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

Documentation/virt/kvm/api.rst

···
   #define KVM_X86_DEFAULT_VM	0
   #define KVM_X86_SW_PROTECTED_VM	1
 
+Note, KVM_X86_SW_PROTECTED_VM is currently only for development and testing.
+Do not use KVM_X86_SW_PROTECTED_VM for "real" VMs, and especially not in
+production.  The behavior and effective ABI for software-protected VMs is
+unstable.
+
 9. Known KVM API problems
 =========================
 

arch/x86/kvm/Kconfig

···
 	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".
 

arch/x86/kvm/mmu/mmu.c

···
 	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;
···
 
 	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;
 }
···
 	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);
 }

arch/x86/kvm/svm/sev.c

···
 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
···
 	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);
···
 		goto e_free;
 	}
 
+	/*
+	 * 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.  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);
-
-	/*
-	 * 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.
-	 */
-	sev_clflush_pages(region->pages, region->npages);
 
 	return ret;
 

arch/x86/kvm/x86.c

···
 {
 	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)
···
 
 	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;
 

include/linux/kvm_host.h

···
 		return 1;
 	return 0;
 }
+
+/*
+ * This lockless version of the range-based retry check *must* be paired with a
+ * call to the locked version after acquiring mmu_lock, i.e. this is safe to
+ * use only as a pre-check to avoid contending mmu_lock.  This version *will*
+ * get false negatives and false positives.
+ */
+static inline bool mmu_invalidate_retry_gfn_unsafe(struct kvm *kvm,
+						   unsigned long mmu_seq,
+						   gfn_t gfn)
+{
+	/*
+	 * Use READ_ONCE() to ensure the in-progress flag and sequence counter
+	 * are always read from memory, e.g. so that checking for retry in a
+	 * loop won't result in an infinite retry loop.  Don't force loads for
+	 * start+end, as the key to avoiding infinite retry loops is observing
+	 * the 1=>0 transition of in-progress, i.e. getting false negatives
+	 * due to stale start+end values is acceptable.
+	 */
+	if (unlikely(READ_ONCE(kvm->mmu_invalidate_in_progress)) &&
+	    gfn >= kvm->mmu_invalidate_range_start &&
+	    gfn < kvm->mmu_invalidate_range_end)
+		return true;
+
+	return READ_ONCE(kvm->mmu_invalidate_seq) != mmu_seq;
+}
 #endif
 
 #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING

tools/testing/selftests/kvm/set_memory_region_test.c

···
 	}
 
 	if (supported_flags & KVM_MEM_GUEST_MEMFD) {
+		int guest_memfd = vm_create_guest_memfd(vm, MEM_REGION_SIZE, 0);
+
 		r = __vm_set_user_memory_region2(vm, 0,
 						 KVM_MEM_LOG_DIRTY_PAGES | KVM_MEM_GUEST_MEMFD,
-						 0, MEM_REGION_SIZE, NULL, 0, 0);
+						 0, MEM_REGION_SIZE, NULL, guest_memfd, 0);
 		TEST_ASSERT(r && errno == EINVAL,
 			    "KVM_SET_USER_MEMORY_REGION2 should have failed, dirty logging private memory is unsupported");
+
+		r = __vm_set_user_memory_region2(vm, 0,
+						 KVM_MEM_READONLY | KVM_MEM_GUEST_MEMFD,
+						 0, MEM_REGION_SIZE, NULL, guest_memfd, 0);
+		TEST_ASSERT(r && errno == EINVAL,
+			    "KVM_SET_USER_MEMORY_REGION2 should have failed, read-only GUEST_MEMFD memslots are unsupported");
+
+		close(guest_memfd);
 	}
 }
 

virt/kvm/kvm_main.c

···
 		valid_flags &= ~KVM_MEM_LOG_DIRTY_PAGES;
 
 #ifdef __KVM_HAVE_READONLY_MEM
-	valid_flags |= KVM_MEM_READONLY;
+	/*
+	 * GUEST_MEMFD is incompatible with read-only memslots, as writes to
+	 * read-only memslots have emulated MMIO, not page fault, semantics,
+	 * and KVM doesn't allow emulated MMIO for private memory.
+	 */
+	if (!(mem->flags & KVM_MEM_GUEST_MEMFD))
+		valid_flags |= KVM_MEM_READONLY;
 #endif
 
 	if (mem->flags & ~valid_flags)