(2011/03/18 23:52), Chumbalkar, Nagananda wrote:
-----Original Message-----
From: Kenji Kaneshige [mailto:kaneshige.kenji@xxxxxxxxxxxxxx]
Sent: Friday, March 18, 2011 12:29 AM
To: Chumbalkar, Nagananda
Cc: jbarnes@xxxxxxxxxxxxxxxx; rjw@xxxxxxx; mjg59@xxxxxxxxxxxxx; linux-
kernel@xxxxxxxxxxxxxxx; linux-pci@xxxxxxxxxxxxxxx
Subject: Re: [RFC][PATCH v2]: PCI: PCIe links may not get configured for
ASPM under POWERSAVE mode
(2011/03/18 13:21), Naga Chumbalkar wrote:
v2 -> v1:
. Kept the logic in pci_raw_set_power_state
. Changed the ASPM enabling logic
. Modified the text that describes the problem
v1 : http://marc.info/?l=linux-pci&m=130013164703283&w=2
The assumption made in commit 41cd766b065970ff6f6c89dd1cf55fa706c84a3d
(PCI: Don't enable aspm before drivers have had a chance to veto it)
that
pci_enable_device() will result in re-configuring ASPM when
aspm_policy is
POWERSAVE is no longer valid. This is due to commit
97c145f7c87453cec90e91238fba5fe2c1561b32 (PCI: read current power
state
at enable time) which resets dev->current_state to D0. This makes the
equality check (below) become true, so pcie_aspm_pm_state_change()
never
gets called.
./drivers/pci/pci.c: pci_raw_set_pci_power_state()
546 /* Check if we're already there */
547 if (dev->current_state == state)
548 return 0;
So OSPM doesnn't configure the PCIe links for ASPM.
The patch below does the following:
At the end of each Root Bridge scan make a call to configure ASPM when
the
ASPM policy is set to "powersave" mode. Note that if a previous pass
had
completed the configuration for all devices under that Bridge then the
configuration will not take place again because
pcie_config_aspm_link()
checks to see if the link is already in the requested state.
We won't reconfigure ASPM when _OSC control is not granted.
Which _OSC controls do we need for configuring ASPM?
There is no _OSC Control bit for ASPM. However, we expect the BIOS to
support _OSC for a Root Bridge that originates a PCIe hierarchy. If this
is not the case - would it be okay to disable ASPM also?
Commit 852972acff8f10f3a15679be2059bb94916cba5d (ACPI: Disable ASPM if the
Platform won't provide _OSC control for PCIe) describes the above scenario.
To quote from there:
The PCI SIG documentation for the _OSC OS/firmware handshaking interface
states:
"If the _OSC control method is absent from the scope of a host bridge
device, then the operating system must not enable or attempt to use any
features defined in this section for the hierarchy originated by the host
bridge."
The obvious interpretation of this is that the OS should not attempt to use
PCIe hotplug, PME or AER - however, the specification also notes that an
_OSC method is *required* for PCIe hierarchies, and experimental validation
with An Alternative OS indicates that it doesn't use any PCIe functionality
if the _OSC method is missing. That arguably means we shouldn't be using
MSI or extended config space, but right now our problems seem to be limited
to vendors being surprised when ASPM gets enabled on machines when other
OSs refuse to do so. So, for now, let's just disable ASPM if the _OSC
method doesn't exist or refuses to hand over PCIe capability control.
I understood. Thank you for clarification.
Regards,
Kenji Kaneshige
--
To unsubscribe from this list: send the line "unsubscribe linux-pci" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
