[PATCH] dmaengine: fl1-edma: Add error handling for devm_kasprintf

[PATCH] dmaengine: fl1-edma: Add error handling for devm_kasprintf

[Greg Kroah-Hartman]

From: Griffin Kroah-Hartman <griffin@kroah.com>

Add error handling statement to fls_edma3_irq_init() for the
devm_kasprintf call.

Assisted-by: gkh_clanker_2000
Cc: stable <stable@kernel.org>
Cc: Frank Li <Frank.Li@nxp.com>
Cc: Vinod Koul <vkoul@kernel.org>
Cc: imx@lists.linux.dev
Signed-off-by: Griffin Kroah-Hartman <griffin@kroah.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/dma/fsl-edma-main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c
index 36155ab1602a..d9fb717b5b53 100644
--- a/drivers/dma/fsl-edma-main.c
+++ b/drivers/dma/fsl-edma-main.c
@@ -414,6 +414,8 @@ static int fsl_edma3_irq_init(struct platform_device *pdev, struct fsl_edma_engi
 
 		errirq_name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%s-err",
 					     dev_name(&pdev->dev));
+		if (!errirq_name)
+			return -ENOMEM;
 
 		ret = devm_request_irq(&pdev->dev, fsl_edma->errirq, fsl_edma3_err_handler_shared,
 				       0, errirq_name, fsl_edma);
-- 
2.55.0

Re: [PATCH] dmaengine: fl1-edma: Add error handling for devm_kasprintf

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:

Pre-existing issues:
- [High] The driver masks `-EPROBE_DEFER` from both `platform_get_irq()` and `platform_get_irq_optional()`.
- [High] Missing explicit cleanup of `txirq_16_31` in `fsl_edma_irq_exit()` creates a race condition during module removal.
- [High] Use of `BIT()` instead of `BIT_ULL()` with a `u64` bitmask causes shift out of bounds on 32-bit platforms.
--

commit dcca75c04a71e337392f5a5707b96105b925f750
Author: Griffin Kroah-Hartman <griffin@kroah.com>

dmaengine: fl1-edma: Add error handling for devm_kasprintf
    
Add error handling statement to fls_edma3_irq_init() for the
devm_kasprintf call.

> diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c
> index 36155ab1602a9..d9fb717b5b53c 100644
> --- a/drivers/dma/fsl-edma-main.c
> +++ b/drivers/dma/fsl-edma-main.c
> @@ -414,6 +414,8 @@ static int fsl_edma3_irq_init(struct platform_device *pdev, struct fsl_edma_engi
>  
>  		errirq_name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%s-err",
>  					     dev_name(&pdev->dev));
> +		if (!errirq_name)
> +			return -ENOMEM;
>  
>  		ret = devm_request_irq(&pdev->dev, fsl_edma->errirq, fsl_edma3_err_handler_shared,
>  				       0, errirq_name, fsl_edma);

[Severity: High]
This isn't a bug introduced by this patch, but while modifying 
fsl_edma3_irq_init(), does the driver mask -EPROBE_DEFER from 
platform_get_irq() and platform_get_irq_optional()?

drivers/dma/fsl-edma-main.c:fsl_edma3_irq_init() {
    ...
		fsl_chan->txirq = platform_get_irq(pdev, i);
		if (fsl_chan->txirq < 0)
			return  -EINVAL;
    ...
		fsl_edma->errirq = platform_get_irq_optional(pdev, fsl_edma->n_chans);
		if (fsl_edma->errirq < 0)
			return 0; /* dts miss err irq, treat as no err irq case */
    ...
}

If either of these functions return -EPROBE_DEFER because the IRQ controller
is not yet ready, discarding the error code converts a recoverable probe
deferral into a permanent initialization failure or a silent missing interrupt.

[Severity: High]
This is a pre-existing issue, but can the chan_masked check result in an 
out-of-bounds shift on 32-bit platforms?

drivers/dma/fsl-edma-main.c:fsl_edma3_irq_init() {
    ...
	for (i = 0; i < fsl_edma->n_chans; i++) {
        ...
		if (fsl_edma->chan_masked & BIT(i))
			continue;
    ...
}

Since chan_masked is a u64, using BIT(i) instead of BIT_ULL(i) produces an
unsigned long.

On 32-bit architectures, this evaluates incorrectly for channels 32-63,
proceeding with initialization for channels that should have been masked off.

[Severity: High]
This is a pre-existing issue, but is there a race condition during module 
removal due to missing cleanup of txirq_16_31?

drivers/dma/fsl-edma-main.c:fsl_edma_remove() {
    ...
	fsl_edma_irq_exit(pdev, fsl_edma);
	fsl_edma_cleanup_vchan(&fsl_edma->dma_dev);
    ...
}

During fsl_edma_remove(), the driver attempts to silence interrupts
by calling devm_free_irq() in fsl_edma_irq_exit():

drivers/dma/fsl-edma-main.c:fsl_edma_irq_exit() {
    ...
    (missing explicit free of txirq_16_31)
    ...
}

If fsl_edma_irq_exit() fails to free fsl_edma->txirq_16_31, an interrupt
can fire for channels 16-31 while fsl_edma_cleanup_vchan() is tearing down
the virtual channels.

Could this cause the handler to execute on partially destroyed state?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/2026070605-frying-fling-b9c5@gregkh?part=1

Re: [PATCH] dmaengine: fl1-edma: Add error handling for devm_kasprintf

[Frank Li]

On Mon, Jul 06, 2026 at 04:57:06PM +0200, Greg Kroah-Hartman wrote:
> From: Griffin Kroah-Hartman <griffin@kroah.com>

Please subject tags

dmaengine: fsl-edma: ....

>
> Add error handling statement to fls_edma3_irq_init() for the
> devm_kasprintf call.

function need ()
devm_kasprintf()

Frank
>
> Assisted-by: gkh_clanker_2000
> Cc: stable <stable@kernel.org>
> Cc: Frank Li <Frank.Li@nxp.com>
> Cc: Vinod Koul <vkoul@kernel.org>
> Cc: imx@lists.linux.dev
> Signed-off-by: Griffin Kroah-Hartman <griffin@kroah.com>
> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
> ---
>  drivers/dma/fsl-edma-main.c | 2 ++
>  1 file changed, 2 insertions(+)
>
> diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c
> index 36155ab1602a..d9fb717b5b53 100644
> --- a/drivers/dma/fsl-edma-main.c
> +++ b/drivers/dma/fsl-edma-main.c
> @@ -414,6 +414,8 @@ static int fsl_edma3_irq_init(struct platform_device *pdev, struct fsl_edma_engi
>
>  		errirq_name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%s-err",
>  					     dev_name(&pdev->dev));
> +		if (!errirq_name)
> +			return -ENOMEM;
>
>  		ret = devm_request_irq(&pdev->dev, fsl_edma->errirq, fsl_edma3_err_handler_shared,
>  				       0, errirq_name, fsl_edma);
> --
> 2.55.0
>

Re: [PATCH] dmaengine: fl1-edma: Add error handling for devm_kasprintf

[Vinod Koul]

On Mon, 06 Jul 2026 16:57:06 +0200, Greg Kroah-Hartman wrote:
> Add error handling statement to fls_edma3_irq_init() for the
> devm_kasprintf call.
> 
> 

Applied, thanks!

[1/1] dmaengine: fl1-edma: Add error handling for devm_kasprintf
      commit: bf1af4dfdc017dfe989c0dbcf0e608dc95f1d2cb

Best regards,
-- 
~Vinod

Re: [PATCH] dmaengine: fl1-edma: Add error handling for devm_kasprintf

[Markus Elfring]

> > Add error handling statement to fls_edma3_irq_init() for the
> > devm_kasprintf call.
…
> Applied, thanks!
> 
> [1/1] dmaengine: fl1-edma: Add error handling for devm_kasprintf
>       commit: bf1af4dfdc017dfe989c0dbcf0e608dc95f1d2cb

Frank Li requested a corrected patch subject.

Regards,
Markus

Re: [PATCH] dmaengine: fl1-edma: Add error handling for devm_kasprintf

[Markus Elfring]

> > Add error handling statement to fls_edma3_irq_init() for the
> > devm_kasprintf call.
…
> Applied, thanks!
> 
> [1/1] dmaengine: fl1-edma: Add error handling for devm_kasprintf
>       commit: bf1af4dfdc017dfe989c0dbcf0e608dc95f1d2cb

https://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine.git/commit/?h=next&id=bf1af4dfdc017dfe989c0dbcf0e608dc95f1d2cb

Would it become helpful to add the following tag?


Fixes: d175222f5e90b7e1f23713378823c338fabb3258 ("dmaegnine: fsl-edma: add edma error interrupt handler")


Regards,
Markus

Re: [PATCH] dmaengine: fl1-edma: Add error handling for devm_kasprintf

[Greg Kroah-Hartman]

On Tue, Jul 14, 2026 at 05:58:32PM +0200, Markus Elfring wrote:
> > > Add error handling statement to fls_edma3_irq_init() for the
> > > devm_kasprintf call.
> …
> > Applied, thanks!
> > 
> > [1/1] dmaengine: fl1-edma: Add error handling for devm_kasprintf
> >       commit: bf1af4dfdc017dfe989c0dbcf0e608dc95f1d2cb
> 
> https://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine.git/commit/?h=next&id=bf1af4dfdc017dfe989c0dbcf0e608dc95f1d2cb
> 
> Would it become helpful to add the following tag?
> 
> 
> Fixes: d175222f5e90b7e1f23713378823c338fabb3258 ("dmaegnine: fsl-edma: add edma error interrupt handler")
> 
> 
> Regards,
> Markus

Hi,

This is the semi-friendly patch-bot of Greg Kroah-Hartman.

Markus, you seem to have sent a nonsensical or otherwise pointless
review comment to a patch submission on a Linux kernel developer mailing
list.  I strongly suggest that you not do this anymore.  Please do not
bother developers who are actively working to produce patches and
features with comments that, in the end, are a waste of time.

Patch submitter, please ignore Markus's suggestion; you do not need to
follow it at all.  The person/bot/AI that sent it is being ignored by
almost all Linux kernel maintainers for having a persistent pattern of
behavior of producing distracting and pointless commentary, and
inability to adapt to feedback.  Please feel free to also ignore emails
from them.

thanks,

greg k-h's patch email bot

Re: [PATCH] dmaengine: fl1-edma: Add error handling for devm_kasprintf

[Vinod Koul]

On 14-07-26, 17:01, Markus Elfring wrote:
> > > Add error handling statement to fls_edma3_irq_init() for the
> > > devm_kasprintf call.
> …
> > Applied, thanks!
> > 
> > [1/1] dmaengine: fl1-edma: Add error handling for devm_kasprintf
> >       commit: bf1af4dfdc017dfe989c0dbcf0e608dc95f1d2cb
> 
> Frank Li requested a corrected patch subject.

Which was done while applying
bf1af4dfdc01 dmaengine: fsl-edma: Add error handling for devm_kasprintf

-- 
~Vinod

Re: [PATCH] dmaengine: fl1-edma: Add error handling for devm_kasprintf

[Markus Elfring]

>>>> Add error handling statement to fls_edma3_irq_init() for the
>>>> devm_kasprintf call.
>> …
>>> Applied, thanks!
>>>
>>> [1/1] dmaengine: fl1-edma: Add error handling for devm_kasprintf
>>>       commit: bf1af4dfdc017dfe989c0dbcf0e608dc95f1d2cb
>>
>> Frank Li requested a corrected patch subject.
> 
> Which was done while applying
> bf1af4dfdc01 dmaengine: fsl-edma: Add error handling for devm_kasprintf
I find it unfortunate that an improvable text was mentioned in the notification.

Did different development opinions remain if all involved function names
should usually be marked with parentheses?

Regards,
Markus

Re: [PATCH] dmaengine: fl1-edma: Add error handling for devm_kasprintf

[Greg Kroah-Hartman]

On Wed, Jul 15, 2026 at 08:11:09AM +0200, Markus Elfring wrote:
> >>>> Add error handling statement to fls_edma3_irq_init() for the
> >>>> devm_kasprintf call.
> >> …
> >>> Applied, thanks!
> >>>
> >>> [1/1] dmaengine: fl1-edma: Add error handling for devm_kasprintf
> >>>       commit: bf1af4dfdc017dfe989c0dbcf0e608dc95f1d2cb
> >>
> >> Frank Li requested a corrected patch subject.
> > 
> > Which was done while applying
> > bf1af4dfdc01 dmaengine: fsl-edma: Add error handling for devm_kasprintf
> I find it unfortunate that an improvable text was mentioned in the notification.
> 
> Did different development opinions remain if all involved function names
> should usually be marked with parentheses?
> 
> Regards,
> Markus

Hi,

This is the semi-friendly patch-bot of Greg Kroah-Hartman.

Markus, you seem to have sent a nonsensical or otherwise pointless
review comment to a patch submission on a Linux kernel developer mailing
list.  I strongly suggest that you not do this anymore.  Please do not
bother developers who are actively working to produce patches and
features with comments that, in the end, are a waste of time.

Patch submitter, please ignore Markus's suggestion; you do not need to
follow it at all.  The person/bot/AI that sent it is being ignored by
almost all Linux kernel maintainers for having a persistent pattern of
behavior of producing distracting and pointless commentary, and
inability to adapt to feedback.  Please feel free to also ignore emails
from them.

thanks,

greg k-h's patch email bot