From: Bjorn Helgaas Date: Wed, 21 Jan 2015 16:28:07 +0000 (-0600) Subject: PCI: pciehp: Handle surprise add even if surprise removal isn't supported X-Git-Url: https://git.karo-electronics.de/?a=commitdiff_plain;h=a93b506e265a83a0f8c56ff003434e2d263961ce;p=linux-beck.git PCI: pciehp: Handle surprise add even if surprise removal isn't supported The PCIe spec (r3.0, sec 7.8.9) says Hot-Plug Surprise indicates support for surprise *removal*, but pciehp checked this to determine if it should handle presence detect interrupts for device *addition*. Allow surprise device addition even if the slot doesn't advertise support for surprise removal. Keith has a platform with slots for front-loading SFF devices. The slots do not have attention buttons and do not support surprise removal, but they do have presence detect. In that case, we still want to use presence detect for device addition. Keith's original patch handled surprise insertions only if Hot-Plug Capable is set. I think that test is superfluous because pciehp only claims slots that advertise Hot-Plug Capable (see get_port_device_capability()). Link: http://lkml.kernel.org/r/1419275223-14602-1-git-send-email-keith.busch@intel.com Based-on-patch-by: Keith Busch Signed-off-by: Bjorn Helgaas Acked-by: Rajat Jain --- diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c index ff32e85e1de6..f052e951b23e 100644 --- a/drivers/pci/hotplug/pciehp_ctrl.c +++ b/drivers/pci/hotplug/pciehp_ctrl.c @@ -532,8 +532,6 @@ static void interrupt_event_handler(struct work_struct *work) pciehp_green_led_off(p_slot); break; case INT_PRESENCE_ON: - if (!HP_SUPR_RM(ctrl)) - break; ctrl_dbg(ctrl, "Surprise Insertion\n"); handle_surprise_event(p_slot); break;