make /dev/pci really readable

Doug Ambrisko ambrisko at ambrisko.com
Mon Jun 16 16:57:54 PDT 2003


Doug Ambrisko writes:
| Scott Long writes:
| | You should not always assume that reading PCI registers has no
| | side-effects.  It is certainly legal and possible for a PCI device to
| | detect the read request and alter the contents of the register (or some
| | other register) as a side effect, or change an internal state machine.
| | 'Fixing' the various bits to allow unpriviledged access to 'pciconf -r'
| | is dangerous since you would have to teach the system about every pci
| | device in existance and how to trap on registers that have side-effects.
| 
| I seem to recall reading some PCI chip spec. for a chip I was working on
| that did a reset on read of that register.  I can't recall which or where 
| so don't take this as fact but a distant memory.

I meant to add this but didn't ...

If the register could get cleared then the device driver could get hosed
and that would be bad.

This is what I was thinking about.

Doug A.


More information about the freebsd-arch mailing list