[PATCH v5 00/12] Direct Map Removal Support for guest_memfd

[David Hildenbrand]

On 28.08.25 11:39, Roy, Patrick wrote:
> [ based on kvm/next ]
> 
> Unmapping virtual machine guest memory from the host kernel's direct map is a
> successful mitigation against Spectre-style transient execution issues: If the
> kernel page tables do not contain entries pointing to guest memory, then any
> attempted speculative read through the direct map will necessarily be blocked
> by the MMU before any observable microarchitectural side-effects happen. This
> means that Spectre-gadgets and similar cannot be used to target virtual machine
> memory. Roughly 60% of speculative execution issues fall into this category [1,
> Table 1].
> 

As discussed, I'll be maintaining a guestmemfd-preview branch where I 
just pile patch sets to see how it will all look together.

It's currently based on kvm/next where "stage 1" resides, and has "Add 
NUMA mempolicy support for KVM guest-memfdAdd NUMA mempolicy support for 
KVM guest-memfd" [1] applied.

There are some minor conflicts with [1] in the "KVM: guest_memfd: Add 
flag to remove from direct map" patch, I tried to resolve them, let's 
see if I messed up.

https://git.kernel.org/pub/scm/linux/kernel/git/david/linux.git/log/?h=guestmemfd-preview

[1] https://lkml.kernel.org/r/20250827175247.83322-2-shivankg@amd.com

-- 
Cheers

David / dhildenb