drm_irq_uninstall should be called before pci_disable_msi, if use
devm_drm_irq_install to register the interrupt, the system will
call pci_disable_msi first and then call drm_irq_uninstall, which
will result in the following callstack.
kernel BUG at drivers/pci/msi.c:376!
Internal error: Oops - BUG: 0 [#1] SMP
CPU: 93 PID: 173814 Comm: rmmod Tainted:
pstate: a0400009 (NzCv daif +PAN -UAO -TCO BTYPE=--)
pc : free_msi_irqs+0x17c/0x1a0
lr : free_msi_irqs+0x16c/0x1a0
sp : ffff2028157f7bd0
x29: ffff2028157f7bd0 x28: ffff202849edab00
x27: 0000000000000000 x26: 0000000000000000
x25: 0000000000000000 x24: 0000000000000000
x23: ffff0020851da000 x22: ffff0020851da2d8
x21: ffff0020cc829000 x20: 0000000000000000
x19: ffff0020d6714800 x18: 0000000000000010
x17: 0000000000000000 x16: 0000000000000000
x15: ffffffffffffffff x14: ffff2028957f77df
x13: ffff2028157f77ed x12: 0000000000000000
x11: 0000000000000040 x10: ffff800011b2f8e0
x9 : ffff800011b2f8d8 x8 : ffff2020203fc458
x7 : 0000000000000000 x6 : 0000000000000000
x5 : ffff2020203fc430 x4 : ffff2020203fc4a0
x3 : 0000000000000000 x2 : 0000000000000000
x1 : 00000000000002c9 x0 : ffff0020d6719500
Call trace:
free_msi_irqs+0x17c/0x1a0
pci_disable_msi+0xe4/0x118
hibmc_unload+0x44/0x80 [hibmc_drm]
hibmc_pci_remove+0x2c/0x38 [hibmc_drm]
pci_device_remove+0x48/0x108
device_release_driver_internal+0x118/0x1f0
driver_detach+0x6c/0xe0
bus_remove_driver+0x74/0x100
driver_unregister+0x34/0x60
pci_unregister_driver+0x24/0xd8
hibmc_pci_driver_exit+0x14/0xe768 [hibmc_drm]
__arm64_sys_delete_module+0x1fc/0x2d0
el0_svc_common.constprop.3+0xa8/0x188
do_el0_svc+0x80/0xa0
el0_sync_handler+0x8c/0xb0
el0_sync+0x15c/0x180
Code: f940b400 b4ffff00 a903e7b8 f90013b5 (d4210000)
---[ end trace 310d94ee8abef44f ]---
Kernel panic - not syncing: Oops - BUG: Fatal exception
Signed-off-by: Tian Tao <[email protected]>
---
drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
index e3ab765b..02f3bd1 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
@@ -251,6 +251,10 @@ static int hibmc_hw_init(struct hibmc_drm_private *priv)
static int hibmc_unload(struct drm_device *dev)
{
drm_atomic_helper_shutdown(dev);
+
+ if (dev->irq_enabled)
+ drm_irq_uninstall(dev);
+
pci_disable_msi(dev->pdev);
return 0;
@@ -286,7 +290,7 @@ static int hibmc_load(struct drm_device *dev)
if (ret) {
drm_warn(dev, "enabling MSI failed: %d\n", ret);
} else {
- ret = devm_drm_irq_install(dev, dev->pdev->irq);
+ ret = drm_irq_install(dev, dev->pdev->irq);
if (ret)
drm_warn(dev, "install irq failed: %d\n", ret);
}
--
2.7.4
Hi Tian
Am 15.12.20 um 04:01 schrieb Tian Tao:
> drm_irq_uninstall should be called before pci_disable_msi, if use
> devm_drm_irq_install to register the interrupt, the system will
> call pci_disable_msi first and then call drm_irq_uninstall, which
> will result in the following callstack.
>
> kernel BUG at drivers/pci/msi.c:376!
> Internal error: Oops - BUG: 0 [#1] SMP
> CPU: 93 PID: 173814 Comm: rmmod Tainted:
> pstate: a0400009 (NzCv daif +PAN -UAO -TCO BTYPE=--)
> pc : free_msi_irqs+0x17c/0x1a0
> lr : free_msi_irqs+0x16c/0x1a0
> sp : ffff2028157f7bd0
> x29: ffff2028157f7bd0 x28: ffff202849edab00
> x27: 0000000000000000 x26: 0000000000000000
> x25: 0000000000000000 x24: 0000000000000000
> x23: ffff0020851da000 x22: ffff0020851da2d8
> x21: ffff0020cc829000 x20: 0000000000000000
> x19: ffff0020d6714800 x18: 0000000000000010
> x17: 0000000000000000 x16: 0000000000000000
> x15: ffffffffffffffff x14: ffff2028957f77df
> x13: ffff2028157f77ed x12: 0000000000000000
> x11: 0000000000000040 x10: ffff800011b2f8e0
> x9 : ffff800011b2f8d8 x8 : ffff2020203fc458
> x7 : 0000000000000000 x6 : 0000000000000000
> x5 : ffff2020203fc430 x4 : ffff2020203fc4a0
> x3 : 0000000000000000 x2 : 0000000000000000
> x1 : 00000000000002c9 x0 : ffff0020d6719500
> Call trace:
> free_msi_irqs+0x17c/0x1a0
> pci_disable_msi+0xe4/0x118
> hibmc_unload+0x44/0x80 [hibmc_drm]
> hibmc_pci_remove+0x2c/0x38 [hibmc_drm]
> pci_device_remove+0x48/0x108
> device_release_driver_internal+0x118/0x1f0
> driver_detach+0x6c/0xe0
> bus_remove_driver+0x74/0x100
> driver_unregister+0x34/0x60
> pci_unregister_driver+0x24/0xd8
> hibmc_pci_driver_exit+0x14/0xe768 [hibmc_drm]
> __arm64_sys_delete_module+0x1fc/0x2d0
> el0_svc_common.constprop.3+0xa8/0x188
> do_el0_svc+0x80/0xa0
> el0_sync_handler+0x8c/0xb0
> el0_sync+0x15c/0x180
> Code: f940b400 b4ffff00 a903e7b8 f90013b5 (d4210000)
> ---[ end trace 310d94ee8abef44f ]---
> Kernel panic - not syncing: Oops - BUG: Fatal exception
>
> Signed-off-by: Tian Tao <[email protected]>
> ---
> drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c | 6 +++++-
> 1 file changed, 5 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
> index e3ab765b..02f3bd1 100644
> --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
> +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
> @@ -251,6 +251,10 @@ static int hibmc_hw_init(struct hibmc_drm_private *priv)
> static int hibmc_unload(struct drm_device *dev)
> {
> drm_atomic_helper_shutdown(dev);
> +
> + if (dev->irq_enabled)
> + drm_irq_uninstall(dev);
> +
> pci_disable_msi(dev->pdev);
We're trying to move towards managed driver releases; and this feels
like a step backwards.
I looked through the PCI-device release code in pcim_release() and it
already disables MSI automatically. [1] You can enable the PCI device
with pcim_enable_device() instead of pci_enable_device() to use the
automatic release. No more need to disable MSI manually.
If this does not work, could you provide a managed version of
pci_disable_msi() that solves the problem?
Best regards
Thomas
[1] https://elixir.bootlin.com/linux/latest/source/drivers/pci/pci.c#L1976
>
> return 0;
> @@ -286,7 +290,7 @@ static int hibmc_load(struct drm_device *dev)
> if (ret) {
> drm_warn(dev, "enabling MSI failed: %d\n", ret);
> } else {
> - ret = devm_drm_irq_install(dev, dev->pdev->irq);
> + ret = drm_irq_install(dev, dev->pdev->irq);
> if (ret)
> drm_warn(dev, "install irq failed: %d\n", ret);
> }
>
--
Thomas Zimmermann
Graphics Driver Developer
SUSE Software Solutions Germany GmbH
Maxfeldstr. 5, 90409 Nürnberg, Germany
(HRB 36809, AG Nürnberg)
Geschäftsführer: Felix Imendörffer
On Tue, Dec 15, 2020 at 12:59:53PM +0100, Daniel Vetter wrote:
> On Tue, Dec 15, 2020 at 11:01:39AM +0800, Tian Tao wrote:
> > drm_irq_uninstall should be called before pci_disable_msi, if use
> > devm_drm_irq_install to register the interrupt, the system will
> > call pci_disable_msi first and then call drm_irq_uninstall, which
> > will result in the following callstack.
> >
> > kernel BUG at drivers/pci/msi.c:376!
> > Internal error: Oops - BUG: 0 [#1] SMP
> > CPU: 93 PID: 173814 Comm: rmmod Tainted:
> > pstate: a0400009 (NzCv daif +PAN -UAO -TCO BTYPE=--)
> > pc : free_msi_irqs+0x17c/0x1a0
> > lr : free_msi_irqs+0x16c/0x1a0
> > sp : ffff2028157f7bd0
> > x29: ffff2028157f7bd0 x28: ffff202849edab00
> > x27: 0000000000000000 x26: 0000000000000000
> > x25: 0000000000000000 x24: 0000000000000000
> > x23: ffff0020851da000 x22: ffff0020851da2d8
> > x21: ffff0020cc829000 x20: 0000000000000000
> > x19: ffff0020d6714800 x18: 0000000000000010
> > x17: 0000000000000000 x16: 0000000000000000
> > x15: ffffffffffffffff x14: ffff2028957f77df
> > x13: ffff2028157f77ed x12: 0000000000000000
> > x11: 0000000000000040 x10: ffff800011b2f8e0
> > x9 : ffff800011b2f8d8 x8 : ffff2020203fc458
> > x7 : 0000000000000000 x6 : 0000000000000000
> > x5 : ffff2020203fc430 x4 : ffff2020203fc4a0
> > x3 : 0000000000000000 x2 : 0000000000000000
> > x1 : 00000000000002c9 x0 : ffff0020d6719500
> > Call trace:
> > free_msi_irqs+0x17c/0x1a0
> > pci_disable_msi+0xe4/0x118
> > hibmc_unload+0x44/0x80 [hibmc_drm]
> > hibmc_pci_remove+0x2c/0x38 [hibmc_drm]
> > pci_device_remove+0x48/0x108
> > device_release_driver_internal+0x118/0x1f0
> > driver_detach+0x6c/0xe0
> > bus_remove_driver+0x74/0x100
> > driver_unregister+0x34/0x60
> > pci_unregister_driver+0x24/0xd8
> > hibmc_pci_driver_exit+0x14/0xe768 [hibmc_drm]
> > __arm64_sys_delete_module+0x1fc/0x2d0
> > el0_svc_common.constprop.3+0xa8/0x188
> > do_el0_svc+0x80/0xa0
> > el0_sync_handler+0x8c/0xb0
> > el0_sync+0x15c/0x180
> > Code: f940b400 b4ffff00 a903e7b8 f90013b5 (d4210000)
> > ---[ end trace 310d94ee8abef44f ]---
> > Kernel panic - not syncing: Oops - BUG: Fatal exception
> >
>
> You should mention here which patch you're reverting. With that:
>
> Acked-by: Daniel Vetter <[email protected]>
>
> Since the proper fix will probably take a while longer. Also why was this
> not noticed when merging the original patch? hisilicon is the only user of
> devm_drm_irq_install we have in-tree right now.
I also just noticed that you didn't add devm_drm_irq_install to the list
of functions in Documentation/driver-api/driver-model/devres.rst. Can you
please submit a patch to fix this?
Thanks, Daniel
> -Daniel
>
> > Signed-off-by: Tian Tao <[email protected]>
> > ---
> > drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c | 6 +++++-
> > 1 file changed, 5 insertions(+), 1 deletion(-)
> >
> > diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
> > index e3ab765b..02f3bd1 100644
> > --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
> > +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
> > @@ -251,6 +251,10 @@ static int hibmc_hw_init(struct hibmc_drm_private *priv)
> > static int hibmc_unload(struct drm_device *dev)
> > {
> > drm_atomic_helper_shutdown(dev);
> > +
> > + if (dev->irq_enabled)
> > + drm_irq_uninstall(dev);
> > +
> > pci_disable_msi(dev->pdev);
> >
> > return 0;
> > @@ -286,7 +290,7 @@ static int hibmc_load(struct drm_device *dev)
> > if (ret) {
> > drm_warn(dev, "enabling MSI failed: %d\n", ret);
> > } else {
> > - ret = devm_drm_irq_install(dev, dev->pdev->irq);
> > + ret = drm_irq_install(dev, dev->pdev->irq);
> > if (ret)
> > drm_warn(dev, "install irq failed: %d\n", ret);
> > }
> > --
> > 2.7.4
> >
>
> --
> Daniel Vetter
> Software Engineer, Intel Corporation
> http://blog.ffwll.ch
--
Daniel Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch
?? 2020/12/15 20:01, Daniel Vetter д??:
> On Tue, Dec 15, 2020 at 12:59:53PM +0100, Daniel Vetter wrote:
>> On Tue, Dec 15, 2020 at 11:01:39AM +0800, Tian Tao wrote:
>>> drm_irq_uninstall should be called before pci_disable_msi, if use
>>> devm_drm_irq_install to register the interrupt, the system will
>>> call pci_disable_msi first and then call drm_irq_uninstall, which
>>> will result in the following callstack.
>>>
>>> kernel BUG at drivers/pci/msi.c:376!
>>> Internal error: Oops - BUG: 0 [#1] SMP
>>> CPU: 93 PID: 173814 Comm: rmmod Tainted:
>>> pstate: a0400009 (NzCv daif +PAN -UAO -TCO BTYPE=--)
>>> pc : free_msi_irqs+0x17c/0x1a0
>>> lr : free_msi_irqs+0x16c/0x1a0
>>> sp : ffff2028157f7bd0
>>> x29: ffff2028157f7bd0 x28: ffff202849edab00
>>> x27: 0000000000000000 x26: 0000000000000000
>>> x25: 0000000000000000 x24: 0000000000000000
>>> x23: ffff0020851da000 x22: ffff0020851da2d8
>>> x21: ffff0020cc829000 x20: 0000000000000000
>>> x19: ffff0020d6714800 x18: 0000000000000010
>>> x17: 0000000000000000 x16: 0000000000000000
>>> x15: ffffffffffffffff x14: ffff2028957f77df
>>> x13: ffff2028157f77ed x12: 0000000000000000
>>> x11: 0000000000000040 x10: ffff800011b2f8e0
>>> x9 : ffff800011b2f8d8 x8 : ffff2020203fc458
>>> x7 : 0000000000000000 x6 : 0000000000000000
>>> x5 : ffff2020203fc430 x4 : ffff2020203fc4a0
>>> x3 : 0000000000000000 x2 : 0000000000000000
>>> x1 : 00000000000002c9 x0 : ffff0020d6719500
>>> Call trace:
>>> free_msi_irqs+0x17c/0x1a0
>>> pci_disable_msi+0xe4/0x118
>>> hibmc_unload+0x44/0x80 [hibmc_drm]
>>> hibmc_pci_remove+0x2c/0x38 [hibmc_drm]
>>> pci_device_remove+0x48/0x108
>>> device_release_driver_internal+0x118/0x1f0
>>> driver_detach+0x6c/0xe0
>>> bus_remove_driver+0x74/0x100
>>> driver_unregister+0x34/0x60
>>> pci_unregister_driver+0x24/0xd8
>>> hibmc_pci_driver_exit+0x14/0xe768 [hibmc_drm]
>>> __arm64_sys_delete_module+0x1fc/0x2d0
>>> el0_svc_common.constprop.3+0xa8/0x188
>>> do_el0_svc+0x80/0xa0
>>> el0_sync_handler+0x8c/0xb0
>>> el0_sync+0x15c/0x180
>>> Code: f940b400 b4ffff00 a903e7b8 f90013b5 (d4210000)
>>> ---[ end trace 310d94ee8abef44f ]---
>>> Kernel panic - not syncing: Oops - BUG: Fatal exception
>>>
>> You should mention here which patch you're reverting. With that:
>>
>> Acked-by: Daniel Vetter <[email protected]>
>>
>> Since the proper fix will probably take a while longer. Also why was this
>> not noticed when merging the original patch? hisilicon is the only user of
>> devm_drm_irq_install we have in-tree right now.
> I also just noticed that you didn't add devm_drm_irq_install to the list
> of functions in Documentation/driver-api/driver-model/devres.rst. Can you
> please submit a patch to fix this?
sure
>
> Thanks, Daniel
>
>> -Daniel
>>
>>> Signed-off-by: Tian Tao <[email protected]>
>>> ---
>>> drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c | 6 +++++-
>>> 1 file changed, 5 insertions(+), 1 deletion(-)
>>>
>>> diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
>>> index e3ab765b..02f3bd1 100644
>>> --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
>>> +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
>>> @@ -251,6 +251,10 @@ static int hibmc_hw_init(struct hibmc_drm_private *priv)
>>> static int hibmc_unload(struct drm_device *dev)
>>> {
>>> drm_atomic_helper_shutdown(dev);
>>> +
>>> + if (dev->irq_enabled)
>>> + drm_irq_uninstall(dev);
>>> +
>>> pci_disable_msi(dev->pdev);
>>>
>>> return 0;
>>> @@ -286,7 +290,7 @@ static int hibmc_load(struct drm_device *dev)
>>> if (ret) {
>>> drm_warn(dev, "enabling MSI failed: %d\n", ret);
>>> } else {
>>> - ret = devm_drm_irq_install(dev, dev->pdev->irq);
>>> + ret = drm_irq_install(dev, dev->pdev->irq);
>>> if (ret)
>>> drm_warn(dev, "install irq failed: %d\n", ret);
>>> }
>>> --
>>> 2.7.4
>>>
>> --
>> Daniel Vetter
>> Software Engineer, Intel Corporation
>> http://blog.ffwll.ch
On Tue, Dec 15, 2020 at 11:01:39AM +0800, Tian Tao wrote:
> drm_irq_uninstall should be called before pci_disable_msi, if use
> devm_drm_irq_install to register the interrupt, the system will
> call pci_disable_msi first and then call drm_irq_uninstall, which
> will result in the following callstack.
>
> kernel BUG at drivers/pci/msi.c:376!
> Internal error: Oops - BUG: 0 [#1] SMP
> CPU: 93 PID: 173814 Comm: rmmod Tainted:
> pstate: a0400009 (NzCv daif +PAN -UAO -TCO BTYPE=--)
> pc : free_msi_irqs+0x17c/0x1a0
> lr : free_msi_irqs+0x16c/0x1a0
> sp : ffff2028157f7bd0
> x29: ffff2028157f7bd0 x28: ffff202849edab00
> x27: 0000000000000000 x26: 0000000000000000
> x25: 0000000000000000 x24: 0000000000000000
> x23: ffff0020851da000 x22: ffff0020851da2d8
> x21: ffff0020cc829000 x20: 0000000000000000
> x19: ffff0020d6714800 x18: 0000000000000010
> x17: 0000000000000000 x16: 0000000000000000
> x15: ffffffffffffffff x14: ffff2028957f77df
> x13: ffff2028157f77ed x12: 0000000000000000
> x11: 0000000000000040 x10: ffff800011b2f8e0
> x9 : ffff800011b2f8d8 x8 : ffff2020203fc458
> x7 : 0000000000000000 x6 : 0000000000000000
> x5 : ffff2020203fc430 x4 : ffff2020203fc4a0
> x3 : 0000000000000000 x2 : 0000000000000000
> x1 : 00000000000002c9 x0 : ffff0020d6719500
> Call trace:
> free_msi_irqs+0x17c/0x1a0
> pci_disable_msi+0xe4/0x118
> hibmc_unload+0x44/0x80 [hibmc_drm]
> hibmc_pci_remove+0x2c/0x38 [hibmc_drm]
> pci_device_remove+0x48/0x108
> device_release_driver_internal+0x118/0x1f0
> driver_detach+0x6c/0xe0
> bus_remove_driver+0x74/0x100
> driver_unregister+0x34/0x60
> pci_unregister_driver+0x24/0xd8
> hibmc_pci_driver_exit+0x14/0xe768 [hibmc_drm]
> __arm64_sys_delete_module+0x1fc/0x2d0
> el0_svc_common.constprop.3+0xa8/0x188
> do_el0_svc+0x80/0xa0
> el0_sync_handler+0x8c/0xb0
> el0_sync+0x15c/0x180
> Code: f940b400 b4ffff00 a903e7b8 f90013b5 (d4210000)
> ---[ end trace 310d94ee8abef44f ]---
> Kernel panic - not syncing: Oops - BUG: Fatal exception
>
You should mention here which patch you're reverting. With that:
Acked-by: Daniel Vetter <[email protected]>
Since the proper fix will probably take a while longer. Also why was this
not noticed when merging the original patch? hisilicon is the only user of
devm_drm_irq_install we have in-tree right now.
-Daniel
> Signed-off-by: Tian Tao <[email protected]>
> ---
> drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c | 6 +++++-
> 1 file changed, 5 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
> index e3ab765b..02f3bd1 100644
> --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
> +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
> @@ -251,6 +251,10 @@ static int hibmc_hw_init(struct hibmc_drm_private *priv)
> static int hibmc_unload(struct drm_device *dev)
> {
> drm_atomic_helper_shutdown(dev);
> +
> + if (dev->irq_enabled)
> + drm_irq_uninstall(dev);
> +
> pci_disable_msi(dev->pdev);
>
> return 0;
> @@ -286,7 +290,7 @@ static int hibmc_load(struct drm_device *dev)
> if (ret) {
> drm_warn(dev, "enabling MSI failed: %d\n", ret);
> } else {
> - ret = devm_drm_irq_install(dev, dev->pdev->irq);
> + ret = drm_irq_install(dev, dev->pdev->irq);
> if (ret)
> drm_warn(dev, "install irq failed: %d\n", ret);
> }
> --
> 2.7.4
>
--
Daniel Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch