[PATCH] i2c: k1: check for transfer error

[PATCH] i2c: k1: check for transfer error

[Alex Elder]

If spacemit_i2c_xfer_msg() times out waiting for a message transfer to
complete, or if the hardware reports an error, it returns a negative
error code (-ETIMEDOUT, -EAGAIN, -ENXIO. or -EIO).

The sole caller of spacemit_i2c_xfer_msg() is spacemit_i2c_xfer(),
which is the i2c_algorithm->xfer callback function.  It currently
does not save the value returned by spacemit_i2c_xfer_msg().

The result is that transfer errors go unreported, and a caller
has no indication anything is wrong.

When this code was out for review, the return value *was* checked
in early versions.  But for some reason, that assignment got dropped
between versions 5 and 6 of the series, perhaps related to reworking
the code to merge spacemit_i2c_xfer_core() into spacemit_i2c_xfer().

Simply assigning the value returned to "ret" fixes the problem.

Fixes: 5ea558473fa31 ("i2c: spacemit: add support for SpacemiT K1 SoC")
Signed-off-by: Alex Elder <elder@riscstar.com>
Reviewed-by: Troy Mitchell <troymitchell988@gmail.com>
---
v2: Added Troy's Reviewed-by

 drivers/i2c/busses/i2c-k1.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/i2c-k1.c b/drivers/i2c/busses/i2c-k1.c
index 5965b4cf6220e..b68a21fff0b56 100644
--- a/drivers/i2c/busses/i2c-k1.c
+++ b/drivers/i2c/busses/i2c-k1.c
@@ -477,7 +477,7 @@ static int spacemit_i2c_xfer(struct i2c_adapter *adapt, struct i2c_msg *msgs, in
 
 	ret = spacemit_i2c_wait_bus_idle(i2c);
 	if (!ret)
-		spacemit_i2c_xfer_msg(i2c);
+		ret = spacemit_i2c_xfer_msg(i2c);
 	else if (ret < 0)
 		dev_dbg(i2c->dev, "i2c transfer error: %d\n", ret);
 	else

base-commit: 19272b37aa4f83ca52bdf9c16d5d81bdd1354494
-- 
2.45.2

Re: [PATCH] i2c: k1: check for transfer error

[Troy Mitchell]

On Thu, Jun 12, 2025 at 05:56:25PM -0500, Alex Elder wrote:
> If spacemit_i2c_xfer_msg() times out waiting for a message transfer to
> complete, or if the hardware reports an error, it returns a negative
> error code (-ETIMEDOUT, -EAGAIN, -ENXIO. or -EIO).
> 
> The sole caller of spacemit_i2c_xfer_msg() is spacemit_i2c_xfer(),
> which is the i2c_algorithm->xfer callback function.  It currently
> does not save the value returned by spacemit_i2c_xfer_msg().
> 
> The result is that transfer errors go unreported, and a caller
> has no indication anything is wrong.
> 
> When this code was out for review, the return value *was* checked
> in early versions.  But for some reason, that assignment got dropped
> between versions 5 and 6 of the series, perhaps related to reworking
> the code to merge spacemit_i2c_xfer_core() into spacemit_i2c_xfer().
> 
> Simply assigning the value returned to "ret" fixes the problem.
> 
> Fixes: 5ea558473fa31 ("i2c: spacemit: add support for SpacemiT K1 SoC")
> Signed-off-by: Alex Elder <elder@riscstar.com>
> Reviewed-by: Troy Mitchell <troymitchell988@gmail.com>
> ---
> v2: Added Troy's Reviewed-by
Hi Alex, you added the changelog, but the subject line 
doesn't have the "V2" suffix. Is this a mistake?

            - Troy

> 
>  drivers/i2c/busses/i2c-k1.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/drivers/i2c/busses/i2c-k1.c b/drivers/i2c/busses/i2c-k1.c
> index 5965b4cf6220e..b68a21fff0b56 100644
> --- a/drivers/i2c/busses/i2c-k1.c
> +++ b/drivers/i2c/busses/i2c-k1.c
> @@ -477,7 +477,7 @@ static int spacemit_i2c_xfer(struct i2c_adapter *adapt, struct i2c_msg *msgs, in
>  
>  	ret = spacemit_i2c_wait_bus_idle(i2c);
>  	if (!ret)
> -		spacemit_i2c_xfer_msg(i2c);
> +		ret = spacemit_i2c_xfer_msg(i2c);
>  	else if (ret < 0)
>  		dev_dbg(i2c->dev, "i2c transfer error: %d\n", ret);
>  	else
> 
> base-commit: 19272b37aa4f83ca52bdf9c16d5d81bdd1354494
> -- 
> 2.45.2
> 

Re: [PATCH] i2c: k1: check for transfer error

[Alex Elder]

On 6/12/25 9:12 PM, Troy Mitchell wrote:
> On Thu, Jun 12, 2025 at 05:56:25PM -0500, Alex Elder wrote:
>> If spacemit_i2c_xfer_msg() times out waiting for a message transfer to
>> complete, or if the hardware reports an error, it returns a negative
>> error code (-ETIMEDOUT, -EAGAIN, -ENXIO. or -EIO).
>>
>> The sole caller of spacemit_i2c_xfer_msg() is spacemit_i2c_xfer(),
>> which is the i2c_algorithm->xfer callback function.  It currently
>> does not save the value returned by spacemit_i2c_xfer_msg().
>>
>> The result is that transfer errors go unreported, and a caller
>> has no indication anything is wrong.
>>
>> When this code was out for review, the return value *was* checked
>> in early versions.  But for some reason, that assignment got dropped
>> between versions 5 and 6 of the series, perhaps related to reworking
>> the code to merge spacemit_i2c_xfer_core() into spacemit_i2c_xfer().
>>
>> Simply assigning the value returned to "ret" fixes the problem.
>>
>> Fixes: 5ea558473fa31 ("i2c: spacemit: add support for SpacemiT K1 SoC")
>> Signed-off-by: Alex Elder <elder@riscstar.com>
>> Reviewed-by: Troy Mitchell <troymitchell988@gmail.com>
>> ---
>> v2: Added Troy's Reviewed-by
> Hi Alex, you added the changelog, but the subject line
> doesn't have the "V2" suffix. Is this a mistake?

Yes it's a mistake.  I contemplated sending an immediate
"oops, this was v2!!!" but opted to wait until someone
like you asked about it.

This *is* version 2, and I made the updates I describe.

					-Alex
> 
>              - Troy
> 
>>
>>   drivers/i2c/busses/i2c-k1.c | 2 +-
>>   1 file changed, 1 insertion(+), 1 deletion(-)
>>
>> diff --git a/drivers/i2c/busses/i2c-k1.c b/drivers/i2c/busses/i2c-k1.c
>> index 5965b4cf6220e..b68a21fff0b56 100644
>> --- a/drivers/i2c/busses/i2c-k1.c
>> +++ b/drivers/i2c/busses/i2c-k1.c
>> @@ -477,7 +477,7 @@ static int spacemit_i2c_xfer(struct i2c_adapter *adapt, struct i2c_msg *msgs, in
>>   
>>   	ret = spacemit_i2c_wait_bus_idle(i2c);
>>   	if (!ret)
>> -		spacemit_i2c_xfer_msg(i2c);
>> +		ret = spacemit_i2c_xfer_msg(i2c);
>>   	else if (ret < 0)
>>   		dev_dbg(i2c->dev, "i2c transfer error: %d\n", ret);
>>   	else
>>
>> base-commit: 19272b37aa4f83ca52bdf9c16d5d81bdd1354494
>> -- 
>> 2.45.2
>>

[PATCH] i2c: k1: check for transfer error

[Alex Elder]

If spacemit_i2c_xfer_msg() times out waiting for a message transfer to
complete, or if the hardware reports an error, it returns a negative
error code (-ETIMEDOUT, -EAGAIN, -ENXIO. or -EIO).

The sole caller of spacemit_i2c_xfer_msg() is spacemit_i2c_xfer(),
which is the i2c_algorithm->xfer callback function.  It currently
does not save the value returned by spacemit_i2c_xfer_msg().

The result is that transfer errors go unreported, and a caller
has no indication anything is wrong.

When this code was out for review, the return value *was* checked
in early versions.  But for some reason, that assignment got dropped
between versions 5 and 6 of the series, perhaps related to reworking
the code to merge spacemit_i2c_xfer_core() into spacemit_i2c_xfer().

Simply assigning the value returned to "ret" fixes the problem.

Fixes: 5ea558473fa31 ("i2c: spacemit: add support for SpacemiT K1 SoC")
Signed-off-by: Alex Elder <elder@riscstar.com>
---
 drivers/i2c/busses/i2c-k1.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/i2c-k1.c b/drivers/i2c/busses/i2c-k1.c
index 5965b4cf6220e..b68a21fff0b56 100644
--- a/drivers/i2c/busses/i2c-k1.c
+++ b/drivers/i2c/busses/i2c-k1.c
@@ -477,7 +477,7 @@ static int spacemit_i2c_xfer(struct i2c_adapter *adapt, struct i2c_msg *msgs, in
 
 	ret = spacemit_i2c_wait_bus_idle(i2c);
 	if (!ret)
-		spacemit_i2c_xfer_msg(i2c);
+		ret = spacemit_i2c_xfer_msg(i2c);
 	else if (ret < 0)
 		dev_dbg(i2c->dev, "i2c transfer error: %d\n", ret);
 	else

base-commit: a5806cd506af5a7c19bcd596e4708b5c464bfd21
-- 
2.45.2

Re: [PATCH] i2c: k1: check for transfer error

[Troy Mitchell]

On Thu, May 29, 2025 at 07:22:26AM -0500, Alex Elder wrote:
> If spacemit_i2c_xfer_msg() times out waiting for a message transfer to
> complete, or if the hardware reports an error, it returns a negative
> error code (-ETIMEDOUT, -EAGAIN, -ENXIO. or -EIO).
> 
> The sole caller of spacemit_i2c_xfer_msg() is spacemit_i2c_xfer(),
> which is the i2c_algorithm->xfer callback function.  It currently
> does not save the value returned by spacemit_i2c_xfer_msg().
> 
> The result is that transfer errors go unreported, and a caller
> has no indication anything is wrong.
> 
> When this code was out for review, the return value *was* checked
> in early versions.  But for some reason, that assignment got dropped
> between versions 5 and 6 of the series, perhaps related to reworking
> the code to merge spacemit_i2c_xfer_core() into spacemit_i2c_xfer().
> 
> Simply assigning the value returned to "ret" fixes the problem.
> 
> Fixes: 5ea558473fa31 ("i2c: spacemit: add support for SpacemiT K1 SoC")
> Signed-off-by: Alex Elder <elder@riscstar.com>
> ---
>  drivers/i2c/busses/i2c-k1.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/drivers/i2c/busses/i2c-k1.c b/drivers/i2c/busses/i2c-k1.c
> index 5965b4cf6220e..b68a21fff0b56 100644
> --- a/drivers/i2c/busses/i2c-k1.c
> +++ b/drivers/i2c/busses/i2c-k1.c
> @@ -477,7 +477,7 @@ static int spacemit_i2c_xfer(struct i2c_adapter *adapt, struct i2c_msg *msgs, in
>  
>  	ret = spacemit_i2c_wait_bus_idle(i2c);
>  	if (!ret)
> -		spacemit_i2c_xfer_msg(i2c);
> +		ret = spacemit_i2c_xfer_msg(i2c);
Sorry this is my mistake.
Thanks for your fixes.

Reviewed-by: Troy Mitchell <troymitchell988@gmail.com>
>  	else if (ret < 0)
>  		dev_dbg(i2c->dev, "i2c transfer error: %d\n", ret);
>  	else
> 
> base-commit: a5806cd506af5a7c19bcd596e4708b5c464bfd21
> -- 
> 2.45.2
>