[PATCH v2 1/1] PCI: X-Gene: Disable Configuration Request Retry Status for X-Gene v1 PCIe

[Bjorn Helgaas]

On Thu, Jun 18, 2015 at 12:55:53PM -0500, Bjorn Helgaas wrote:
> On Fri, Jun 12, 2015 at 05:35:57PM -0700, Duc Dang wrote:
> > X-Gene v1 PCIe controller has a bug in Configuration Request Retry
> > Status (CRS) logic:
> >   When CPU tries to read Vendor ID and Device ID of not-existed
> >   remote device, the controller returns 0xFFFF0001 instead of
> >   0xFFFFFFFF; this will add significant delay in boot time as
> >   pci_bus_read_dev_vendor_id will wait for 60 seconds before
> >   giving up.
> > 
> > So for X-Gene v1 PCIe controllers, disable CRS capability
> > advertisement by clearing CRS Software Visibility bit before
> > returning the Root Capability value to the callers. This is done
> > by implementing X-Gene PCIe specific xgene_pcie_config_read32 for
> > CFG read accesses to replace the generic default pci_generic_config_read32
> > function.
> > 
> > v2 changes:
> >         Use pci_generic_config_read32 to implement xgene_pcie_config_read32
> > 
> > Signed-off-by: Duc Dang <dhdang at apm.com>
> > Tested-by: Ian Campbell <ian.campbell at citrix.com>
> > Tested-by: Marcin Juszkiewicz <mjuszkiewicz at redhat.com>
> 
> I'd like to merge this (as amended below) for v4.2.  But I'm looking for an
> ack from Tanmay, and I'm still waiting for the second patch to remove the
> link_up test.
> 
> Bjorn

Applied to pci/host-xgene for v4.2, thanks very much!

> commit 49ac8c566d7a37f9f295e1fd4fbdd96517f22d55
> Author: Duc Dang <dhdang at apm.com>
> Date:   Fri Jun 12 17:35:57 2015 -0700
> 
>     PCI: xgene: Disable Configuration Request Retry Status for v1 silicon
>     
>     When a CPU reads the Vendor and Device ID of a non-existent device, the
>     controller should fabricate return data of 0xFFFFFFFF.  Configuration
>     Request Retry Status (CRS) is not applicable in this case because the
>     device doesn't exist at all.
>     
>     The X-Gene v1 PCIe controller has a bug in the CRS logic such that when CRS
>     is enabled, it fabricates return data of 0xFFFF0001 for this case, which
>     means "the device exists but is not ready."  That causes the PCI core to
>     retry the read until it times out after 60 seconds.
>     
>     Disable CRS capability advertisement by clearing the CRS Software
>     Visibility bit in the Root Capabilities Register.
>     
>     [bhelgaas: changelog and comment]
>     Tested-by: Ian Campbell <ian.campbell at citrix.com>
>     Tested-by: Marcin Juszkiewicz <mjuszkiewicz at redhat.com>
>     Signed-off-by: Duc Dang <dhdang at apm.com>
>     Signed-off-by: Bjorn Helgaas <bhelgaas at google.com>
> 
> diff --git a/drivers/pci/host/pci-xgene.c b/drivers/pci/host/pci-xgene.c
> index 3e5a636..70af714 100644
> --- a/drivers/pci/host/pci-xgene.c
> +++ b/drivers/pci/host/pci-xgene.c
> @@ -59,6 +59,12 @@
>  #define SZ_1T				(SZ_1G*1024ULL)
>  #define PIPE_PHY_RATE_RD(src)		((0xc000 & (u32)(src)) >> 0xe)
>  
> +#define ROOT_CAP_AND_CTRL		0x5C
> +
> +/* PCIe IP version */
> +#define XGENE_PCIE_IP_VER_UNKN		0
> +#define XGENE_PCIE_IP_VER_1		1
> +
>  struct xgene_pcie_port {
>  	struct device_node	*node;
>  	struct device		*dev;
> @@ -67,6 +73,7 @@ struct xgene_pcie_port {
>  	void __iomem		*cfg_base;
>  	unsigned long		cfg_addr;
>  	bool			link_up;
> +	u32			version;
>  };
>  
>  static inline u32 pcie_bar_low_val(u32 addr, u32 flags)
> @@ -140,9 +147,37 @@ static void __iomem *xgene_pcie_map_bus(struct pci_bus *bus, unsigned int devfn,
>  	return xgene_pcie_get_cfg_base(bus) + offset;
>  }
>  
> +static int xgene_pcie_config_read32(struct pci_bus *bus, unsigned int devfn,
> +				    int where, int size, u32 *val)
> +{
> +	struct xgene_pcie_port *port = bus->sysdata;
> +
> +	if (pci_generic_config_read32(bus, devfn, where & ~0x3, 4, val) !=
> +	    PCIBIOS_SUCCESSFUL)
> +		return PCIBIOS_DEVICE_NOT_FOUND;
> +
> +	/*
> +	 * The v1 controller has a bug in its Configuration Request
> +	 * Retry Status (CRS) logic: when CRS is enabled and we read the
> +	 * Vendor and Device ID of a non-existent device, the controller
> +	 * fabricates return data of 0xFFFF0001 ("device exists but is not
> +	 * ready") instead of 0xFFFFFFFF ("device does not exist").  This
> +	 * causes the PCI core to retry the read until it times out.
> +	 * Avoid this by not claiming to support CRS.
> +	 */
> +	if (pci_is_root_bus(bus) && (port->version == XGENE_PCIE_IP_VER_1) &&
> +	    ((where & ~0x3) == ROOT_CAP_AND_CTRL))
> +		*val &= ~(PCI_EXP_RTCAP_CRSVIS << 16);
> +
> +	if (size <= 2)
> +		*val = (*val >> (8 * (where & 3))) & ((1 << (size * 8)) - 1);
> +
> +	return PCIBIOS_SUCCESSFUL;
> +}
> +
>  static struct pci_ops xgene_pcie_ops = {
>  	.map_bus = xgene_pcie_map_bus,
> -	.read = pci_generic_config_read32,
> +	.read = xgene_pcie_config_read32,
>  	.write = pci_generic_config_write32,
>  };
>  
> @@ -500,6 +535,10 @@ static int xgene_pcie_probe_bridge(struct platform_device *pdev)
>  	port->node = of_node_get(pdev->dev.of_node);
>  	port->dev = &pdev->dev;
>  
> +	port->version = XGENE_PCIE_IP_VER_UNKN;
> +	if (of_device_is_compatible(port->node, "apm,xgene-pcie"))
> +		port->version = XGENE_PCIE_IP_VER_1;
> +
>  	ret = xgene_pcie_map_reg(port, pdev);
>  	if (ret)
>  		return ret;