From: Suzuki K Poulose Architectures may need to reject deletion of a memory slot without changing the guest's memory mappings. Currently, KVM invalidates the slot and calls kvm_arch_flush_shadow_memslot() before kvm_arch_prepare_memory_region() can reject the request. On arm64, this unmaps the slot from stage-2. Restoring the old memslot on failure does not restore those mappings, so even a rejected deletion has side effects. Add kvm_arch_validate_memory_region() and invoke it before invalidating the slot, with slots_lock and slots_arch_lock held. The hook performs validation only, allowing architectures to reject a request without changing the memslot or its mappings. Provide a weak no-op implementation for architectures that do not need early validation. Move arm64's protected VM checks into the new hook so that unsupported deletions and moves are rejected before stage-2 unmapping. Keep resource preparation after invalidation, since invalidation drops slots_arch_lock and allows concurrent updates to architecture-specific memslot metadata. Assisted-by: LLM Signed-off-by: Suzuki K Poulose Signed-off-by: Steven Price --- arch/arm64/kvm/mmu.c | 22 ++++++++++++++++------ arch/arm64/kvm/pkvm.c | 2 +- include/linux/kvm_host.h | 4 ++++ virt/kvm/kvm_main.c | 33 ++++++++++++++++++++++++++------- 4 files changed, 47 insertions(+), 14 deletions(-) diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index be014f6c00e7..8c29ed204d61 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -2851,13 +2851,12 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, } } -int kvm_arch_prepare_memory_region(struct kvm *kvm, - const struct kvm_memory_slot *old, - struct kvm_memory_slot *new, - enum kvm_mr_change change) +int kvm_arch_validate_memory_region(struct kvm *kvm, + const struct kvm_memory_slot *old, + const struct kvm_memory_slot *new, + enum kvm_mr_change change) { - hva_t hva, reg_end; - int ret = 0; + lockdep_assert_held(&kvm->slots_lock); if (kvm_vm_is_protected(kvm)) { /* Cannot modify memslots once a pVM has run. */ @@ -2872,6 +2871,17 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, } } + return 0; +} + +int kvm_arch_prepare_memory_region(struct kvm *kvm, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, + enum kvm_mr_change change) +{ + hva_t hva, reg_end; + int ret = 0; + if (change != KVM_MR_CREATE && change != KVM_MR_MOVE && change != KVM_MR_FLAGS_ONLY) return 0; diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c index a5145bd75d0c..f4db0e051d6a 100644 --- a/arch/arm64/kvm/pkvm.c +++ b/arch/arm64/kvm/pkvm.c @@ -262,7 +262,7 @@ int pkvm_create_hyp_vm(struct kvm *kvm) int ret = 0; /* - * Synchronise with kvm_arch_prepare_memory_region(), as we + * Synchronise with kvm_arch_validate_memory_region(), as we * prevent memslot modifications on a pVM that has been run. */ mutex_lock(&kvm->slots_lock); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index f65728a713ec..15848221860f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1255,6 +1255,10 @@ int kvm_set_internal_memslot(struct kvm *kvm, const struct kvm_userspace_memory_region2 *mem); void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot); void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen); +int kvm_arch_validate_memory_region(struct kvm *kvm, + const struct kvm_memory_slot *old, + const struct kvm_memory_slot *new, + enum kvm_mr_change change); int kvm_arch_prepare_memory_region(struct kvm *kvm, const struct kvm_memory_slot *old, struct kvm_memory_slot *new, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index cf4cb586f140..3ef370d71818 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1682,6 +1682,20 @@ static void kvm_swap_active_memslots(struct kvm *kvm, int as_id) slots->generation = gen; } +/* + * Validate a memslot change before invalidation, which may irreversibly reclaim + * private guest memory. Called with slots_lock and slots_arch_lock held. + * Implementations must not modify memslot state or allocate resources; leave + * those operations to kvm_arch_prepare_memory_region(). + */ +__weak int kvm_arch_validate_memory_region(struct kvm *kvm, + const struct kvm_memory_slot *old, + const struct kvm_memory_slot *new, + enum kvm_mr_change change) +{ + return 0; +} + static int kvm_prepare_memory_region(struct kvm *kvm, const struct kvm_memory_slot *old, struct kvm_memory_slot *new, @@ -1934,6 +1948,10 @@ static int kvm_set_memslot(struct kvm *kvm, */ mutex_lock(&kvm->slots_arch_lock); + r = kvm_arch_validate_memory_region(kvm, old, new, change); + if (r) + goto unlock_err; + /* * Invalidate the old slot if it's being deleted or moved. This is * done prior to actually deleting/moving the memslot to allow vCPUs to @@ -1950,22 +1968,22 @@ static int kvm_set_memslot(struct kvm *kvm, if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) { invalid_slot = kzalloc_obj(*invalid_slot, GFP_KERNEL_ACCOUNT); if (!invalid_slot) { - mutex_unlock(&kvm->slots_arch_lock); - return -ENOMEM; + r = -ENOMEM; + goto unlock_err; } kvm_invalidate_memslot(kvm, old, invalid_slot); } r = kvm_prepare_memory_region(kvm, old, new, change); if (r) - goto err; + goto revert_slot; if (change == KVM_MR_CREATE && (new->flags & KVM_MEM_GUEST_MEMFD)) { r = kvm_gmem_commit_memory_region(kvm, new); if (r) { kvm_arch_free_memslot(kvm, new); kvm_destroy_dirty_bitmap(new); - goto err; + goto unlock_err; } } @@ -2000,7 +2018,7 @@ static int kvm_set_memslot(struct kvm *kvm, return 0; -err: +revert_slot: /* * For DELETE/MOVE, revert the above INVALID change. No modifications * required since the original slot was preserved in the inactive slots. @@ -2009,9 +2027,10 @@ static int kvm_set_memslot(struct kvm *kvm, if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) { kvm_activate_memslot(kvm, invalid_slot, old); kfree(invalid_slot); - } else { - mutex_unlock(&kvm->slots_arch_lock); + return r; } +unlock_err: + mutex_unlock(&kvm->slots_arch_lock); return r; } -- 2.43.0