aboutsummaryrefslogtreecommitdiff
path: root/include/linux/bcma
AgeCommit message (Collapse)AuthorFilesLines
2011-06-03bcma: read SPROM and extract MAC from itRafał Miłecki2-0/+6
In case of BCMA cards SPROM is located in the ChipCommon core, it is not mapped as separated host window. So far we have met only SPROMs rev 8. SPROM layout seems to be the same as for SSB buses, so we decided to share SPROM struct and some defines. For now we extract MAC address only, this can be improved of course. Signed-off-by: Rafał Miłecki <[email protected]> Signed-off-by: John W. Linville <[email protected]>
2011-06-01bcma: host pci: implement block R/W operationsRafał Miłecki1-0/+18
Signed-off-by: Rafał Miłecki <[email protected]> Signed-off-by: John W. Linville <[email protected]>
2011-06-01bcma: add IRQ number and pointer to DMA devRafał Miłecki1-0/+2
Signed-off-by: Rafał Miłecki <[email protected]> Signed-off-by: John W. Linville <[email protected]>
2011-05-11bcma: add missing GPIO defines, use PULL register only when availableRafał Miłecki1-0/+5
Similar patch was commited to ssb. Signed-off-by: Rafał Miłecki <[email protected]> Signed-off-by: John W. Linville <[email protected]>
2011-05-10bcma: add Broadcom specific AMBA bus driverRafał Miłecki4-0/+644
Broadcom has released cards based on a new AMBA-based bus type. From a programming point of view, this new bus type differs from AMBA and does not use AMBA common registers. It also differs enough from SSB. We decided that a new bus driver is needed to keep the code clean. In its current form, the driver detects devices present on the bus and registers them in the system. It allows registering BCMA drivers for specified bus devices and provides them basic operations. The bus driver itself includes two important bus managing drivers: ChipCommon core driver and PCI(c) core driver. They are early used to allow correct initialization. Currently code is limited to supporting buses on PCI(e) devices, however the driver is designed to be used also on other hosts. The host abstraction layer is implemented and already used for PCI(e). Support for PCI(e) hosts is working and seems to be stable (access to 80211 core was tested successfully on a few devices). We can still optimize it by using some fixed windows, but this can be done later without affecting any external code. Windows are just ranges in MMIO used for accessing cores on the bus. Cc: Greg KH <[email protected]> Cc: Michael Büsch <[email protected]> Cc: Larry Finger <[email protected]> Cc: George Kashperko <[email protected]> Cc: Arend van Spriel <[email protected]> Cc: [email protected] Cc: Russell King <[email protected]> Cc: Arnd Bergmann <[email protected]> Cc: Andy Botting <[email protected]> Cc: linuxdriverproject <[email protected]> Cc: [email protected] <[email protected]> Signed-off-by: Rafał Miłecki <[email protected]> Signed-off-by: John W. Linville <[email protected]>