On Wed, May 11, 2011 at 4:21 PM, Jesse Barnes <jbarnes@xxxxxxxxxxxxxxxx> wrote:
> Latency tolerance reporting allows devices to send messages to the root
> complex indicating their latency tolerance for snooped & unsnooped
> memory transactions. Add support for enabling & disabling this
> feature, along with a routine to set the max latencies a device should
> send upstream.
>
> Signed-off-by: Jesse Barnes <jbarnes@xxxxxxxxxxxxxxxx>
> ---
> drivers/pci/pci.c | 149 ++++++++++++++++++++++++++++++++++++++++++++++
> include/linux/pci.h | 5 ++
> include/linux/pci_regs.h | 9 +++
> 3 files changed, 163 insertions(+), 0 deletions(-)
>
> diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
> index 01e4cab..53302cb 100644
> --- a/drivers/pci/pci.c
> +++ b/drivers/pci/pci.c
> @@ -1979,6 +1979,155 @@ void pci_disable_obff(struct pci_dev *dev)
> }
> EXPORT_SYMBOL(pci_disable_obff);
>
> +/**
> + * pci_ltr_supported - check whether a device supports LTR
> + * @dev: PCI device
> + *
> + * RETURNS:
> + * True if @dev supports latency tolerance reporting, false otherwise.
> + */
> +bool pci_ltr_supported(struct pci_dev *dev)
> +{
> + int pos;
> + u32 cap;
> +
> + if (!pci_is_pcie(dev))
> + return false;
Jesse,
Based on Bjorn's comment to the initial posting of [PATCH 1/3] PCI:
add ID-based ordering enable/disable support
(http://marc.info/?l=linux-pci&m=130463494319762&w=2) you may want to
also drop the above check both in this patch and the OBFF patch for
consistency.
Reviewed-by: Myron Stowe <myron.stowe@xxxxxxxxxx>
Myron
> +
> + pos = pci_pcie_cap(dev);
> + if (!pos)
> + return false;
> +
> + pci_read_config_dword(dev, pos + PCI_EXP_DEVCAP2, &cap);
> +
> + return cap & PCI_EXP_DEVCAP2_LTR;
> +}
> +EXPORT_SYMBOL(pci_ltr_supported);
> +
snip
--
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
