mbox series

[0/2] phy: ti-pipe3: Update PCIe PHY settings

Message ID 20171009090338.26033-1-kishon@ti.com
Headers show
Series phy: ti-pipe3: Update PCIe PHY settings | expand

Message

Kishon Vijay Abraham I Oct. 9, 2017, 9:03 a.m. UTC
This was supposed to only update ti-pipe3 PHY registers. However because
of the way the ti-pipe3 PHY, OCP2SCP and PCIe controller are connected
in dra7xx where

PCIe controller --------------> ti-pipe3 PHY --------------> OCP2SCP
		  depends on		       depends on

updating ti-pipe3 PHY registers results in an abort.

Though the dependency between ti-pipe3 PHY and OCP2SCP is created
(OCP2SCP is parent of ti-pipe3 PHY), and enabling ti-pipe3 PHY clocks
should in turn enable OCP2SCP (with the help of pm_runtime framework),
this doesn't work in no_irq stage since pm_runtime is disabled during
no_irq stage. Since pci-dra7xx enables/initializes ti-pipe3 phy in
no_irq stage, OCP2SCP is not enabled resulting in an abort with ti-pipe3
PHY registers are accessed.

In order to solve this a functional dependency is created between
PCIe and ti-pipe3 PHY so that PCIe is suspended before PHY/OCP2SCP
and resumed after PCIe PHY/OCP2SCP

Kishon Vijay Abraham I (2):
  PCI: dwc: dra7xx: Create functional dependency between PCIe and PHY
  phy: ti-pipe3: Update pcie phy settings

 drivers/pci/dwc/pci-dra7xx.c  |  16 +++++++
 drivers/phy/ti/phy-ti-pipe3.c | 101 +++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 116 insertions(+), 1 deletion(-)

Comments

Bjorn Helgaas Oct. 17, 2017, 7:31 p.m. UTC | #1
On Mon, Oct 09, 2017 at 02:33:36PM +0530, Kishon Vijay Abraham I wrote:
> This was supposed to only update ti-pipe3 PHY registers. However because
> of the way the ti-pipe3 PHY, OCP2SCP and PCIe controller are connected
> in dra7xx where
> 
> PCIe controller --------------> ti-pipe3 PHY --------------> OCP2SCP
> 		  depends on		       depends on
> 
> updating ti-pipe3 PHY registers results in an abort.
> 
> Though the dependency between ti-pipe3 PHY and OCP2SCP is created
> (OCP2SCP is parent of ti-pipe3 PHY), and enabling ti-pipe3 PHY clocks
> should in turn enable OCP2SCP (with the help of pm_runtime framework),
> this doesn't work in no_irq stage since pm_runtime is disabled during
> no_irq stage. Since pci-dra7xx enables/initializes ti-pipe3 phy in
> no_irq stage, OCP2SCP is not enabled resulting in an abort with ti-pipe3
> PHY registers are accessed.
> 
> In order to solve this a functional dependency is created between
> PCIe and ti-pipe3 PHY so that PCIe is suspended before PHY/OCP2SCP
> and resumed after PCIe PHY/OCP2SCP
> 
> Kishon Vijay Abraham I (2):
>   PCI: dwc: dra7xx: Create functional dependency between PCIe and PHY

s/PCI: dwc: dra7xx: Create functional dependency between PCIe and PHY/
  PCI: dra7xx: Create functional dependency between PCIe and PHY/

Should these be merged together?  If it makes sense for you to merge them
together, here's my ack for the PCI piece:

Acked-by: Bjorn Helgaas <bhelgaas@google.com>

Let me know if you'd like me to take one or both of them.

>   phy: ti-pipe3: Update pcie phy settings
> 
>  drivers/pci/dwc/pci-dra7xx.c  |  16 +++++++
>  drivers/phy/ti/phy-ti-pipe3.c | 101 +++++++++++++++++++++++++++++++++++++++++-
>  2 files changed, 116 insertions(+), 1 deletion(-)
> 
> -- 
> 2.11.0
>
Kishon Vijay Abraham I Oct. 18, 2017, 12:08 p.m. UTC | #2
On Wednesday 18 October 2017 01:01 AM, Bjorn Helgaas wrote:
> On Mon, Oct 09, 2017 at 02:33:36PM +0530, Kishon Vijay Abraham I wrote:
>> This was supposed to only update ti-pipe3 PHY registers. However because
>> of the way the ti-pipe3 PHY, OCP2SCP and PCIe controller are connected
>> in dra7xx where
>>
>> PCIe controller --------------> ti-pipe3 PHY --------------> OCP2SCP
>> 		  depends on		       depends on
>>
>> updating ti-pipe3 PHY registers results in an abort.
>>
>> Though the dependency between ti-pipe3 PHY and OCP2SCP is created
>> (OCP2SCP is parent of ti-pipe3 PHY), and enabling ti-pipe3 PHY clocks
>> should in turn enable OCP2SCP (with the help of pm_runtime framework),
>> this doesn't work in no_irq stage since pm_runtime is disabled during
>> no_irq stage. Since pci-dra7xx enables/initializes ti-pipe3 phy in
>> no_irq stage, OCP2SCP is not enabled resulting in an abort with ti-pipe3
>> PHY registers are accessed.
>>
>> In order to solve this a functional dependency is created between
>> PCIe and ti-pipe3 PHY so that PCIe is suspended before PHY/OCP2SCP
>> and resumed after PCIe PHY/OCP2SCP
>>
>> Kishon Vijay Abraham I (2):
>>   PCI: dwc: dra7xx: Create functional dependency between PCIe and PHY
> 
> s/PCI: dwc: dra7xx: Create functional dependency between PCIe and PHY/
>   PCI: dra7xx: Create functional dependency between PCIe and PHY/
> 
> Should these be merged together?  If it makes sense for you to merge them
> together, here's my ack for the PCI piece:
> 
> Acked-by: Bjorn Helgaas <bhelgaas@google.com>

Yeah both should be merged together. I'll make the change you suggested, add
your Ack and merge myself.

Thanks
Kishon