[PATCH] i2c-rcar: fix MNR interrupt handling

[PATCH] i2c-rcar: fix MNR interrupt handling

[Sergei Shtylyov]

Sometimes the MNR and MST interrupts happen simultaneously  (stop  automatically
follows NACK, according to the manuals) and in such case the ID_NACK flag  isn't
set since the MST interrupt handling precedes MNR and all interrupts are cleared
and disabled then, so that MNR interrupt is never noticed -- this causes NACK'ed
transfers to be falsely reported as successful. Exchanging MNR and  MST handlers
fixes this issue, however the MNR bit  somehow  gets set again even after  being
explicitly cleared, so I decided to completely suppress handling of all disabled
interrupts (which is a good thing anyway)...

Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Cc: stable@vger.kernel.org

---
The patch is against Wolfram Sang's 'linux.git' repo.

 drivers/i2c/busses/i2c-rcar.c |   15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

Index: linux/drivers/i2c/busses/i2c-rcar.c
===================================================================
--- linux.orig/drivers/i2c/busses/i2c-rcar.c
+++ linux/drivers/i2c/busses/i2c-rcar.c
@@ -367,18 +367,15 @@ static irqreturn_t rcar_i2c_irq(int irq,
 
 	msr = rcar_i2c_read(priv, ICMSR);
 
+	/* Only handle interrupts that are currently enabled */
+	msr &= rcar_i2c_read(priv, ICMIER);
+
 	/* Arbitration lost */
 	if (msr & MAL) {
 		rcar_i2c_flags_set(priv, (ID_DONE | ID_ARBLOST));
 		goto out;
 	}
 
-	/* Stop */
-	if (msr & MST) {
-		rcar_i2c_flags_set(priv, ID_DONE);
-		goto out;
-	}
-
 	/* Nack */
 	if (msr & MNR) {
 		/* go to stop phase */
@@ -388,6 +385,12 @@ static irqreturn_t rcar_i2c_irq(int irq,
 		goto out;
 	}
 
+	/* Stop */
+	if (msr & MST) {
+		rcar_i2c_flags_set(priv, ID_DONE);
+		goto out;
+	}
+
 	if (rcar_i2c_is_recv(priv))
 		rcar_i2c_flags_set(priv, rcar_i2c_irq_recv(priv, msr));
 	else

Re: [PATCH] i2c-rcar: fix MNR interrupt handling

[Wolfram Sang]

[-- Attachment #1: Type: text/plain, Size: 848 bytes --]

On Tue, Sep 02, 2014 at 01:15:26AM +0400, Sergei Shtylyov wrote:
> Sometimes the MNR and MST interrupts happen simultaneously  (stop  automatically
> follows NACK, according to the manuals) and in such case the ID_NACK flag  isn't
> set since the MST interrupt handling precedes MNR and all interrupts are cleared
> and disabled then, so that MNR interrupt is never noticed -- this causes NACK'ed
> transfers to be falsely reported as successful. Exchanging MNR and  MST handlers
> fixes this issue, however the MNR bit  somehow  gets set again even after  being
> explicitly cleared, so I decided to completely suppress handling of all disabled
> interrupts (which is a good thing anyway)...
> 
> Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
> Cc: stable@vger.kernel.org
> 

Applied to for-current, thanks!


[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 819 bytes --]

Re: [PATCH] i2c-rcar: fix MNR interrupt handling

[Sergei Shtylyov]

On 09/02/2014 01:15 AM, Sergei Shtylyov wrote:

> Sometimes the MNR and MST interrupts happen simultaneously  (stop  automatically
> follows NACK, according to the manuals) and in such case the ID_NACK flag  isn't
> set since the MST interrupt handling precedes MNR and all interrupts are cleared
> and disabled then, so that MNR interrupt is never noticed -- this causes NACK'ed
> transfers to be falsely reported as successful. Exchanging MNR and  MST handlers
> fixes this issue, however the MNR bit  somehow  gets set again even after  being
> explicitly cleared, so I decided to completely suppress handling of all disabled
> interrupts (which is a good thing anyway)...

> Signed-off-by: Sergei Shtylyov <sergei.shtylyov-M4DtvfQ/ZS1MRgGoP+s0PdBPR1lH4CV8@public.gmane.org>
> Cc: stable-u79uwXL29TY76Z2rM5mHXA@public.gmane.org

> ---
> The patch is against Wolfram Sang's 'linux.git' repo.

>   drivers/i2c/busses/i2c-rcar.c |   15 +++++++++------
>   1 file changed, 9 insertions(+), 6 deletions(-)
>
> Index: linux/drivers/i2c/busses/i2c-rcar.c
> ===================================================================
> --- linux.orig/drivers/i2c/busses/i2c-rcar.c
> +++ linux/drivers/i2c/busses/i2c-rcar.c
> @@ -367,18 +367,15 @@ static irqreturn_t rcar_i2c_irq(int irq,
>
>   	msr = rcar_i2c_read(priv, ICMSR);
>
> +	/* Only handle interrupts that are currently enabled */
> +	msr &= rcar_i2c_read(priv, ICMIER);
> +

    I think it makes sense to check 'msr' for 0 and return IRQ_NONE in this 
case. Would you apply such patch (probably to the -next branch)?

WBR, Sergei