1Accessing PCI device resources through sysfs 2-------------------------------------------- 3 4sysfs, usually mounted at /sys, provides access to PCI resources on platforms 5that support it. For example, a given bus might look like this: 6 7 /sys/devices/pci0000:17 8 |-- 0000:17:00.0 9 | |-- class 10 | |-- config 11 | |-- device 12 | |-- enable 13 | |-- irq 14 | |-- local_cpus 15 | |-- remove 16 | |-- resource 17 | |-- resource0 18 | |-- resource1 19 | |-- resource2 20 | |-- rom 21 | |-- subsystem_device 22 | |-- subsystem_vendor 23 | `-- vendor 24 `-- ... 25 26The topmost element describes the PCI domain and bus number. In this case, 27the domain number is 0000 and the bus number is 17 (both values are in hex). 28This bus contains a single function device in slot 0. The domain and bus 29numbers are reproduced for convenience. Under the device directory are several 30files, each with their own function. 31 32 file function 33 ---- -------- 34 class PCI class (ascii, ro) 35 config PCI config space (binary, rw) 36 device PCI device (ascii, ro) 37 enable Whether the device is enabled (ascii, rw) 38 irq IRQ number (ascii, ro) 39 local_cpus nearby CPU mask (cpumask, ro) 40 remove remove device from kernel's list (ascii, wo) 41 resource PCI resource host addresses (ascii, ro) 42 resource0..N PCI resource N, if present (binary, mmap) 43 resource0_wc..N_wc PCI WC map resource N, if prefetchable (binary, mmap) 44 rom PCI ROM resource, if present (binary, ro) 45 subsystem_device PCI subsystem device (ascii, ro) 46 subsystem_vendor PCI subsystem vendor (ascii, ro) 47 vendor PCI vendor (ascii, ro) 48 49 ro - read only file 50 rw - file is readable and writable 51 wo - write only file 52 mmap - file is mmapable 53 ascii - file contains ascii text 54 binary - file contains binary data 55 cpumask - file contains a cpumask type 56 57The read only files are informational, writes to them will be ignored, with 58the exception of the 'rom' file. Writable files can be used to perform 59actions on the device (e.g. changing config space, detaching a device). 60mmapable files are available via an mmap of the file at offset 0 and can be 61used to do actual device programming from userspace. Note that some platforms 62don't support mmapping of certain resources, so be sure to check the return 63value from any attempted mmap. 64 65The 'enable' file provides a counter that indicates how many times the device 66has been enabled. If the 'enable' file currently returns '4', and a '1' is 67echoed into it, it will then return '5'. Echoing a '0' into it will decrease 68the count. Even when it returns to 0, though, some of the initialisation 69may not be reversed. 70 71The 'rom' file is special in that it provides read-only access to the device's 72ROM file, if available. It's disabled by default, however, so applications 73should write the string "1" to the file to enable it before attempting a read 74call, and disable it following the access by writing "0" to the file. Note 75that the device must be enabled for a rom read to return data successfully. 76In the event a driver is not bound to the device, it can be enabled using the 77'enable' file, documented above. 78 79The 'remove' file is used to remove the PCI device, by writing a non-zero 80integer to the file. This does not involve any kind of hot-plug functionality, 81e.g. powering off the device. The device is removed from the kernel's list of 82PCI devices, the sysfs directory for it is removed, and the device will be 83removed from any drivers attached to it. Removal of PCI root buses is 84disallowed. 85 86Accessing legacy resources through sysfs 87---------------------------------------- 88 89Legacy I/O port and ISA memory resources are also provided in sysfs if the 90underlying platform supports them. They're located in the PCI class hierarchy, 91e.g. 92 93 /sys/class/pci_bus/0000:17/ 94 |-- bridge -> ../../../devices/pci0000:17 95 |-- cpuaffinity 96 |-- legacy_io 97 `-- legacy_mem 98 99The legacy_io file is a read/write file that can be used by applications to 100do legacy port I/O. The application should open the file, seek to the desired 101port (e.g. 0x3e8) and do a read or a write of 1, 2 or 4 bytes. The legacy_mem 102file should be mmapped with an offset corresponding to the memory offset 103desired, e.g. 0xa0000 for the VGA frame buffer. The application can then 104simply dereference the returned pointer (after checking for errors of course) 105to access legacy memory space. 106 107Supporting PCI access on new platforms 108-------------------------------------- 109 110In order to support PCI resource mapping as described above, Linux platform 111code must define HAVE_PCI_MMAP and provide a pci_mmap_page_range function. 112Platforms are free to only support subsets of the mmap functionality, but 113useful return codes should be provided. 114 115Legacy resources are protected by the HAVE_PCI_LEGACY define. Platforms 116wishing to support legacy functionality should define it and provide 117pci_legacy_read, pci_legacy_write and pci_mmap_legacy_page_range functions. 118