---irq_thread
|--33.75%--irq_thread_fn
| |--19.27%--0x7f08a878
| | i2c_master_recv
| | i2c_transfer
| | __i2c_transfer
| | i2c_imx_xfer
| | |--11.71%--i2c_imx_trx_complete
| | |--5.70%--i2c_imx_start <<<<----------------
| | | |--5.38%--__timer_const_udelay
| | | | __timer_delay
| | | | --5.07%--read_current_timer
i2c-imx with usleep_range(50,100)
29.08% 0.00% irq/220-Neonode [kernel.kallsyms] [k] irq_thread
---irq_thread
|--28.89%--irq_thread_fn
| |--17.21%--0x7f08a878
| | i2c_master_recv
| | |--17.14%--i2c_transfer
| | | __i2c_transfer
| | | i2c_imx_xfer
| | | |--14.29%--i2c_imx_trx_complete
| | | |--1.42%--i2c_imx_start <<<<----------
| | | | |--0.71%--usleep_range
| | | | |--0.53%--i2c_imx_bus_busy
Signed-off-by: Oleksij Rempel <[email protected]>
---
drivers/i2c/busses/i2c-imx.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c
index 1ca7ef2..1844bc9 100644
--- a/drivers/i2c/busses/i2c-imx.c
+++ b/drivers/i2c/busses/i2c-imx.c
@@ -525,7 +525,7 @@ static int i2c_imx_start(struct imx_i2c_struct *i2c_imx)
imx_i2c_write_reg(i2c_imx->hwdata->i2cr_ien_opcode, i2c_imx, IMX_I2C_I2CR);
/* Wait controller to be stable */
- udelay(50);
+ usleep_range(50, 150);
/* Start I2C transaction */
temp = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2CR);
--
2.8.0
Hi Dirk,
On 26.04.2016 09:27, Dirk Behme wrote:
> From: Oleksij Rempel <[email protected]>
>
> Documentation/timers/timers-howto.txt recommends to use
> usleep_range on delays > 10usec. According to my test results
> with Neonode zForce touchscreen driver, usleep_range indeed
> reduces CPU load.
>
> Stats collected with "./perf record -a -g -F 1000 sleep 10"
>
> i2c-imx with udelay(50):
> 34.19% 0.00% irq/220-Neonode [kernel.kallsyms] [k] irq_thread
> ---irq_thread
> |--33.75%--irq_thread_fn
> | |--19.27%--0x7f08a878
> | | i2c_master_recv
> | | i2c_transfer
> | | __i2c_transfer
> | | i2c_imx_xfer
> | | |--11.71%--i2c_imx_trx_complete
> | | |--5.70%--i2c_imx_start <<<<----------------
> | | | |--5.38%--__timer_const_udelay
> | | | | __timer_delay
> | | | | --5.07%--read_current_timer
>
> i2c-imx with usleep_range(50,100)
> 29.08% 0.00% irq/220-Neonode [kernel.kallsyms] [k] irq_thread
> ---irq_thread
> |--28.89%--irq_thread_fn
> | |--17.21%--0x7f08a878
> | | i2c_master_recv
> | | |--17.14%--i2c_transfer
> | | | __i2c_transfer
> | | | i2c_imx_xfer
> | | | |--14.29%--i2c_imx_trx_complete
> | | | |--1.42%--i2c_imx_start <<<<----------
> | | | | |--0.71%--usleep_range
> | | | | |--0.53%--i2c_imx_bus_busy
>
> Signed-off-by: Oleksij Rempel <[email protected]>
missing your Signed-off-by.
Reviewed-by: Vladimir Zapolskiy <[email protected]>
> ---
> drivers/i2c/busses/i2c-imx.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c
> index 1ca7ef2..1844bc9 100644
> --- a/drivers/i2c/busses/i2c-imx.c
> +++ b/drivers/i2c/busses/i2c-imx.c
> @@ -525,7 +525,7 @@ static int i2c_imx_start(struct imx_i2c_struct *i2c_imx)
> imx_i2c_write_reg(i2c_imx->hwdata->i2cr_ien_opcode, i2c_imx, IMX_I2C_I2CR);
>
> /* Wait controller to be stable */
> - udelay(50);
> + usleep_range(50, 150);
>
> /* Start I2C transaction */
> temp = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2CR);
>
--
With best wishes,
Vladimir
On 26.04.2016 13:02, Vladimir Zapolskiy wrote:
> Hi Dirk,
>
> On 26.04.2016 09:27, Dirk Behme wrote:
>> From: Oleksij Rempel <[email protected]>
>>
>> Documentation/timers/timers-howto.txt recommends to use
>> usleep_range on delays > 10usec. According to my test results
>> with Neonode zForce touchscreen driver, usleep_range indeed
>> reduces CPU load.
>>
>> Stats collected with "./perf record -a -g -F 1000 sleep 10"
>>
>> i2c-imx with udelay(50):
>> 34.19% 0.00% irq/220-Neonode [kernel.kallsyms] [k] irq_thread
>> ---irq_thread
>> |--33.75%--irq_thread_fn
>> | |--19.27%--0x7f08a878
>> | | i2c_master_recv
>> | | i2c_transfer
>> | | __i2c_transfer
>> | | i2c_imx_xfer
>> | | |--11.71%--i2c_imx_trx_complete
>> | | |--5.70%--i2c_imx_start <<<<----------------
>> | | | |--5.38%--__timer_const_udelay
>> | | | | __timer_delay
>> | | | | --5.07%--read_current_timer
>>
>> i2c-imx with usleep_range(50,100)
>> 29.08% 0.00% irq/220-Neonode [kernel.kallsyms] [k] irq_thread
>> ---irq_thread
>> |--28.89%--irq_thread_fn
>> | |--17.21%--0x7f08a878
>> | | i2c_master_recv
>> | | |--17.14%--i2c_transfer
>> | | | __i2c_transfer
>> | | | i2c_imx_xfer
>> | | | |--14.29%--i2c_imx_trx_complete
>> | | | |--1.42%--i2c_imx_start <<<<----------
>> | | | | |--0.71%--usleep_range
>> | | | | |--0.53%--i2c_imx_bus_busy
>>
>> Signed-off-by: Oleksij Rempel <[email protected]>
Signed-off-by: Dirk Behme <[email protected]>
> missing your Signed-off-by.
>
> Reviewed-by: Vladimir Zapolskiy <[email protected]>
>
>> ---
>> drivers/i2c/busses/i2c-imx.c | 2 +-
>> 1 file changed, 1 insertion(+), 1 deletion(-)
>>
>> diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c
>> index 1ca7ef2..1844bc9 100644
>> --- a/drivers/i2c/busses/i2c-imx.c
>> +++ b/drivers/i2c/busses/i2c-imx.c
>> @@ -525,7 +525,7 @@ static int i2c_imx_start(struct imx_i2c_struct *i2c_imx)
>> imx_i2c_write_reg(i2c_imx->hwdata->i2cr_ien_opcode, i2c_imx, IMX_I2C_I2CR);
>>
>> /* Wait controller to be stable */
>> - udelay(50);
>> + usleep_range(50, 150);
>>
>> /* Start I2C transaction */
>> temp = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2CR);
>>
On Tue, Apr 26, 2016 at 08:27:46AM +0200, Dirk Behme wrote:
> From: Oleksij Rempel <[email protected]>
>
> Documentation/timers/timers-howto.txt recommends to use
> usleep_range on delays > 10usec. According to my test results
> with Neonode zForce touchscreen driver, usleep_range indeed
> reduces CPU load.
>
> Stats collected with "./perf record -a -g -F 1000 sleep 10"
>
> i2c-imx with udelay(50):
> 34.19% 0.00% irq/220-Neonode [kernel.kallsyms] [k] irq_thread
> ---irq_thread
> |--33.75%--irq_thread_fn
> | |--19.27%--0x7f08a878
> | | i2c_master_recv
> | | i2c_transfer
> | | __i2c_transfer
> | | i2c_imx_xfer
> | | |--11.71%--i2c_imx_trx_complete
Reworded $subject to match code and applied to for-next, thanks!