Messages in this thread |  | | Date | Mon, 03 Aug 2009 10:01:19 +0900 | From | Tejun Heo <> | Subject | Re: [GIT PULL] Additional x86 fixes for 2.6.31-rc5 |
| |
Hello,
H. Peter Anvin wrote: > You can't actually do "lea %gs:foo,%rbx" (lea doesn't include the > segment offset, unfortunately; I asked AMD to change that on 64 bits > but, not too surprisingly, they weren't able to make that change.) > Getting the address is expensive, but it's obviously possible -- which > may have similar bad results. It would be worth experimenting with a > little bit, though.
Yeap, this part is strange. I can't understand why it was done that way. Interestingly, the segment override doesn't trigger any exception, it just gets ignored. Is there a way to retrieve %gs value without accessing memory? ie. other than %gs:identity_gs?
Thanks.
-- tejun
|  |