Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm fixes from Paolo Bonzini:
 "KVM GUEST_MEMFD fixes for 6.8:

   - Make KVM_MEM_GUEST_MEMFD mutually exclusive with KVM_MEM_READONLY
     to avoid creating an inconsistent ABI (KVM_MEM_GUEST_MEMFD is not
     writable from userspace, so there would be no way to write to a
     read-only guest_memfd).

   - Update documentation for KVM_SW_PROTECTED_VM to make it abundantly
     clear that such VMs are purely for development and testing.

   - Limit KVM_SW_PROTECTED_VM guests to the TDP MMU, as the long term
     plan is to support confidential VMs with deterministic private
     memory (SNP and TDX) only in the TDP MMU.

   - Fix a bug in a GUEST_MEMFD dirty logging test that caused false
     passes.

  x86 fixes:

   - Fix missing marking of a guest page as dirty when emulating an
     atomic access.

   - Check for mmu_notifier invalidation events before faulting in the
     pfn, and before acquiring mmu_lock, to avoid unnecessary work and
     lock contention with preemptible kernels (including
     CONFIG_PREEMPT_DYNAMIC in non-preemptible mode).

   - Disable AMD DebugSwap by default, it breaks VMSA signing and will
     be re-enabled with a better VM creation API in 6.10.

   - Do the cache flush of converted pages in svm_register_enc_region()
     before dropping kvm->lock, to avoid a race with unregistering of
     the same region and the consequent use-after-free issue"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  SEV: disable SEV-ES DebugSwap by default
  KVM: x86/mmu: Retry fault before acquiring mmu_lock if mapping is changing
  KVM: SVM: Flush pages under kvm->lock to fix UAF in svm_register_enc_region()
  KVM: selftests: Add a testcase to verify GUEST_MEMFD and READONLY are exclusive
  KVM: selftests: Create GUEST_MEMFD for relevant invalid flags testcases
  KVM: x86/mmu: Restrict KVM_SW_PROTECTED_VM to the TDP MMU
  KVM: x86: Update KVM_SW_PROTECTED_VM docs to make it clear they're a WIP
  KVM: Make KVM_MEM_GUEST_MEMFD mutually exclusive with KVM_MEM_READONLY
  KVM: x86: Mark target gfn of emulated atomic instruction as dirty

4 files changed, 71 insertions, 13 deletions

diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 87e3da7b0439..65ed14b6540b 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -80,9 +80,10 @@ config KVM_SW_PROTECTED_VM
 	depends on KVM && X86_64
 	select KVM_GENERIC_PRIVATE_MEM
 	help
-	  Enable support for KVM software-protected VMs.  Currently "protected"
-	  means the VM can be backed with memory provided by
-	  KVM_CREATE_GUEST_MEMFD.
+	  Enable support for KVM software-protected VMs.  Currently, software-
+	  protected VMs are purely a development and testing vehicle for
+	  KVM_CREATE_GUEST_MEMFD.  Attempting to run a "real" VM workload as a
+	  software-protected VM will fail miserably.
 
 	  If unsure, say "N".
 
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 2d6cdeab1f8a..0544700ca50b 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4405,6 +4405,31 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
 	fault->mmu_seq = vcpu->kvm->mmu_invalidate_seq;
 	smp_rmb();
 
+	/*
+	 * Check for a relevant mmu_notifier invalidation event before getting
+	 * the pfn from the primary MMU, and before acquiring mmu_lock.
+	 *
+	 * For mmu_lock, if there is an in-progress invalidation and the kernel
+	 * allows preemption, the invalidation task may drop mmu_lock and yield
+	 * in response to mmu_lock being contended, which is *very* counter-
+	 * productive as this vCPU can't actually make forward progress until
+	 * the invalidation completes.
+	 *
+	 * Retrying now can also avoid unnessary lock contention in the primary
+	 * MMU, as the primary MMU doesn't necessarily hold a single lock for
+	 * the duration of the invalidation, i.e. faulting in a conflicting pfn
+	 * can cause the invalidation to take longer by holding locks that are
+	 * needed to complete the invalidation.
+	 *
+	 * Do the pre-check even for non-preemtible kernels, i.e. even if KVM
+	 * will never yield mmu_lock in response to contention, as this vCPU is
+	 * *guaranteed* to need to retry, i.e. waiting until mmu_lock is held
+	 * to detect retry guarantees the worst case latency for the vCPU.
+	 */
+	if (fault->slot &&
+	    mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn))
+		return RET_PF_RETRY;
+
 	ret = __kvm_faultin_pfn(vcpu, fault);
 	if (ret != RET_PF_CONTINUE)
 		return ret;
@@ -4415,6 +4440,18 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
 	if (unlikely(!fault->slot))
 		return kvm_handle_noslot_fault(vcpu, fault, access);
 
+	/*
+	 * Check again for a relevant mmu_notifier invalidation event purely to
+	 * avoid contending mmu_lock.  Most invalidations will be detected by
+	 * the previous check, but checking is extremely cheap relative to the
+	 * overall cost of failing to detect the invalidation until after
+	 * mmu_lock is acquired.
+	 */
+	if (mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn)) {
+		kvm_release_pfn_clean(fault->pfn);
+		return RET_PF_RETRY;
+	}
+
 	return RET_PF_CONTINUE;
 }
 
@@ -4442,6 +4479,11 @@ static bool is_page_fault_stale(struct kvm_vcpu *vcpu,
 	if (!sp && kvm_test_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu))
 		return true;
 
+	/*
+	 * Check for a relevant mmu_notifier invalidation event one last time
+	 * now that mmu_lock is held, as the "unsafe" checks performed without
+	 * holding mmu_lock can get false negatives.
+	 */
 	return fault->slot &&
 	       mmu_invalidate_retry_gfn(vcpu->kvm, fault->mmu_seq, fault->gfn);
 }
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index f760106c31f8..a8ce5226b3b5 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -57,7 +57,7 @@ static bool sev_es_enabled = true;
 module_param_named(sev_es, sev_es_enabled, bool, 0444);
 
 /* enable/disable SEV-ES DebugSwap support */
-static bool sev_es_debug_swap_enabled = true;
+static bool sev_es_debug_swap_enabled = false;
 module_param_named(debug_swap, sev_es_debug_swap_enabled, bool, 0444);
 #else
 #define sev_enabled false
@@ -612,8 +612,11 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm)
 	save->xss  = svm->vcpu.arch.ia32_xss;
 	save->dr6  = svm->vcpu.arch.dr6;
 
-	if (sev_es_debug_swap_enabled)
+	if (sev_es_debug_swap_enabled) {
 		save->sev_features |= SVM_SEV_FEAT_DEBUG_SWAP;
+		pr_warn_once("Enabling DebugSwap with KVM_SEV_ES_INIT. "
+			     "This will not work starting with Linux 6.10\n");
+	}
 
 	pr_debug("Virtual Machine Save Area (VMSA):\n");
 	print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1, save, sizeof(*save), false);
@@ -1975,20 +1978,22 @@ int sev_mem_enc_register_region(struct kvm *kvm,
 		goto e_free;
 	}
 
-	region->uaddr = range->addr;
-	region->size = range->size;
-
-	list_add_tail(&region->list, &sev->regions_list);
-	mutex_unlock(&kvm->lock);
-
 	/*
 	 * The guest may change the memory encryption attribute from C=0 -> C=1
 	 * or vice versa for this memory range. Lets make sure caches are
 	 * flushed to ensure that guest data gets written into memory with
-	 * correct C-bit.
+	 * correct C-bit.  Note, this must be done before dropping kvm->lock,
+	 * as region and its array of pages can be freed by a different task
+	 * once kvm->lock is released.
 	 */
 	sev_clflush_pages(region->pages, region->npages);
 
+	region->uaddr = range->addr;
+	region->size = range->size;
+
+	list_add_tail(&region->list, &sev->regions_list);
+	mutex_unlock(&kvm->lock);
+
 	return ret;
 
 e_free:
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 48a61d283406..e02cc710f56d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4580,7 +4580,7 @@ static bool kvm_is_vm_type_supported(unsigned long type)
 {
 	return type == KVM_X86_DEFAULT_VM ||
 	       (type == KVM_X86_SW_PROTECTED_VM &&
-		IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && tdp_enabled);
+		IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && tdp_mmu_enabled);
 }
 
 int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
@@ -8007,6 +8007,16 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt,
 
 	if (r < 0)
 		return X86EMUL_UNHANDLEABLE;
+
+	/*
+	 * Mark the page dirty _before_ checking whether or not the CMPXCHG was
+	 * successful, as the old value is written back on failure.  Note, for
+	 * live migration, this is unnecessarily conservative as CMPXCHG writes
+	 * back the original value and the access is atomic, but KVM's ABI is
+	 * that all writes are dirty logged, regardless of the value written.
+	 */
+	kvm_vcpu_mark_page_dirty(vcpu, gpa_to_gfn(gpa));
+
 	if (r)
 		return X86EMUL_CMPXCHG_FAILED;