On 12/18/2015 04:41 PM, Pratyush Anand wrote:
On Fri, Dec 18, 2015 at 6:08 PM, Stanimir Varbanov
[off-list ref] wrote:
quoted
There is no guarantees that enabling ATU will hit the hardware
immediately, and subsequent accesses to configuration / IO spaces
are reliable. So fixing this by read back PCIE_ATU_CR2 register
just after writing.
Without such a fix the PCI device enumeration during kernel boot
is not reliable, and reading configuration space for particular
PCI device on the bus returns zero aka no device.
Signed-off-by: Stanimir Varbanov <redacted>
Acked-by: Pratyush Anand <pratyush.anand@gmail.com>
Bjorn, Do you want to resend the whole patchset with collected acks and
tested tags?
--
regards,
Stan