| Message ID | 3fb1398741536232a1e9b54a5de4072420046db5.1710146668.git.hanshu-oc@zhaoxin.com |
|---|---|
| State | New |
| Headers | show |
| Series | [v2,1/2] i2c: viai2c: Fix some minor style issues | expand |
Hi Andi, On 2024/3/11 17:46, Andi Shyti wrote: > > [这封邮件来自外部发件人 谨防风险] > > Hi Hans, > > because Mukes had questions on the v1, please do include him for > the next versions. > > On Mon, Mar 11, 2024 at 04:46:55PM +0800, Hans Hu wrote: >> For the case that msg->len is 0(I2C_SMBUS_QUICK), when the interrupt >> occurs, it means that the access has completed, viai2c_irq_xfer() >> should return 1. > The commit log is still not enough. We don't konw which patch has > introduced the error and why. > > Next time, please, try to be a bit more specific, trying to anser > the questions: > > - what is the problem > - how did you find out > - how you fixed > - how you tested it > > But, I see that the issue was introduced here: > > 4b0c0569f032 ("i2c: wmt: fix a bug when thread blocked") > > This patch has not been yet merged into Wolfram's tree. > Therefore, I will ask you to let this go this time and we can > take the whole series after the merge window. > > Please, fix all the issues you find, including the checkpatch > warnings/errors (please keep one patch per kind of checkpatch > fix). > > Last thing, please keep bug fixes separate from > features/cosmetic/refactoring. They need to be merged separately. > > Does it work for you? No other issues have been found so far. All these suggestions you mentioned, I will pay attention to when submitting patches in the future. Hans, Thanks
diff --git a/drivers/i2c/busses/i2c-viai2c-common.c b/drivers/i2c/busses/i2c-viai2c-common.c index 4c208b3a509e..fbb76d7ea3b0 100644 --- a/drivers/i2c/busses/i2c-viai2c-common.c +++ b/drivers/i2c/busses/i2c-viai2c-common.c @@ -123,6 +123,14 @@ int viai2c_xfer(struct i2c_adapter *adap, struct i2c_msg msgs[], int num) return (ret < 0) ? ret : i; } +/* + * Main process of the byte mode xfer + * + * Return value indicates whether the transfer is complete + * 1: all the data has been successfully transferred + * 0: there is still data that needs to be transferred + * -EIO: error occurred + */ static int viai2c_irq_xfer(struct viai2c *i2c) { u16 val; @@ -142,10 +150,11 @@ static int viai2c_irq_xfer(struct viai2c *i2c) if (val & VIAI2C_CSR_RCV_NOT_ACK) return -EIO; + /* I2C_SMBUS_QUICK */ if (msg->len == 0) { val = VIAI2C_CR_TX_END | VIAI2C_CR_CPU_RDY | VIAI2C_CR_ENABLE; writew(val, base + VIAI2C_REG_CR); - return 0; + return 1; } if ((i2c->xfered_len + 1) == msg->len) { @@ -195,6 +204,7 @@ static irqreturn_t viai2c_isr(int irq, void *data) i2c->ret = viai2c_fifo_irq_xfer(i2c, true); } + /* All the data has been successfully transferred or error occurred */ if (i2c->ret) complete(&i2c->complete);
For the case that msg->len is 0(I2C_SMBUS_QUICK), when the interrupt occurs, it means that the access has completed, viai2c_irq_xfer() should return 1. v1->v2: Added some code comments; The commit log is adjusted. Link: https://lore.kernel.org/all/20240311032600.56244-2-hanshu-oc@zhaoxin.com/ Signed-off-by: Hans Hu <hanshu-oc@zhaoxin.com> --- drivers/i2c/busses/i2c-viai2c-common.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-)