mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2026-05-16 00:51:51 -04:00
KVM: arm64: Handle permission faults with guest_memfd
gmem_abort() calls kvm_pgtable_stage2_map() to make changes to stage 2. It
does this for both relaxing permissions on an existing mapping and to
install a missing mapping.
kvm_pgtable_stage2_map() doesn't make changes to stage 2 if there is an
existing, valid entry and the new entry modifies only the permissions.
This is checked in:
kvm_pgtable_stage2_map()
stage2_map_walk_leaf()
stage2_map_walker_try_leaf()
stage2_pte_needs_update()
and if only the permissions differ, kvm_pgtable_stage2_map() returns
-EAGAIN and KVM returns to the guest to replay the instruction. The
assumption is that a concurrent fault on a different VCPU already mapped
the faulting IPA, and replaying the instruction will either succeed, or
cause a permission fault, which should be handled with
kvm_pgtable_stage2_relax_perms().
gmem_abort(), on a read or write fault on a system without DIC (instruction
cache invalidation required for data to instruction coherence), installs a
valid entry with read and write permissions, but without executable
permissions. On an execution fault on the same page, gmem_abort() attempts
to relax the permissions to allow execution, but calls
kvm_pgtable_stage2_map() to change the existing, valid, entry.
kvm_pgtable_stage2_map() returns -EAGAIN and KVM resumes execution from the
faulting instruction, which leads to an infinite loop of permission faults
on the same instruction.
Allow the guest to make progress by using kvm_pgtable_stage2_relax_perms()
to relax permissions.
Fixes: a7b57e0995 ("KVM: arm64: Handle guest_memfd-backed guest page faults")
Signed-off-by: Alexandru Elisei <alexandru.elisei@arm.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Link: https://patch.msgid.link/20260505094913.75317-1-alexandru.elisei@arm.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
This commit is contained in:
committed by
Marc Zyngier
parent
8d9b9d985a
commit
9be19df816
@@ -1576,21 +1576,24 @@ struct kvm_s2_fault_desc {
|
||||
static int gmem_abort(const struct kvm_s2_fault_desc *s2fd)
|
||||
{
|
||||
bool write_fault, exec_fault;
|
||||
bool perm_fault = kvm_vcpu_trap_is_permission_fault(s2fd->vcpu);
|
||||
enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_SHARED;
|
||||
enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
|
||||
struct kvm_pgtable *pgt = s2fd->vcpu->arch.hw_mmu->pgt;
|
||||
unsigned long mmu_seq;
|
||||
struct page *page;
|
||||
struct kvm *kvm = s2fd->vcpu->kvm;
|
||||
void *memcache;
|
||||
void *memcache = NULL;
|
||||
kvm_pfn_t pfn;
|
||||
gfn_t gfn;
|
||||
int ret;
|
||||
|
||||
memcache = get_mmu_memcache(s2fd->vcpu);
|
||||
ret = topup_mmu_memcache(s2fd->vcpu, memcache);
|
||||
if (ret)
|
||||
return ret;
|
||||
if (!perm_fault) {
|
||||
memcache = get_mmu_memcache(s2fd->vcpu);
|
||||
ret = topup_mmu_memcache(s2fd->vcpu, memcache);
|
||||
if (ret)
|
||||
return ret;
|
||||
}
|
||||
|
||||
if (s2fd->nested)
|
||||
gfn = kvm_s2_trans_output(s2fd->nested) >> PAGE_SHIFT;
|
||||
@@ -1631,9 +1634,19 @@ static int gmem_abort(const struct kvm_s2_fault_desc *s2fd)
|
||||
goto out_unlock;
|
||||
}
|
||||
|
||||
ret = KVM_PGT_FN(kvm_pgtable_stage2_map)(pgt, s2fd->fault_ipa, PAGE_SIZE,
|
||||
__pfn_to_phys(pfn), prot,
|
||||
memcache, flags);
|
||||
if (perm_fault) {
|
||||
/*
|
||||
* Drop the SW bits in favour of those stored in the
|
||||
* PTE, which will be preserved.
|
||||
*/
|
||||
prot &= ~KVM_NV_GUEST_MAP_SZ;
|
||||
ret = KVM_PGT_FN(kvm_pgtable_stage2_relax_perms)(pgt, s2fd->fault_ipa,
|
||||
prot, flags);
|
||||
} else {
|
||||
ret = KVM_PGT_FN(kvm_pgtable_stage2_map)(pgt, s2fd->fault_ipa, PAGE_SIZE,
|
||||
__pfn_to_phys(pfn), prot,
|
||||
memcache, flags);
|
||||
}
|
||||
|
||||
out_unlock:
|
||||
kvm_release_faultin_page(kvm, page, !!ret, prot & KVM_PGTABLE_PROT_W);
|
||||
|
||||
Reference in New Issue
Block a user