[PATCH] drm/amd/pm: check return value of amdgpu_irq_add_id()

[PATCH] drm/amd/pm: check return value of amdgpu_irq_add_id()

[Igor Artemiev]

amdgpu_irq_ad_id() may fail and the irq handlers will not be registered.
This patch adds error code check.

Found by Linux Verification Center (linuxtesting.org) with static
analysis tool SVACE.

Signed-off-by: Igor Artemiev <Igor.A.Artemiev@mcst.ru>
---
 .../drm/amd/pm/powerplay/hwmgr/smu_helper.c   | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c
index 79a566f3564a..109df1039d5c 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c
@@ -647,28 +647,41 @@ int smu9_register_irq_handlers(struct pp_hwmgr *hwmgr)
 {
 	struct amdgpu_irq_src *source =
 		kzalloc(sizeof(struct amdgpu_irq_src), GFP_KERNEL);
+	int ret;
 
 	if (!source)
 		return -ENOMEM;
 
 	source->funcs = &smu9_irq_funcs;
 
-	amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
+	ret = amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
 			SOC15_IH_CLIENTID_THM,
 			THM_9_0__SRCID__THM_DIG_THERM_L2H,
 			source);
-	amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
+	if (ret)
+		goto err;
+
+	ret = amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
 			SOC15_IH_CLIENTID_THM,
 			THM_9_0__SRCID__THM_DIG_THERM_H2L,
 			source);
+	if (ret)
+		goto err;
 
 	/* Register CTF(GPIO_19) interrupt */
-	amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
+	ret = amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
 			SOC15_IH_CLIENTID_ROM_SMUIO,
 			SMUIO_9_0__SRCID__SMUIO_GPIO19,
 			source);
+	if (ret)
+		goto err;
 
 	return 0;
+
+err:
+	kfree(source);
+
+	return ret;
 }
 
 void *smu_atom_get_data_table(void *dev, uint32_t table, uint16_t *size,
-- 
2.39.2

Re: [PATCH] drm/amd/pm: check return value of amdgpu_irq_add_id()

[Christian König]

Am 01.10.24 um 12:57 schrieb Igor Artemiev:
> amdgpu_irq_ad_id() may fail and the irq handlers will not be registered.
> This patch adds error code check.
>
> Found by Linux Verification Center (linuxtesting.org) with static
> analysis tool SVACE.
>
> Signed-off-by: Igor Artemiev <Igor.A.Artemiev@mcst.ru>
> ---
>   .../drm/amd/pm/powerplay/hwmgr/smu_helper.c   | 19 ++++++++++++++++---
>   1 file changed, 16 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c
> index 79a566f3564a..109df1039d5c 100644
> --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c
> +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c
> @@ -647,28 +647,41 @@ int smu9_register_irq_handlers(struct pp_hwmgr *hwmgr)
>   {
>   	struct amdgpu_irq_src *source =
>   		kzalloc(sizeof(struct amdgpu_irq_src), GFP_KERNEL);
> +	int ret;
>   
>   	if (!source)
>   		return -ENOMEM;
>   
>   	source->funcs = &smu9_irq_funcs;
>   
> -	amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
> +	ret = amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),

The cast to struct amdgpu_device should probably be removed.

>   			SOC15_IH_CLIENTID_THM,
>   			THM_9_0__SRCID__THM_DIG_THERM_L2H,
>   			source);

And the parameters indented to the new opening of the (.

Regards,
Christian.

> -	amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
> +	if (ret)
> +		goto err;
> +
> +	ret = amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
>   			SOC15_IH_CLIENTID_THM,
>   			THM_9_0__SRCID__THM_DIG_THERM_H2L,
>   			source);
> +	if (ret)
> +		goto err;
>   
>   	/* Register CTF(GPIO_19) interrupt */
> -	amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
> +	ret = amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
>   			SOC15_IH_CLIENTID_ROM_SMUIO,
>   			SMUIO_9_0__SRCID__SMUIO_GPIO19,
>   			source);
> +	if (ret)
> +		goto err;
>   
>   	return 0;
> +
> +err:
> +	kfree(source);
> +
> +	return ret;
>   }
>   
>   void *smu_atom_get_data_table(void *dev, uint32_t table, uint16_t *size,

[PATCH v2] drm/amd/pm: check return value of amdgpu_irq_add_id()

[Igor Artemiev]

amdgpu_irq_ad_id() may fail and the irq handlers will not be registered.
This patch adds error code check.

Found by Linux Verification Center (linuxtesting.org) with static
analysis tool SVACE.

Signed-off-by: Igor Artemiev <Igor.A.Artemiev@mcst.ru>
---
v2: Remove the cast to struct amdgpu_device as Christian König 
<christian.koenig@amd.com> suggested.

 .../drm/amd/pm/powerplay/hwmgr/smu_helper.c   | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c
index 79a566f3564a..50a3085c00aa 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c
@@ -647,28 +647,41 @@ int smu9_register_irq_handlers(struct pp_hwmgr *hwmgr)
 {
 	struct amdgpu_irq_src *source =
 		kzalloc(sizeof(struct amdgpu_irq_src), GFP_KERNEL);
+	int ret;
 
 	if (!source)
 		return -ENOMEM;
 
 	source->funcs = &smu9_irq_funcs;
 
-	amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
+	ret = amdgpu_irq_add_id(hwmgr->adev,
 			SOC15_IH_CLIENTID_THM,
 			THM_9_0__SRCID__THM_DIG_THERM_L2H,
 			source);
-	amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
+	if (ret)
+		goto err;
+
+	ret = amdgpu_irq_add_id(hwmgr->adev,
 			SOC15_IH_CLIENTID_THM,
 			THM_9_0__SRCID__THM_DIG_THERM_H2L,
 			source);
+	if (ret)
+		goto err;
 
 	/* Register CTF(GPIO_19) interrupt */
-	amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
+	ret = amdgpu_irq_add_id(hwmgr->adev,
 			SOC15_IH_CLIENTID_ROM_SMUIO,
 			SMUIO_9_0__SRCID__SMUIO_GPIO19,
 			source);
+	if (ret)
+		goto err;
 
 	return 0;
+
+err:
+	kfree(source);
+
+	return ret;
 }
 
 void *smu_atom_get_data_table(void *dev, uint32_t table, uint16_t *size,
-- 
2.39.2

Re: [PATCH v2] drm/amd/pm: check return value of amdgpu_irq_add_id()

[Alex Deucher]

Applied.  Thanks!

Alex

On Wed, Oct 2, 2024 at 9:28 AM Igor Artemiev <Igor.A.Artemiev@mcst.ru> wrote:
>
> amdgpu_irq_ad_id() may fail and the irq handlers will not be registered.
> This patch adds error code check.
>
> Found by Linux Verification Center (linuxtesting.org) with static
> analysis tool SVACE.
>
> Signed-off-by: Igor Artemiev <Igor.A.Artemiev@mcst.ru>
> ---
> v2: Remove the cast to struct amdgpu_device as Christian König
> <christian.koenig@amd.com> suggested.
>
>  .../drm/amd/pm/powerplay/hwmgr/smu_helper.c   | 19 ++++++++++++++++---
>  1 file changed, 16 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c
> index 79a566f3564a..50a3085c00aa 100644
> --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c
> +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c
> @@ -647,28 +647,41 @@ int smu9_register_irq_handlers(struct pp_hwmgr *hwmgr)
>  {
>         struct amdgpu_irq_src *source =
>                 kzalloc(sizeof(struct amdgpu_irq_src), GFP_KERNEL);
> +       int ret;
>
>         if (!source)
>                 return -ENOMEM;
>
>         source->funcs = &smu9_irq_funcs;
>
> -       amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
> +       ret = amdgpu_irq_add_id(hwmgr->adev,
>                         SOC15_IH_CLIENTID_THM,
>                         THM_9_0__SRCID__THM_DIG_THERM_L2H,
>                         source);
> -       amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
> +       if (ret)
> +               goto err;
> +
> +       ret = amdgpu_irq_add_id(hwmgr->adev,
>                         SOC15_IH_CLIENTID_THM,
>                         THM_9_0__SRCID__THM_DIG_THERM_H2L,
>                         source);
> +       if (ret)
> +               goto err;
>
>         /* Register CTF(GPIO_19) interrupt */
> -       amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
> +       ret = amdgpu_irq_add_id(hwmgr->adev,
>                         SOC15_IH_CLIENTID_ROM_SMUIO,
>                         SMUIO_9_0__SRCID__SMUIO_GPIO19,
>                         source);
> +       if (ret)
> +               goto err;
>
>         return 0;
> +
> +err:
> +       kfree(source);
> +
> +       return ret;
>  }
>
>  void *smu_atom_get_data_table(void *dev, uint32_t table, uint16_t *size,
> --
> 2.39.2
>

Re: [lvc-project] [PATCH v2] drm/amd/pm: check return value of amdgpu_irq_add_id()

[Fedor Pchelkin]

On Wed, 02. Oct 16:01, Igor Artemiev wrote:
> amdgpu_irq_ad_id() may fail and the irq handlers will not be registered.
> This patch adds error code check.
> 
> Found by Linux Verification Center (linuxtesting.org) with static
> analysis tool SVACE.
> 
> Signed-off-by: Igor Artemiev <Igor.A.Artemiev@mcst.ru>
> ---
> v2: Remove the cast to struct amdgpu_device as Christian König 
> <christian.koenig@amd.com> suggested.
> 
>  .../drm/amd/pm/powerplay/hwmgr/smu_helper.c   | 19 ++++++++++++++++---
>  1 file changed, 16 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c
> index 79a566f3564a..50a3085c00aa 100644
> --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c
> +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c
> @@ -647,28 +647,41 @@ int smu9_register_irq_handlers(struct pp_hwmgr *hwmgr)
>  {
>  	struct amdgpu_irq_src *source =
>  		kzalloc(sizeof(struct amdgpu_irq_src), GFP_KERNEL);
> +	int ret;
>  
>  	if (!source)
>  		return -ENOMEM;
>  
>  	source->funcs = &smu9_irq_funcs;
>  
> -	amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
> +	ret = amdgpu_irq_add_id(hwmgr->adev,
>  			SOC15_IH_CLIENTID_THM,
>  			THM_9_0__SRCID__THM_DIG_THERM_L2H,
>  			source);
> -	amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
> +	if (ret)
> +		goto err;
> +
> +	ret = amdgpu_irq_add_id(hwmgr->adev,
>  			SOC15_IH_CLIENTID_THM,
>  			THM_9_0__SRCID__THM_DIG_THERM_H2L,
>  			source);
> +	if (ret)
> +		goto err;
>  
>  	/* Register CTF(GPIO_19) interrupt */
> -	amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
> +	ret = amdgpu_irq_add_id(hwmgr->adev,
>  			SOC15_IH_CLIENTID_ROM_SMUIO,
>  			SMUIO_9_0__SRCID__SMUIO_GPIO19,
>  			source);
> +	if (ret)
> +		goto err;
>  
>  	return 0;
> +
> +err:
> +	kfree(source);

Oh, the calltrace looks like:

hwmgr_sw_init()
  phm_register_irq_handlers()
    ->register_irq_handlers()
    smu9_register_irq_handlers()

And the return value of phm_register_irq_handlers() is not processed and
the error is not reported anywhere, so I guess there is a risk of
use-after-free: the source pointer may have been already registered by
some of amdgpu_irq_add_id() calls before the error occured.

The similar code exists in smu7_register_irq_handlers(), maybe should be
fixed as well.

Alex, is https://gitlab.freedesktop.org/agd5f/linux a public repo this
patch should go in? I'd suggest to drop the patch and ask Igor to do a
complete fix or, if dropping is not possible now, fix it by another patch.
For the latter one I can do this myself but it would be nice to refer to
the current patch via a git hash (it's probably not published yet in your
repo).

> +
> +	return ret;
>  }
>  
>  void *smu_atom_get_data_table(void *dev, uint32_t table, uint16_t *size,
> -- 
> 2.39.2

Re: [lvc-project] [PATCH v2] drm/amd/pm: check return value of amdgpu_irq_add_id()

[Alex Deucher]

On Thu, Oct 3, 2024 at 10:28 AM Fedor Pchelkin <pchelkin@ispras.ru> wrote:
>
> On Wed, 02. Oct 16:01, Igor Artemiev wrote:
> > amdgpu_irq_ad_id() may fail and the irq handlers will not be registered.
> > This patch adds error code check.
> >
> > Found by Linux Verification Center (linuxtesting.org) with static
> > analysis tool SVACE.
> >
> > Signed-off-by: Igor Artemiev <Igor.A.Artemiev@mcst.ru>
> > ---
> > v2: Remove the cast to struct amdgpu_device as Christian König
> > <christian.koenig@amd.com> suggested.
> >
> >  .../drm/amd/pm/powerplay/hwmgr/smu_helper.c   | 19 ++++++++++++++++---
> >  1 file changed, 16 insertions(+), 3 deletions(-)
> >
> > diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c
> > index 79a566f3564a..50a3085c00aa 100644
> > --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c
> > +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c
> > @@ -647,28 +647,41 @@ int smu9_register_irq_handlers(struct pp_hwmgr *hwmgr)
> >  {
> >       struct amdgpu_irq_src *source =
> >               kzalloc(sizeof(struct amdgpu_irq_src), GFP_KERNEL);
> > +     int ret;
> >
> >       if (!source)
> >               return -ENOMEM;
> >
> >       source->funcs = &smu9_irq_funcs;
> >
> > -     amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
> > +     ret = amdgpu_irq_add_id(hwmgr->adev,
> >                       SOC15_IH_CLIENTID_THM,
> >                       THM_9_0__SRCID__THM_DIG_THERM_L2H,
> >                       source);
> > -     amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
> > +     if (ret)
> > +             goto err;
> > +
> > +     ret = amdgpu_irq_add_id(hwmgr->adev,
> >                       SOC15_IH_CLIENTID_THM,
> >                       THM_9_0__SRCID__THM_DIG_THERM_H2L,
> >                       source);
> > +     if (ret)
> > +             goto err;
> >
> >       /* Register CTF(GPIO_19) interrupt */
> > -     amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
> > +     ret = amdgpu_irq_add_id(hwmgr->adev,
> >                       SOC15_IH_CLIENTID_ROM_SMUIO,
> >                       SMUIO_9_0__SRCID__SMUIO_GPIO19,
> >                       source);
> > +     if (ret)
> > +             goto err;
> >
> >       return 0;
> > +
> > +err:
> > +     kfree(source);
>
> Oh, the calltrace looks like:
>
> hwmgr_sw_init()
>   phm_register_irq_handlers()
>     ->register_irq_handlers()
>     smu9_register_irq_handlers()
>
> And the return value of phm_register_irq_handlers() is not processed and
> the error is not reported anywhere, so I guess there is a risk of
> use-after-free: the source pointer may have been already registered by
> some of amdgpu_irq_add_id() calls before the error occured.
>
> The similar code exists in smu7_register_irq_handlers(), maybe should be
> fixed as well.
>
> Alex, is https://gitlab.freedesktop.org/agd5f/linux a public repo this
> patch should go in? I'd suggest to drop the patch and ask Igor to do a
> complete fix or, if dropping is not possible now, fix it by another patch.
> For the latter one I can do this myself but it would be nice to refer to
> the current patch via a git hash (it's probably not published yet in your
> repo).

Dropped.  Thanks.

Alex

>
> > +
> > +     return ret;
> >  }
> >
> >  void *smu_atom_get_data_table(void *dev, uint32_t table, uint16_t *size,
> > --
> > 2.39.2