On 03/01/2018 10:58 AM, Jan Beulich wrote: >>>> On 28.02.18 at 11:38, <[email protected]> wrote: >> In hardware, when PCID support is enabled and the NOFLUSH bit is set >> when writing a CR3 value, the hardware will clear that that bit and >> change the CR3 without flushing the TLB. hvm_set_cr3(), however, was >> ignoring this bit; the result was that post-vm_event checks detected >> an invalid CR3 value and crashed the domain. >> >> Handle NOFLUSH in hvm_set_cr3() by: >> 1. Clearing the bit >> 2. Passing a "noflush" flag to lower-level cr3 setting functions to >> indicate that a flush should not be performed. >> >> Also clear X86_CR3_NOFLUSH when reporting CR3 monitored CR3 writes. >> >> This allows introspection to be used on VMs whose operating system uses >> the NOFLUSH bit. >> >> Signed-off-by: Razvan Cojocaru <[email protected]> >> Reported-by: Bitweasil <[email protected]> >> Suggested-by: Andrew Cooper <[email protected]> >> Acked-by: Tamas K Lengyel <[email protected]> >> Reviewed-by: Jan Beulich <[email protected]> >> Reviewed-by: Kevin Tian <[email protected]> >> Acked-by: George Dunlap <[email protected]> > > There's now the question of whether to backport this change: > It's quite large, and as per the description it deals with an > introspection issue only. Hence for the moment I'll leave this > out. If someone comes forward with good reasons to take this > for some or all of the still maintained older trees, I'm willing to > reconsider. But of course possible interdependencies with > other changes that weren't backported will also need to be > taken into consideration with any such request.
That seems reasonable to me. -George _______________________________________________ Xen-devel mailing list [email protected] https://lists.xenproject.org/mailman/listinfo/xen-devel
