Re: [RFC 1/2] PCI-Express Non-Transparent Bridge Support
flat view
From: Stephen Hemminger <hidden>
Date: 2012-07-14 00:01:05
Also in:
linux-pci, lkml
On Fri, 13 Jul 2012 14:44:59 -0700 Jon Mason [off-list ref] wrote:
A PCI-Express non-transparent bridge (NTB) is a point-to-point PCIe bus connecting 2 systems, providing electrical isolation between the two subsystems. A non-transparent bridge is functionally similar to a transparent bridge except that both sides of the bridge have their own independent address domains. The host on one side of the bridge will not have the visibility of the complete memory or I/O space on the other side of the bridge. To communicate across the non-transparent bridge, each NTB endpoint has one (or more) apertures exposed to the local system. Writes to these apertures are mirrored to memory on the remote system. Communications can also occur through the use of doorbell registers that initiate interrupts to the alternate domain, and scratch-pad registers accessible from both sides. The NTB device driver is needed to configure these memory windows, doorbell, and scratch-pad registers as well as use them in such a way as they can be turned into a viable communication channel to the remote system. ntb_hw.[ch] determines the usage model (NTB to NTB or NTB to Root Port) and abstracts away the underlying hardware to provide access and a common interface to the doorbell registers, scratch pads, and memory windows. These hardware interfaces are exported so that other, non-mainlined kernel drivers can access these. ntb_transport.[ch] also uses the exported interfaces in ntb_hw.[ch] to setup a communication channel(s) and provide a reliable way of transferring data from one side to the other, which it then exports so that "client" drivers can access them. These client drivers are used to provide a standard kernel interface (i.e., Ethernet device) to NTB, such that Linux can transfer data from one system to the other in a standard way. Signed-off-by: Jon Mason <redacted>
quoted hunk ↗ jump to hunk
+ +static int max_num_cbs = 2; +module_param(max_num_cbs, uint, 0644); +MODULE_PARM_DESC(max_num_cbs, "Maximum number of NTB transport connections");
Rather than making it a fixed size, could you dynamically set these up with rtnl_link_ops?
+static struct ntb_device *ntbdev;
What about multiple boards in system?
quoted hunk ↗ jump to hunk
+/** + * ntb_hw_link_status() - return the hardware link status + * @ndev: pointer to ntb_device instance + * + * Returns true if the hardware is connected to the remote system + * + * RETURNS: true or false based on the hardware link state + */ +bool ntb_hw_link_status(struct ntb_device *ndev) +{ + return ndev->link_status == NTB_LINK_UP; +} +EXPORT_SYMBOL(ntb_hw_link_status);
Why isn't this inline in some header?
quoted hunk ↗ jump to hunk
+/** + * ntb_query_pdev() - return the pci_dev pointer + * @ndev: pointer to ntb_device instance + * + * Given the ntb pointer return the pci_dev pointerfor the NTB hardware device + * + * RETURNS: a pointer to the ntb pci_dev + */ +struct pci_dev *ntb_query_pdev(struct ntb_device *ndev) +{ + return ndev->pdev; +} +EXPORT_SYMBOL(ntb_query_pdev); + +/** + * ntb_query_max_cbs() - return the maximum number of callback tuples + * @ndev: pointer to ntb_device instance + * + * The number of callbacks can vary depending on the platform and MSI-X/MSI + * enablement + * + * RETURNS: the maximum number of callback tuples (3, 15, or 33) + */ +unsigned int ntb_query_max_cbs(struct ntb_device *ndev) +{ + return ndev->max_cbs > max_num_cbs ? max_num_cbs : ndev->max_cbs; +} +EXPORT_SYMBOL(ntb_query_max_cbs); + +/** + * ntb_register_event_callback() - register event callback + * @ndev: pointer to ntb_device instance + * @func: callback function to register + * + * This function registers a callback for any HW driver events such as link + * up/down, power management notices and etc. + * + * RETURNS: An appropriate -ERRNO error value on error, or zero for success. + */ +int ntb_register_event_callback(struct ntb_device *ndev, + void (*func)(void *handle, unsigned int event)) +{ + if (ndev->event_cb) + return -EINVAL; + + ndev->event_cb = func; + + return 0; +} +EXPORT_SYMBOL(ntb_register_event_callback); + +/** + * ntb_unregister_event_callback() - unregisters the event callback + * @ndev: pointer to ntb_device instance + * + * This function unregisters the existing callback from transport + */ +void ntb_unregister_event_callback(struct ntb_device *ndev) +{ + ndev->event_cb = NULL; +} +EXPORT_SYMBOL(ntb_unregister_event_callback); +