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 toHi Alex, you added the changelog, but the subject line
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@xxxxxxxxxxxx>
Reviewed-by: Troy Mitchell <troymitchell988@xxxxxxxxx>
---
v2: Added Troy's Reviewed-by
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