| Message ID | 20240117160748.37682-5-brgl@bgdev.pl |
|---|---|
| State | New |
| Headers | show |
| Series | PCI: introduce the concept of power sequencing of PCIe devices | expand |
Bartosz Golaszewski wrote: > From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org> > > In order to introduce PCI power-sequencing, we need to create platform > devices for child nodes of the port node. They will get matched against > the pwrseq drivers (if one exists) and then the actual PCI device will > reuse the node once it's detected on the bus. > > Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org> [..] > diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c > index d749ea8250d6..77be0630b7b3 100644 > --- a/drivers/pci/remove.c > +++ b/drivers/pci/remove.c > @@ -1,6 +1,7 @@ > // SPDX-License-Identifier: GPL-2.0 > #include <linux/pci.h> > #include <linux/module.h> > +#include <linux/of_platform.h> > #include "pci.h" > > static void pci_free_resources(struct pci_dev *dev) > @@ -18,11 +19,11 @@ static void pci_stop_dev(struct pci_dev *dev) > pci_pme_active(dev, false); > > if (pci_dev_is_added(dev)) { > - > device_release_driver(&dev->dev); > pci_proc_detach_device(dev); > pci_remove_sysfs_dev_files(dev); > of_pci_remove_node(dev); > + of_platform_depopulate(&dev->dev); > > pci_dev_assign_added(dev, false); Why is pci_stop_dev() not in strict reverse order of pci_bus_add_device()? I see that pci_dev_assign_added() was already not in reverse "add" order before your change, but I otherwise would have expected of_platform_depopulate() before of_pci_remove_node() (assumed paired with of_pci_make_dev_node()).
On Wed, Jan 17, 2024 at 05:07:43PM +0100, Bartosz Golaszewski wrote: > From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org> > > In order to introduce PCI power-sequencing, we need to create platform > devices for child nodes of the port node. Ick, why a platform device? What is the parent of this device, a PCI device? If so, then this can't be a platform device, as that's not what it is, it's something else so make it a device of that type,. > They will get matched against > the pwrseq drivers (if one exists) and then the actual PCI device will > reuse the node once it's detected on the bus. Reuse it how? > Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org> > --- > drivers/pci/bus.c | 9 ++++++++- > drivers/pci/remove.c | 3 ++- > 2 files changed, 10 insertions(+), 2 deletions(-) > > diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c > index 9c2137dae429..8ab07f711834 100644 > --- a/drivers/pci/bus.c > +++ b/drivers/pci/bus.c > @@ -12,6 +12,7 @@ > #include <linux/errno.h> > #include <linux/ioport.h> > #include <linux/of.h> > +#include <linux/of_platform.h> > #include <linux/proc_fs.h> > #include <linux/slab.h> > > @@ -342,8 +343,14 @@ void pci_bus_add_device(struct pci_dev *dev) > */ > pcibios_bus_add_device(dev); > pci_fixup_device(pci_fixup_final, dev); > - if (pci_is_bridge(dev)) > + if (pci_is_bridge(dev)) { > of_pci_make_dev_node(dev); > + retval = of_platform_populate(dev->dev.of_node, NULL, NULL, > + &dev->dev); So this is a pci bridge device, not a platform device, please don't do this, make it a real device of a new type. thanks, greg k-h
On Wed, Jan 17, 2024 at 5:45 PM Greg Kroah-Hartman <gregkh@linuxfoundation.org> wrote: > > On Wed, Jan 17, 2024 at 05:07:43PM +0100, Bartosz Golaszewski wrote: > > From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org> > > > > In order to introduce PCI power-sequencing, we need to create platform > > devices for child nodes of the port node. > > Ick, why a platform device? What is the parent of this device, a PCI > device? If so, then this can't be a platform device, as that's not what > it is, it's something else so make it a device of that type,. > Greg, This is literally what we agreed on at LPC. In fact: during one of the hall track discussions I said that you typically NAK any attempts at using the platform bus for "fake" devices but you responded that this is what the USB on-board HUB does and while it's not pretty, this is what we need to do. Now as for the implementation, the way I see it we have two solutions: either we introduce a fake, top-level PCI slot platform device device that will reference the PCI host controller by phandle or we will live with a secondary, "virtual" platform device for power sequencing that is tied to the actual PCI device. The former requires us to add DT bindings, add a totally fake DT node representing the "slot" which doesn't really exist (and Krzysztof already expressed his negative opinion of that) and then have code that will be more complex than it needs to be. The latter allows us to not change DT at all (other than adding regulators, clocks and GPIOs to already existing WLAN nodes), reuse the existing parent-child relationship between the port node and the instantiated platform device as well as result in simpler code. Given that DT needs to be stable while the underlying C code can freely change if we find a better solution, I think that the second option is a no-brainer here. > > They will get matched against > > the pwrseq drivers (if one exists) and then the actual PCI device will > > reuse the node once it's detected on the bus. > > Reuse it how? > By consuming the same DT node using device_set_of_node_from_dev() when the PCI device is registered. This ensures we don't try to bind pinctrl twice etc. > > Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org> > > --- > > drivers/pci/bus.c | 9 ++++++++- > > drivers/pci/remove.c | 3 ++- > > 2 files changed, 10 insertions(+), 2 deletions(-) > > > > diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c > > index 9c2137dae429..8ab07f711834 100644 > > --- a/drivers/pci/bus.c > > +++ b/drivers/pci/bus.c > > @@ -12,6 +12,7 @@ > > #include <linux/errno.h> > > #include <linux/ioport.h> > > #include <linux/of.h> > > +#include <linux/of_platform.h> > > #include <linux/proc_fs.h> > > #include <linux/slab.h> > > > > @@ -342,8 +343,14 @@ void pci_bus_add_device(struct pci_dev *dev) > > */ > > pcibios_bus_add_device(dev); > > pci_fixup_device(pci_fixup_final, dev); > > - if (pci_is_bridge(dev)) > > + if (pci_is_bridge(dev)) { > > of_pci_make_dev_node(dev); > > + retval = of_platform_populate(dev->dev.of_node, NULL, NULL, > > + &dev->dev); > > So this is a pci bridge device, not a platform device, please don't do > this, make it a real device of a new type. > Not sure what you mean. Are you suggesting adding a new bus? Or do we already have a concept of PCI bridge devices in the kernel? Bartosz > thanks, > > greg k-h
On Thu, Jan 18, 2024 at 11:58:50AM +0100, Bartosz Golaszewski wrote: > On Wed, Jan 17, 2024 at 5:45 PM Greg Kroah-Hartman > <gregkh@linuxfoundation.org> wrote: > > > > On Wed, Jan 17, 2024 at 05:07:43PM +0100, Bartosz Golaszewski wrote: > > > From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org> > > > > > > In order to introduce PCI power-sequencing, we need to create platform > > > devices for child nodes of the port node. > > > > Ick, why a platform device? What is the parent of this device, a PCI > > device? If so, then this can't be a platform device, as that's not what > > it is, it's something else so make it a device of that type,. > > > > Greg, > > This is literally what we agreed on at LPC. In fact: during one of the > hall track discussions I said that you typically NAK any attempts at > using the platform bus for "fake" devices but you responded that this > is what the USB on-board HUB does and while it's not pretty, this is > what we need to do. Ah, you need to remind me of these things, this changelog was pretty sparse :) > Now as for the implementation, the way I see it we have two solutions: > either we introduce a fake, top-level PCI slot platform device device > that will reference the PCI host controller by phandle or we will live > with a secondary, "virtual" platform device for power sequencing that > is tied to the actual PCI device. The former requires us to add DT > bindings, add a totally fake DT node representing the "slot" which > doesn't really exist (and Krzysztof already expressed his negative > opinion of that) and then have code that will be more complex than it > needs to be. The latter allows us to not change DT at all (other than > adding regulators, clocks and GPIOs to already existing WLAN nodes), > reuse the existing parent-child relationship between the port node and > the instantiated platform device as well as result in simpler code. > > Given that DT needs to be stable while the underlying C code can > freely change if we find a better solution, I think that the second > option is a no-brainer here. Ok, I remove my objections, sorry about that, my confusion. greg k-h
diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index 9c2137dae429..8ab07f711834 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -12,6 +12,7 @@ #include <linux/errno.h> #include <linux/ioport.h> #include <linux/of.h> +#include <linux/of_platform.h> #include <linux/proc_fs.h> #include <linux/slab.h> @@ -342,8 +343,14 @@ void pci_bus_add_device(struct pci_dev *dev) */ pcibios_bus_add_device(dev); pci_fixup_device(pci_fixup_final, dev); - if (pci_is_bridge(dev)) + if (pci_is_bridge(dev)) { of_pci_make_dev_node(dev); + retval = of_platform_populate(dev->dev.of_node, NULL, NULL, + &dev->dev); + if (retval) + pci_err(dev, "failed to populate child OF nodes (%d)\n", + retval); + } pci_create_sysfs_dev_files(dev); pci_proc_attach_device(dev); pci_bridge_d3_update(dev); diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c index d749ea8250d6..77be0630b7b3 100644 --- a/drivers/pci/remove.c +++ b/drivers/pci/remove.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/pci.h> #include <linux/module.h> +#include <linux/of_platform.h> #include "pci.h" static void pci_free_resources(struct pci_dev *dev) @@ -18,11 +19,11 @@ static void pci_stop_dev(struct pci_dev *dev) pci_pme_active(dev, false); if (pci_dev_is_added(dev)) { - device_release_driver(&dev->dev); pci_proc_detach_device(dev); pci_remove_sysfs_dev_files(dev); of_pci_remove_node(dev); + of_platform_depopulate(&dev->dev); pci_dev_assign_added(dev, false); }