Re: [PATCH v2 2/2] misc: amd-sbi: Address copy_to/from_user() warning reported in smatch

[Gupta, Akshay]

On 6/25/2025 5:13 PM, Dan Carpenter wrote:
> Caution: This message originated from an External Source. Use proper caution when opening attachments, clicking links, or responding.
>
>
> On Wed, Jun 25, 2025 at 11:07:07AM +0000, Akshay Gupta wrote:
> > Smatch warnings are reported for below commit,
> >
> > Commit bb13a84ed6b7 ("misc: amd-sbi: Add support for CPUID protocol")
> > from Apr 28, 2025 (linux-next), leads to the following Smatch static
> > checker warning:
> >
> > drivers/misc/amd-sbi/rmi-core.c:376 apml_rmi_reg_xfer() warn: maybe return -EFAULT instead of the bytes remaining?
> > drivers/misc/amd-sbi/rmi-core.c:394 apml_mailbox_xfer() warn: maybe return -EFAULT instead of the bytes remaining?
> > drivers/misc/amd-sbi/rmi-core.c:411 apml_cpuid_xfer() warn: maybe return -EFAULT instead of the bytes remaining?
> > drivers/misc/amd-sbi/rmi-core.c:428 apml_mcamsr_xfer() warn: maybe return -EFAULT instead of the bytes remaining?
> >
> > copy_to/from_user() returns number of bytes, not copied.
> > In case data not copied, return "-EFAULT".
> >
> > Reported-by: Dan Carpenter <dan.carpenter@xxxxxxxxxx>
> > Closes: https://lore.kernel.org/all/aDVyO8ByVsceybk9@stanley.mountain/
> > Reviewed-by: Naveen Krishna Chatradhi <naveenkrishna.chatradhi@xxxxxxx>
> > Signed-off-by: Akshay Gupta <akshay.gupta@xxxxxxx>
> > ---
> > Changes from v1:
> >   - Split patch as per Greg's suggestion
> >   drivers/misc/amd-sbi/rmi-core.c | 15 +++++++++++----
> >   1 file changed, 11 insertions(+), 4 deletions(-)
> >
> > diff --git a/drivers/misc/amd-sbi/rmi-core.c b/drivers/misc/amd-sbi/rmi-core.c
> > index 3570f3b269a9..9048517c088c 100644
> > --- a/drivers/misc/amd-sbi/rmi-core.c
> > +++ b/drivers/misc/amd-sbi/rmi-core.c
> > @@ -372,7 +372,8 @@ static int apml_rmi_reg_xfer(struct sbrmi_data *data,
> >        mutex_unlock(&data->lock);
> >
> >        if (msg.rflag && !ret)
> Unrelated to this patch, but it's always better to do if (ret) {.
> Do error handling not success handling etc.

Hi Dan,

Thank you for the suggestion, will take care of this.

> > -             return copy_to_user(arg, &msg, sizeof(struct apml_reg_xfer_msg));
> > +             if (copy_to_user(arg, &msg, sizeof(struct apml_reg_xfer_msg)))
> > +                     return -EFAULT;
> >        return ret;
> >   }
> >
> > @@ -390,7 +391,9 @@ static int apml_mailbox_xfer(struct sbrmi_data *data, struct apml_mbox_msg __use
> >        if (ret && ret != -EPROTOTYPE)
> >                return ret;
> >
> > -     return copy_to_user(arg, &msg, sizeof(struct apml_mbox_msg));
> > +     if (copy_to_user(arg, &msg, sizeof(struct apml_mbox_msg)))
> > +             return -EFAULT;
> > +     return ret;
> This fixes the -EPROTOTYPE as well.  In the original code, it would
> return success where -EPROTOTYPE was intended.  It's probably worth
> mentioning that in the commit message and maybe adding a test cases to
> your test platform.
I will update the commit message to address this.
> regards,
> dan carpenter