diff mbox

[v3,3/3] dmaengine: mpc512x: initialize with subsys_initcall()

Message ID 1443115737-3948-4-git-send-email-alex.popov@linux.com (mailing list archive)
State Changes Requested
Delegated to: Anatolij Gustschin
Headers show

Commit Message

Alexander Popov Sept. 24, 2015, 5:28 p.m. UTC 
Initialize Freescale MPC512x DMA driver with subsys_initcall()
to allow the depending drivers to call dma_request_slave_channel()
during their probe.

Signed-off-by: Alexander Popov <alex.popov@linux.com>
---
 drivers/dma/mpc512x_dma.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

Comments

Timur Tabi Sept. 25, 2015, 12:16 a.m. UTC | #1 
Alexander Popov wrote:
> Initialize Freescale MPC512x DMA driver with subsys_initcall()
> to allow the depending drivers to call dma_request_slave_channel()
> during their probe.
>
> Signed-off-by: Alexander Popov<alex.popov@linux.com>

Is there any way we can use -EPROBEDEFER instead?
Alexander Popov Sept. 28, 2015, 1:15 p.m. UTC | #2 
On 25.09.2015 03:16, Timur Tabi wrote:
> Alexander Popov wrote:
>> Initialize Freescale MPC512x DMA driver with subsys_initcall()
>> to allow the depending drivers to call dma_request_slave_channel()
>> during their probe.
>>
>> Signed-off-by: Alexander Popov<alex.popov@linux.com>
> 
> Is there any way we can use -EPROBEDEFER instead?

Thanks Timur, I'll try.

Best regards,
Alexander
Vinod Koul Oct. 7, 2015, 2:17 p.m. UTC | #3 
On Thu, Sep 24, 2015 at 08:28:57PM +0300, Alexander Popov wrote:
> Initialize Freescale MPC512x DMA driver with subsys_initcall()
> to allow the depending drivers to call dma_request_slave_channel()
> during their probe.

Why can't we use defered probe ? I have been asking people to not move init
levels and esnure we have right solutions using defered probe
Alexander Popov Oct. 7, 2015, 9:31 p.m. UTC | #4 
On 07.10.2015 17:17, Vinod Koul wrote:
> On Thu, Sep 24, 2015 at 08:28:57PM +0300, Alexander Popov wrote:
>> Initialize Freescale MPC512x DMA driver with subsys_initcall()
>> to allow the depending drivers to call dma_request_slave_channel()
>> during their probe.
> 
> Why can't we use defered probe ? I have been asking people to not move init
> levels and esnure we have right solutions using defered probe

Thanks, Vinod, I'll do it in v4.

Best regards,
Alexander
diff mbox

Patch

diff --git a/drivers/dma/mpc512x_dma.c b/drivers/dma/mpc512x_dma.c
index e6281e7..4f29d7c 100644
--- a/drivers/dma/mpc512x_dma.c
+++ b/drivers/dma/mpc512x_dma.c
@@ -1083,7 +1083,17 @@  static struct platform_driver mpc_dma_driver = {
 	},
 };
 
-module_platform_driver(mpc_dma_driver);
+static int __init mpc_dma_driver_init(void)
+{
+	return platform_driver_register(&mpc_dma_driver);
+}
+subsys_initcall(mpc_dma_driver_init);
+
+static void __exit mpc_dma_driver_exit(void)
+{
+	platform_driver_unregister(&mpc_dma_driver);
+}
+module_exit(mpc_dma_driver_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Piotr Ziecik <kosmo@semihalf.com>");