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

Pull kvm fixes from Paolo Bonzini:
 "ARM:

   - Fix the handling of ZCR_EL2 in NV VMs

   - Pick the correct translation regime when doing a PTW on the back of
     a SEA

   - Prevent userspace from injecting an event into a vcpu that isn't
     initialised yet

   - Move timer save/restore to the sysreg handling code, fixing EL2
     timer access in the process

   - Add FGT-based trapping of MDSCR_EL1 to reduce the overhead of debug

   - Fix trapping configuration when the host isn't GICv3

   - Improve the detection of HCR_EL2.E2H being RES1

   - Drop a spurious 'break' statement in the S1 PTW

   - Don't try to access SPE when owned by EL3

  Documentation updates:

   - Document the failure modes of event injection

   - Document that a GICv3 guest can be created on a GICv5 host with
     FEAT_GCIE_LEGACY

  Selftest improvements:

   - Add a selftest for the effective value of HCR_EL2.AMO

   - Address build warning in the timer selftest when building with
     clang

   - Teach irqfd selftests about non-x86 architectures

   - Add missing sysregs to the set_id_regs selftest

   - Fix vcpu allocation in the vgic_lpi_stress selftest

   - Correctly enable interrupts in the vgic_lpi_stress selftest

  x86:

   - Expand the KVM_PRE_FAULT_MEMORY selftest to add a regression test
     for the bug fixed by commit 3ccbf6f47098 ("KVM: x86/mmu: Return
     -EAGAIN if userspace deletes/moves memslot during prefault")

   - Don't try to get PMU capabilities from perf when running a CPU with
     hybrid CPUs/PMUs, as perf will rightly WARN.

  guest_memfd:

   - Rework KVM_CAP_GUEST_MEMFD_MMAP (newly introduced in 6.18) into a
     more generic KVM_CAP_GUEST_MEMFD_FLAGS

   - Add a guest_memfd INIT_SHARED flag and require userspace to
     explicitly set said flag to initialize memory as SHARED,
     irrespective of MMAP.

     The behavior merged in 6.18 is that enabling mmap() implicitly
     initializes memory as SHARED, which would result in an ABI
     collision for x86 CoCo VMs as their memory is currently always
     initialized PRIVATE.

   - Allow mmap() on guest_memfd for x86 CoCo VMs, i.e. on VMs with
     private memory, to enable testing such setups, i.e. to hopefully
     flush out any other lurking ABI issues before 6.18 is officially
     released.

   - Add testcases to the guest_memfd selftest to cover guest_memfd
     without MMAP, and host userspace accesses to mmap()'d private
     memory"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (46 commits)
  arm64: Revamp HCR_EL2.E2H RES1 detection
  KVM: arm64: nv: Use FGT write trap of MDSCR_EL1 when available
  KVM: arm64: Compute per-vCPU FGTs at vcpu_load()
  KVM: arm64: selftests: Fix misleading comment about virtual timer encoding
  KVM: arm64: selftests: Add an E2H=0-specific configuration to get_reg_list
  KVM: arm64: selftests: Make dependencies on VHE-specific registers explicit
  KVM: arm64: Kill leftovers of ad-hoc timer userspace access
  KVM: arm64: Fix WFxT handling of nested virt
  KVM: arm64: Move CNT*CT_EL0 userspace accessors to generic infrastructure
  KVM: arm64: Move CNT*_CVAL_EL0 userspace accessors to generic infrastructure
  KVM: arm64: Move CNT*_CTL_EL0 userspace accessors to generic infrastructure
  KVM: arm64: Add timer UAPI workaround to sysreg infrastructure
  KVM: arm64: Make timer_set_offset() generally accessible
  KVM: arm64: Replace timer context vcpu pointer with timer_id
  KVM: arm64: Introduce timer_context_to_vcpu() helper
  KVM: arm64: Hide CNTHV_*_EL2 from userspace for nVHE guests
  Documentation: KVM: Update GICv3 docs for GICv5 hosts
  KVM: arm64: gic-v3: Only set ICH_HCR traps for v2-on-v3 or v3 guests
  KVM: arm64: selftests: Actually enable IRQs in vgic_lpi_stress
  KVM: arm64: selftests: Allocate vcpus with correct size
  ...

1 files changed, 114 insertions, 17 deletions

diff --git a/tools/testing/selftests/kvm/pre_fault_memory_test.c b/tools/testing/selftests/kvm/pre_fault_memory_test.c
index 0350a8896a2f..f04768c1d2e4 100644
--- a/tools/testing/selftests/kvm/pre_fault_memory_test.c
+++ b/tools/testing/selftests/kvm/pre_fault_memory_test.c
@@ -10,6 +10,7 @@
 #include <test_util.h>
 #include <kvm_util.h>
 #include <processor.h>
+#include <pthread.h>
 
 /* Arbitrarily chosen values */
 #define TEST_SIZE		(SZ_2M + PAGE_SIZE)
@@ -30,18 +31,66 @@ static void guest_code(uint64_t base_gpa)
 	GUEST_DONE();
 }
 
-static void pre_fault_memory(struct kvm_vcpu *vcpu, u64 gpa, u64 size,
-			     u64 left)
+struct slot_worker_data {
+	struct kvm_vm *vm;
+	u64 gpa;
+	uint32_t flags;
+	bool worker_ready;
+	bool prefault_ready;
+	bool recreate_slot;
+};
+
+static void *delete_slot_worker(void *__data)
+{
+	struct slot_worker_data *data = __data;
+	struct kvm_vm *vm = data->vm;
+
+	WRITE_ONCE(data->worker_ready, true);
+
+	while (!READ_ONCE(data->prefault_ready))
+		cpu_relax();
+
+	vm_mem_region_delete(vm, TEST_SLOT);
+
+	while (!READ_ONCE(data->recreate_slot))
+		cpu_relax();
+
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, data->gpa,
+				    TEST_SLOT, TEST_NPAGES, data->flags);
+
+	return NULL;
+}
+
+static void pre_fault_memory(struct kvm_vcpu *vcpu, u64 base_gpa, u64 offset,
+			     u64 size, u64 expected_left, bool private)
 {
 	struct kvm_pre_fault_memory range = {
-		.gpa = gpa,
+		.gpa = base_gpa + offset,
 		.size = size,
 		.flags = 0,
 	};
-	u64 prev;
+	struct slot_worker_data data = {
+		.vm = vcpu->vm,
+		.gpa = base_gpa,
+		.flags = private ? KVM_MEM_GUEST_MEMFD : 0,
+	};
+	bool slot_recreated = false;
+	pthread_t slot_worker;
 	int ret, save_errno;
+	u64 prev;
+
+	/*
+	 * Concurrently delete (and recreate) the slot to test KVM's handling
+	 * of a racing memslot deletion with prefaulting.
+	 */
+	pthread_create(&slot_worker, NULL, delete_slot_worker, &data);
 
-	do {
+	while (!READ_ONCE(data.worker_ready))
+		cpu_relax();
+
+	WRITE_ONCE(data.prefault_ready, true);
+
+	for (;;) {
 		prev = range.size;
 		ret = __vcpu_ioctl(vcpu, KVM_PRE_FAULT_MEMORY, &range);
 		save_errno = errno;
@@ -49,18 +98,65 @@ static void pre_fault_memory(struct kvm_vcpu *vcpu, u64 gpa, u64 size,
 			    "%sexpecting range.size to change on %s",
 			    ret < 0 ? "not " : "",
 			    ret < 0 ? "failure" : "success");
-	} while (ret >= 0 ? range.size : save_errno == EINTR);
 
-	TEST_ASSERT(range.size == left,
-		    "Completed with %lld bytes left, expected %" PRId64,
-		    range.size, left);
+		/*
+		 * Immediately retry prefaulting if KVM was interrupted by an
+		 * unrelated signal/event.
+		 */
+		if (ret < 0 && save_errno == EINTR)
+			continue;
+
+		/*
+		 * Tell the worker to recreate the slot in order to complete
+		 * prefaulting (if prefault didn't already succeed before the
+		 * slot was deleted) and/or to prepare for the next testcase.
+		 * Wait for the worker to exit so that the next invocation of
+		 * prefaulting is guaranteed to complete (assuming no KVM bugs).
+		 */
+		if (!slot_recreated) {
+			WRITE_ONCE(data.recreate_slot, true);
+			pthread_join(slot_worker, NULL);
+			slot_recreated = true;
+
+			/*
+			 * Retry prefaulting to get a stable result, i.e. to
+			 * avoid seeing random EAGAIN failures.  Don't retry if
+			 * prefaulting already succeeded, as KVM disallows
+			 * prefaulting with size=0, i.e. blindly retrying would
+			 * result in test failures due to EINVAL.  KVM should
+			 * always return success if all bytes are prefaulted,
+			 * i.e. there is no need to guard against EAGAIN being
+			 * returned.
+			 */
+			if (range.size)
+				continue;
+		}
+
+		/*
+		 * All done if there are no remaining bytes to prefault, or if
+		 * prefaulting failed (EINTR was handled above, and EAGAIN due
+		 * to prefaulting a memslot that's being actively deleted should
+		 * be impossible since the memslot has already been recreated).
+		 */
+		if (!range.size || ret < 0)
+			break;
+	}
 
-	if (left == 0)
-		__TEST_ASSERT_VM_VCPU_IOCTL(!ret, "KVM_PRE_FAULT_MEMORY", ret, vcpu->vm);
+	TEST_ASSERT(range.size == expected_left,
+		    "Completed with %llu bytes left, expected %lu",
+		    range.size, expected_left);
+
+	/*
+	 * Assert success if prefaulting the entire range should succeed, i.e.
+	 * complete with no bytes remaining.  Otherwise prefaulting should have
+	 * failed due to ENOENT (due to RET_PF_EMULATE for emulated MMIO when
+	 * no memslot exists).
+	 */
+	if (!expected_left)
+		TEST_ASSERT_VM_VCPU_IOCTL(!ret, KVM_PRE_FAULT_MEMORY, ret, vcpu->vm);
 	else
-		/* No memory slot causes RET_PF_EMULATE. it results in -ENOENT. */
-		__TEST_ASSERT_VM_VCPU_IOCTL(ret && save_errno == ENOENT,
-					    "KVM_PRE_FAULT_MEMORY", ret, vcpu->vm);
+		TEST_ASSERT_VM_VCPU_IOCTL(ret && save_errno == ENOENT,
+					  KVM_PRE_FAULT_MEMORY, ret, vcpu->vm);
 }
 
 static void __test_pre_fault_memory(unsigned long vm_type, bool private)
@@ -97,9 +193,10 @@ static void __test_pre_fault_memory(unsigned long vm_type, bool private)
 
 	if (private)
 		vm_mem_set_private(vm, guest_test_phys_mem, TEST_SIZE);
-	pre_fault_memory(vcpu, guest_test_phys_mem, SZ_2M, 0);
-	pre_fault_memory(vcpu, guest_test_phys_mem + SZ_2M, PAGE_SIZE * 2, PAGE_SIZE);
-	pre_fault_memory(vcpu, guest_test_phys_mem + TEST_SIZE, PAGE_SIZE, PAGE_SIZE);
+
+	pre_fault_memory(vcpu, guest_test_phys_mem, 0, SZ_2M, 0, private);
+	pre_fault_memory(vcpu, guest_test_phys_mem, SZ_2M, PAGE_SIZE * 2, PAGE_SIZE, private);
+	pre_fault_memory(vcpu, guest_test_phys_mem, TEST_SIZE, PAGE_SIZE, PAGE_SIZE, private);
 
 	vcpu_args_set(vcpu, 1, guest_test_virt_mem);
 	vcpu_run(vcpu);