[PATCH 1/2] accel/amdxdna: use modern PM helpers

[PATCH 1/2] accel/amdxdna: use modern PM helpers

[Arnd Bergmann]

From: Arnd Bergmann <arnd@arndb.de>

The old SET_SYSTEM_SLEEP_PM_OPS and SET_RUNTIME_PM_OPS macros cause a build
warning when CONFIG_PM is disabled:

drivers/accel/amdxdna/amdxdna_pci_drv.c:343:12: error: 'amdxdna_pmops_resume' defined but not used [-Werror=unused-function]
  343 | static int amdxdna_pmops_resume(struct device *dev)
      |            ^~~~~~~~~~~~~~~~~~~~
drivers/accel/amdxdna/amdxdna_pci_drv.c:328:12: error: 'amdxdna_pmops_suspend' defined but not used [-Werror=unused-function]
  328 | static int amdxdna_pmops_suspend(struct device *dev)
      |            ^~~~~~~~~~~~~~~~~~~~~

Change these to the modern replacements.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 drivers/accel/amdxdna/amdxdna_pci_drv.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.c b/drivers/accel/amdxdna/amdxdna_pci_drv.c
index 02533732d4ca..b2342abdddc6 100644
--- a/drivers/accel/amdxdna/amdxdna_pci_drv.c
+++ b/drivers/accel/amdxdna/amdxdna_pci_drv.c
@@ -390,8 +390,8 @@ static int amdxdna_rpmops_resume(struct device *dev)
 }
 
 static const struct dev_pm_ops amdxdna_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(amdxdna_pmops_suspend, amdxdna_pmops_resume)
-	SET_RUNTIME_PM_OPS(amdxdna_rpmops_suspend, amdxdna_rpmops_resume, NULL)
+	SYSTEM_SLEEP_PM_OPS(amdxdna_pmops_suspend, amdxdna_pmops_resume)
+	RUNTIME_PM_OPS(amdxdna_rpmops_suspend, amdxdna_rpmops_resume, NULL)
 };
 
 static struct pci_driver amdxdna_pci_driver = {
-- 
2.39.5

[PATCH 2/2] accel/amdxdna: add missing includes

[Arnd Bergmann]

From: Arnd Bergmann <arnd@arndb.de>

This driver fails to build in random configurations:

drivers/accel/amdxdna/amdxdna_mailbox.c:357:8: error: unknown type name 'irqreturn_t'
  357 | static irqreturn_t mailbox_irq_handler(int irq, void *p)
      |        ^~~~~~~~~~~
drivers/accel/amdxdna/amdxdna_mailbox.c: In function 'mailbox_irq_handler':
drivers/accel/amdxdna/amdxdna_mailbox.c:367:16: error: 'IRQ_HANDLED' undeclared (first use in this function)
  367 |         return IRQ_HANDLED;
      |                ^~~~~~~~~~~
drivers/accel/amdxdna/amdxdna_mailbox.c:367:16: note: each undeclared identifier is reported only once for each function it appears in
drivers/accel/amdxdna/amdxdna_mailbox.c: In function 'mailbox_rx_worker':
drivers/accel/amdxdna/amdxdna_mailbox.c:395:25: error: implicit declaration of function 'disable_irq'; did you mean 'disable_work'? [-Wimplicit-function-declaration]
  395 |                         disable_irq(mb_chann->msix_irq);
      |                         ^~~~~~~~~~~
drivers/accel/amdxdna/aie2_solver.c: In function 'remove_partition_node':
drivers/accel/amdxdna/aie2_solver.c:121:9: error: implicit declaration of function 'kfree' [-Wimplicit-function-declaration]
  121 |         kfree(pt_node);
      |         ^~~~~
drivers/accel/amdxdna/aie2_solver.c: In function 'get_free_partition':
drivers/accel/amdxdna/aie2_solver.c:153:19: error: implicit declaration of function 'kzalloc' [-Wimplicit-function-declaration]
  153 |         pt_node = kzalloc(sizeof(*pt_node), GFP_KERNEL);

Include the headers that have the necessary declarations.

Fixes: c88d3325ae69 ("accel/amdxdna: Add hardware resource solver")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>

amdxdna: includ linux/interrupt.h

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 drivers/accel/amdxdna/aie2_solver.c     | 1 +
 drivers/accel/amdxdna/amdxdna_mailbox.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/accel/amdxdna/aie2_solver.c b/drivers/accel/amdxdna/aie2_solver.c
index a537c66589a4..0bbf91cad334 100644
--- a/drivers/accel/amdxdna/aie2_solver.c
+++ b/drivers/accel/amdxdna/aie2_solver.c
@@ -8,6 +8,7 @@
 #include <drm/drm_print.h>
 #include <linux/bitops.h>
 #include <linux/bitmap.h>
+#include <linux/slab.h>
 
 #include "aie2_solver.h"
 
diff --git a/drivers/accel/amdxdna/amdxdna_mailbox.c b/drivers/accel/amdxdna/amdxdna_mailbox.c
index 415d99abaaa3..41bbc5796e11 100644
--- a/drivers/accel/amdxdna/amdxdna_mailbox.c
+++ b/drivers/accel/amdxdna/amdxdna_mailbox.c
@@ -7,6 +7,7 @@
 #include <drm/drm_managed.h>
 #include <linux/bitfield.h>
 #include <linux/iopoll.h>
+#include <linux/interrupt.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/amdxdna.h>
-- 
2.39.5

Re: [PATCH 1/2] accel/amdxdna: use modern PM helpers

[Jeffrey Hugo]

On 12/13/2024 2:02 AM, Arnd Bergmann wrote:
> From: Arnd Bergmann <arnd@arndb.de>
> 
> The old SET_SYSTEM_SLEEP_PM_OPS and SET_RUNTIME_PM_OPS macros cause a build
> warning when CONFIG_PM is disabled:
> 
> drivers/accel/amdxdna/amdxdna_pci_drv.c:343:12: error: 'amdxdna_pmops_resume' defined but not used [-Werror=unused-function]
>    343 | static int amdxdna_pmops_resume(struct device *dev)
>        |            ^~~~~~~~~~~~~~~~~~~~
> drivers/accel/amdxdna/amdxdna_pci_drv.c:328:12: error: 'amdxdna_pmops_suspend' defined but not used [-Werror=unused-function]
>    328 | static int amdxdna_pmops_suspend(struct device *dev)
>        |            ^~~~~~~~~~~~~~~~~~~~~
> 
> Change these to the modern replacements.
> 
> Signed-off-by: Arnd Bergmann <arnd@arndb.de>

Looks sane to me.

Lizhi, can you verify that this works as expected for you?  I'd hate to 
accidentally break something.

-Jeff

Re: [PATCH 2/2] accel/amdxdna: add missing includes

[Jeffrey Hugo]

On 12/13/2024 2:02 AM, Arnd Bergmann wrote:
> From: Arnd Bergmann <arnd@arndb.de>
> 
> This driver fails to build in random configurations:
> 
> drivers/accel/amdxdna/amdxdna_mailbox.c:357:8: error: unknown type name 'irqreturn_t'
>    357 | static irqreturn_t mailbox_irq_handler(int irq, void *p)
>        |        ^~~~~~~~~~~
> drivers/accel/amdxdna/amdxdna_mailbox.c: In function 'mailbox_irq_handler':
> drivers/accel/amdxdna/amdxdna_mailbox.c:367:16: error: 'IRQ_HANDLED' undeclared (first use in this function)
>    367 |         return IRQ_HANDLED;
>        |                ^~~~~~~~~~~
> drivers/accel/amdxdna/amdxdna_mailbox.c:367:16: note: each undeclared identifier is reported only once for each function it appears in
> drivers/accel/amdxdna/amdxdna_mailbox.c: In function 'mailbox_rx_worker':
> drivers/accel/amdxdna/amdxdna_mailbox.c:395:25: error: implicit declaration of function 'disable_irq'; did you mean 'disable_work'? [-Wimplicit-function-declaration]
>    395 |                         disable_irq(mb_chann->msix_irq);
>        |                         ^~~~~~~~~~~
> drivers/accel/amdxdna/aie2_solver.c: In function 'remove_partition_node':
> drivers/accel/amdxdna/aie2_solver.c:121:9: error: implicit declaration of function 'kfree' [-Wimplicit-function-declaration]
>    121 |         kfree(pt_node);
>        |         ^~~~~
> drivers/accel/amdxdna/aie2_solver.c: In function 'get_free_partition':
> drivers/accel/amdxdna/aie2_solver.c:153:19: error: implicit declaration of function 'kzalloc' [-Wimplicit-function-declaration]
>    153 |         pt_node = kzalloc(sizeof(*pt_node), GFP_KERNEL);
> 
> Include the headers that have the necessary declarations.
> 
> Fixes: c88d3325ae69 ("accel/amdxdna: Add hardware resource solver")
> Signed-off-by: Arnd Bergmann <arnd@arndb.de>
> 
> amdxdna: includ linux/interrupt.h
> 
> Signed-off-by: Arnd Bergmann <arnd@arndb.de>

The interrupt part of this is now fixed, see "accel/amdxdna: Add include 
interrupt.h to amdxdna_mailbox.c".

The slab portion looks sane. I'll trim the patch when applying unless 
you'd prefer something else.

Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>

Re: [PATCH 1/2] accel/amdxdna: use modern PM helpers

[Lizhi Hou]

On 12/13/24 09:07, Jeffrey Hugo wrote:
> On 12/13/2024 2:02 AM, Arnd Bergmann wrote:
>> From: Arnd Bergmann <arnd@arndb.de>
>>
>> The old SET_SYSTEM_SLEEP_PM_OPS and SET_RUNTIME_PM_OPS macros cause a 
>> build
>> warning when CONFIG_PM is disabled:
>>
>> drivers/accel/amdxdna/amdxdna_pci_drv.c:343:12: error: 
>> 'amdxdna_pmops_resume' defined but not used [-Werror=unused-function]
>>    343 | static int amdxdna_pmops_resume(struct device *dev)
>>        |            ^~~~~~~~~~~~~~~~~~~~
>> drivers/accel/amdxdna/amdxdna_pci_drv.c:328:12: error: 
>> 'amdxdna_pmops_suspend' defined but not used [-Werror=unused-function]
>>    328 | static int amdxdna_pmops_suspend(struct device *dev)
>>        |            ^~~~~~~~~~~~~~~~~~~~~
>>
>> Change these to the modern replacements.
>>
>> Signed-off-by: Arnd Bergmann <arnd@arndb.de>
>
> Looks sane to me.
>
> Lizhi, can you verify that this works as expected for you?  I'd hate 
> to accidentally break something.

Verified suspend/resume. It works fine.


Lizhi

>
> -Jeff
>

Re: [PATCH 1/2] accel/amdxdna: use modern PM helpers

[Jeffrey Hugo]

On 12/13/2024 10:41 AM, Lizhi Hou wrote:
> 
> On 12/13/24 09:07, Jeffrey Hugo wrote:
>> On 12/13/2024 2:02 AM, Arnd Bergmann wrote:
>>> From: Arnd Bergmann <arnd@arndb.de>
>>>
>>> The old SET_SYSTEM_SLEEP_PM_OPS and SET_RUNTIME_PM_OPS macros cause a 
>>> build
>>> warning when CONFIG_PM is disabled:
>>>
>>> drivers/accel/amdxdna/amdxdna_pci_drv.c:343:12: error: 
>>> 'amdxdna_pmops_resume' defined but not used [-Werror=unused-function]
>>>    343 | static int amdxdna_pmops_resume(struct device *dev)
>>>        |            ^~~~~~~~~~~~~~~~~~~~
>>> drivers/accel/amdxdna/amdxdna_pci_drv.c:328:12: error: 
>>> 'amdxdna_pmops_suspend' defined but not used [-Werror=unused-function]
>>>    328 | static int amdxdna_pmops_suspend(struct device *dev)
>>>        |            ^~~~~~~~~~~~~~~~~~~~~
>>>
>>> Change these to the modern replacements.
>>>
>>> Signed-off-by: Arnd Bergmann <arnd@arndb.de>
>>
>> Looks sane to me.
>>
>> Lizhi, can you verify that this works as expected for you?  I'd hate 
>> to accidentally break something.
> 
> Verified suspend/resume. It works fine.

Excellent.  Would you like to give a reviewed-by and/or a tested-by?

-Jeff

Re: [PATCH 1/2] accel/amdxdna: use modern PM helpers

[Lizhi Hou]

On 12/13/24 09:49, Jeffrey Hugo wrote:
> On 12/13/2024 10:41 AM, Lizhi Hou wrote:
>>
>> On 12/13/24 09:07, Jeffrey Hugo wrote:
>>> On 12/13/2024 2:02 AM, Arnd Bergmann wrote:
>>>> From: Arnd Bergmann <arnd@arndb.de>
>>>>
>>>> The old SET_SYSTEM_SLEEP_PM_OPS and SET_RUNTIME_PM_OPS macros cause 
>>>> a build
>>>> warning when CONFIG_PM is disabled:
>>>>
>>>> drivers/accel/amdxdna/amdxdna_pci_drv.c:343:12: error: 
>>>> 'amdxdna_pmops_resume' defined but not used [-Werror=unused-function]
>>>>    343 | static int amdxdna_pmops_resume(struct device *dev)
>>>>        |            ^~~~~~~~~~~~~~~~~~~~
>>>> drivers/accel/amdxdna/amdxdna_pci_drv.c:328:12: error: 
>>>> 'amdxdna_pmops_suspend' defined but not used [-Werror=unused-function]
>>>>    328 | static int amdxdna_pmops_suspend(struct device *dev)
>>>>        |            ^~~~~~~~~~~~~~~~~~~~~
>>>>
>>>> Change these to the modern replacements.
>>>>
>>>> Signed-off-by: Arnd Bergmann <arnd@arndb.de>
>>>
>>> Looks sane to me.
>>>
>>> Lizhi, can you verify that this works as expected for you? I'd hate 
>>> to accidentally break something.
>>
>> Verified suspend/resume. It works fine.
>
> Excellent.  Would you like to give a reviewed-by and/or a tested-by?

Reviewed-by: Lizhi Hou <lizhi.hou@amd.com>

Tested-by: Lizhi Hou <lizhi.hou@amd.com>

>
> -Jeff
>

Re: [PATCH 1/2] accel/amdxdna: use modern PM helpers

[Jeffrey Hugo]

On 12/13/2024 10:57 AM, Lizhi Hou wrote:
> 
> On 12/13/24 09:49, Jeffrey Hugo wrote:
>> On 12/13/2024 10:41 AM, Lizhi Hou wrote:
>>>
>>> On 12/13/24 09:07, Jeffrey Hugo wrote:
>>>> On 12/13/2024 2:02 AM, Arnd Bergmann wrote:
>>>>> From: Arnd Bergmann <arnd@arndb.de>
>>>>>
>>>>> The old SET_SYSTEM_SLEEP_PM_OPS and SET_RUNTIME_PM_OPS macros cause 
>>>>> a build
>>>>> warning when CONFIG_PM is disabled:
>>>>>
>>>>> drivers/accel/amdxdna/amdxdna_pci_drv.c:343:12: error: 
>>>>> 'amdxdna_pmops_resume' defined but not used [-Werror=unused-function]
>>>>>    343 | static int amdxdna_pmops_resume(struct device *dev)
>>>>>        |            ^~~~~~~~~~~~~~~~~~~~
>>>>> drivers/accel/amdxdna/amdxdna_pci_drv.c:328:12: error: 
>>>>> 'amdxdna_pmops_suspend' defined but not used [-Werror=unused-function]
>>>>>    328 | static int amdxdna_pmops_suspend(struct device *dev)
>>>>>        |            ^~~~~~~~~~~~~~~~~~~~~
>>>>>
>>>>> Change these to the modern replacements.
>>>>>
>>>>> Signed-off-by: Arnd Bergmann <arnd@arndb.de>
>>>>
>>>> Looks sane to me.
>>>>
>>>> Lizhi, can you verify that this works as expected for you? I'd hate 
>>>> to accidentally break something.
>>>
>>> Verified suspend/resume. It works fine.
>>
>> Excellent.  Would you like to give a reviewed-by and/or a tested-by?
> 
> Reviewed-by: Lizhi Hou <lizhi.hou@amd.com>
> 
> Tested-by: Lizhi Hou <lizhi.hou@amd.com>

Thanks!

Pushed to drm-misc-next

-Jeff