usb_match_id searches an array of usb_device_id's and returns the first one matching the device or interface, or null. This is used when binding (or rebinding) a driver to an interface. Most USB device drivers will use this indirectly, through the usb core, but some layered driver frameworks use it directly. These device tables are exported with MODULE_DEVICE_TABLE, through modutils, to support the driver loading functionality of USB hotplugging.
The "match_flags" element in a usb_device_id controls which members are used. If the corresponding bit is set, the value in the device_id must match its corresponding member in the device or interface descriptor, or else the device_id does not match.
"driver_info" is normally used only by device drivers, but you can create a wildcard "matches anything" usb_device_id as a driver's "modules.usbmap" entry if you provide an id with only a nonzero "driver_info" field. If you do this, the USB device driver's probe() routine should use additional intelligence to decide whether to bind to the specified interface.
What Makes Good usb_device_id Tables:
The match algorithm is very simple, so that intelligence in driver selection must come from smart driver id records. Unless you have good reasons to use another selection policy, provide match elements only in related groups, and order match specifiers from specific to general. Use the macros provided for that purpose if you can.
The most specific match specifiers use device descriptor data. These are commonly used with product-specific matches; the USB_DEVICE macro lets you provide vendor and product IDs, and you can also match against ranges of product revisions. These are widely used for devices with application or vendor specific bDeviceClass values.
Matches based on device class/subclass/protocol specifications are slightly more general; use the USB_DEVICE_INFO macro, or its siblings. These are used with single-function devices where bDeviceClass doesn't specify that each interface has its own class.
Matches based on interface class/subclass/protocol are the most general; they let drivers bind to any interface on a multiple-function device. Use the USB_INTERFACE_INFO macro, or its siblings, to match class-per-interface style devices (as recorded in bDeviceClass).
Within those groups, remember that not all combinations are meaningful. For example, don't give a product version range without vendor and product IDs; or specify a protocol without its associated class and subclass.
This is used to enable data transfers on interfaces that may not be enabled by default. Not all devices support such configurability. Only the driver bound to an interface may change its setting.
Within any given configuration, each interface may have several alternative settings. These are often used to control levels of bandwidth consumption. For example, the default setting for a high speed interrupt endpoint may not send more than 64 bytes per microframe, while interrupt transfers of up to 3KBytes per microframe are legal. Also, isochronous endpoints may never be part of an interface's default setting. To access such bandwidth, alternate interface settings must be made current.
Note that in the Linux USB subsystem, bandwidth associated with an endpoint in a given alternate setting is not reserved until an URB is submitted that needs that bandwidth. Some other operating systems allocate bandwidth early, when a configuration is chosen.
This call is synchronous, and may not be used in an interrupt context. Also, drivers must not change altsettings while urbs are scheduled for endpoints in that interface; all such urbs must first be completed (perhaps forced by unlinking).