linux-kernel - Re: [PATCH v1] ACPI: Property: Fix type detection of unified integer reading functions

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Thu, 25 Aug 2022 07:45:06 +0000
From:   Sakari Ailus <sakari.ailus@...ux.intel.com>
To:     Ard Biesheuvel <ardb@...nel.org>
Cc:     sbinding@...nsource.cirrus.com, andriy.shevchenko@...el.com,
        linux-acpi@...r.kernel.org, linux-kernel@...r.kernel.org,
        patches@...nsource.cirrus.com, rafael@...nel.org
Subject: Re: [PATCH v1] ACPI: Property: Fix type detection of unified integer
 reading functions

Hi Ard,

On Thu, Aug 25, 2022 at 09:25:05AM +0200, Ard Biesheuvel wrote:
> > The current code expects the type of the value to be an integer type,
> > instead the value passed to the macro is a pointer.
> > Ensure the size comparison uses the correct pointer type to choose the
> > max value, instead of using the integer type.
> > 
> > Fixes: 923044133367 ("ACPI: property: Unify integer value reading functions")
> > 
> > Signed-off-by: Stefan Binding <sbinding@...nsource.cirrus.com>
> 
> Acked-by: Ard Biesheuvel <ardb@...nel.org>
> 
> Can we get this queued up and sent out please? This is breaking some ACPI arm64
> systems, which use device properties for their MAC addresses.
> 
> Some grumbling about the original patch below.
> 
> > ---
> >  drivers/acpi/property.c | 8 ++++----
> >  1 file changed, 4 insertions(+), 4 deletions(-)
> > 
> > diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
> > index 7b3ad8ed2f4e..b1d4a8db89df 100644
> > --- a/drivers/acpi/property.c
> > +++ b/drivers/acpi/property.c
> > @@ -1043,10 +1043,10 @@ static int acpi_data_prop_read_single(const struct acpi_device_data *data,
> >  				break;					\
> >  			}						\
> >  			if (__items[i].integer.value > _Generic(__val,	\
> > -								u8: U8_MAX, \
> > -								u16: U16_MAX, \
> > -								u32: U32_MAX, \
> > -								u64: U64_MAX, \
> > +								u8 *: U8_MAX, \
> > +								u16 *: U16_MAX, \
> > +								u32 *: U32_MAX, \
> > +								u64 *: U64_MAX, \
> >  								default: 0U)) { \
> 
> Why is there a default here? Having one is what hides the fact that the patch was completely broken.

I think the default can be removed. I can send a patch.

> 
> >  				ret = -EOVERFLOW;			\
> >  				break;					\
> > 
> 
> Also, I must ask: given how broken the original patch is, I suppose no testing whatsoever was done? 

Testing was done but it failed to uncover this. It seems all the properties
in the system were of buffer type.

Please wrap your lines before 80. It'll be easier to read that way.

-- 
Kind regards,

Sakari Ailus