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

Pull x86 kvm fixes from Paolo Bonzini:

 - Avoid freeing stack-allocated node in kvm_async_pf_queue_task

 - Clear XSTATE_BV[i] in guest XSAVE state whenever XFD[i]=1

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  selftests: kvm: Verify TILELOADD actually #NM faults when XFD[18]=1
  selftests: kvm: try getting XFD and XSAVE state out of sync
  selftests: kvm: replace numbered sync points with actions
  x86/fpu: Clear XSTATE_BV[i] in guest XSAVE state whenever XFD[i]=1
  x86/kvm: Avoid freeing stack-allocated node in kvm_async_pf_queue_task

Author: torvalds

arch/x86/kernel/fpu/core.c

@@ -319,10 +319,29 @@ EXPORT_SYMBOL_FOR_KVM(fpu_enable_guest_xfd_features);
 #ifdef CONFIG_X86_64
 void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd)
 {
+	struct fpstate *fpstate = guest_fpu->fpstate;
+
 	fpregs_lock();
-	guest_fpu->fpstate->xfd = xfd;
-	if (guest_fpu->fpstate->in_use)
-		xfd_update_state(guest_fpu->fpstate);
+
+	/*
+	 * KVM's guest ABI is that setting XFD[i]=1 *can* immediately revert the
+	 * save state to its initial configuration.  Likewise, KVM_GET_XSAVE does
+	 * the same as XSAVE and returns XSTATE_BV[i]=0 whenever XFD[i]=1.
+	 *
+	 * If the guest's FPU state is in hardware, just update XFD: the XSAVE
+	 * in fpu_swap_kvm_fpstate will clear XSTATE_BV[i] whenever XFD[i]=1.
+	 *
+	 * If however the guest's FPU state is NOT resident in hardware, clear
+	 * disabled components in XSTATE_BV now, or a subsequent XRSTOR will
+	 * attempt to load disabled components and generate #NM _in the host_.
+	 */
+	if (xfd && test_thread_flag(TIF_NEED_FPU_LOAD))
+		fpstate->regs.xsave.header.xfeatures &= ~xfd;
+
+	fpstate->xfd = xfd;
+	if (fpstate->in_use)
+		xfd_update_state(fpstate);
+
 	fpregs_unlock();
 }
 EXPORT_SYMBOL_FOR_KVM(fpu_update_guest_xfd);
@@ -430,6 +449,13 @@ int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf,
 	if (ustate->xsave.header.xfeatures & ~xcr0)
 		return -EINVAL;
 
+	/*
+	 * Disabled features must be in their initial state, otherwise XRSTOR
+	 * causes an exception.
+	 */
+	if (WARN_ON_ONCE(ustate->xsave.header.xfeatures & kstate->xfd))
+		return -EINVAL;
+
 	/*
 	 * Nullify @vpkru to preserve its current value if PKRU's bit isn't set
 	 * in the header.  KVM's odd ABI is to leave PKRU untouched in this

arch/x86/kernel/kvm.c

@@ -89,6 +89,7 @@ struct kvm_task_sleep_node {
 	struct swait_queue_head wq;
 	u32 token;
 	int cpu;
+	bool dummy;
 };
 
 static struct kvm_task_sleep_head {
@@ -120,15 +121,26 @@ static bool kvm_async_pf_queue_task(u32 token, struct kvm_task_sleep_node *n)
 	raw_spin_lock(&b->lock);
 	e = _find_apf_task(b, token);
 	if (e) {
-		/* dummy entry exist -> wake up was delivered ahead of PF */
-		hlist_del(&e->link);
+		struct kvm_task_sleep_node *dummy = NULL;
+
+		/*
+		 * The entry can either be a 'dummy' entry (which is put on the
+		 * list when wake-up happens ahead of APF handling completion)
+		 * or a token from another task which should not be touched.
+		 */
+		if (e->dummy) {
+			hlist_del(&e->link);
+			dummy = e;
+		}
+
 		raw_spin_unlock(&b->lock);
-		kfree(e);
+		kfree(dummy);
 		return false;
 	}
 
 	n->token = token;
 	n->cpu = smp_processor_id();
+	n->dummy = false;
 	init_swait_queue_head(&n->wq);
 	hlist_add_head(&n->link, &b->list);
 	raw_spin_unlock(&b->lock);
@@ -231,6 +243,7 @@ static void kvm_async_pf_task_wake(u32 token)
 		}
 		dummy->token = token;
 		dummy->cpu = smp_processor_id();
+		dummy->dummy = true;
 		init_swait_queue_head(&dummy->wq);
 		hlist_add_head(&dummy->link, &b->list);
 		dummy = NULL;

arch/x86/kvm/x86.c

@@ -5807,9 +5807,18 @@ static int kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
 static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 					struct kvm_xsave *guest_xsave)
 {
+	union fpregs_state *xstate = (union fpregs_state *)guest_xsave->region;
+
 	if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
 		return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0;
 
+	/*
+	 * For backwards compatibility, do not expect disabled features to be in
+	 * their initial state.  XSTATE_BV[i] must still be cleared whenever
+	 * XFD[i]=1, or XRSTOR would cause a #NM.
+	 */
+	xstate->xsave.header.xfeatures &= ~vcpu->arch.guest_fpu.fpstate->xfd;
+
 	return fpu_copy_uabi_to_guest_fpstate(&vcpu->arch.guest_fpu,
 					      guest_xsave->region,
 					      kvm_caps.supported_xcr0,

tools/testing/selftests/kvm/x86/amx_test.c

@@ -69,6 +69,12 @@ static inline void __tileloadd(void *tile)
 		     : : "a"(tile), "d"(0));
 }
 
+static inline int tileloadd_safe(void *tile)
+{
+	return kvm_asm_safe(".byte 0xc4,0xe2,0x7b,0x4b,0x04,0x10",
+			    "a"(tile), "d"(0));
+}
+
 static inline void __tilerelease(void)
 {
 	asm volatile(".byte 0xc4, 0xe2, 0x78, 0x49, 0xc0" ::);
@@ -124,27 +130,52 @@ static void set_tilecfg(struct tile_config *cfg)
 	}
 }
 
+enum {
+	/* Retrieve TMM0 from guest, stash it for TEST_RESTORE_TILEDATA */
+	TEST_SAVE_TILEDATA = 1,
+
+	/* Check TMM0 against tiledata */
+	TEST_COMPARE_TILEDATA = 2,
+
+	/* Restore TMM0 from earlier save */
+	TEST_RESTORE_TILEDATA = 4,
+
+	/* Full VM save/restore */
+	TEST_SAVE_RESTORE = 8,
+};
+
 static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg,
 						    struct tile_data *tiledata,
 						    struct xstate *xstate)
 {
+	int vector;
+
 	GUEST_ASSERT(this_cpu_has(X86_FEATURE_XSAVE) &&
 		     this_cpu_has(X86_FEATURE_OSXSAVE));
 	check_xtile_info();
-	GUEST_SYNC(1);
+	GUEST_SYNC(TEST_SAVE_RESTORE);
 
 	/* xfd=0, enable amx */
 	wrmsr(MSR_IA32_XFD, 0);
-	GUEST_SYNC(2);
+	GUEST_SYNC(TEST_SAVE_RESTORE);
 	GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == 0);
 	set_tilecfg(amx_cfg);
 	__ldtilecfg(amx_cfg);
-	GUEST_SYNC(3);
+	GUEST_SYNC(TEST_SAVE_RESTORE);
 	/* Check save/restore when trap to userspace */
 	__tileloadd(tiledata);
-	GUEST_SYNC(4);
+	GUEST_SYNC(TEST_SAVE_TILEDATA | TEST_COMPARE_TILEDATA | TEST_SAVE_RESTORE);
+
+	/* xfd=0x40000, disable amx tiledata */
+	wrmsr(MSR_IA32_XFD, XFEATURE_MASK_XTILE_DATA);
+
+	/* host tries setting tiledata while guest XFD is set */
+	GUEST_SYNC(TEST_RESTORE_TILEDATA);
+	GUEST_SYNC(TEST_SAVE_RESTORE);
+
+	wrmsr(MSR_IA32_XFD, 0);
 	__tilerelease();
-	GUEST_SYNC(5);
+	GUEST_SYNC(TEST_SAVE_RESTORE);
 	/*
 	 * After XSAVEC, XTILEDATA is cleared in the xstate_bv but is set in
 	 * the xcomp_bv.
@@ -154,6 +185,8 @@ static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg,
 	GUEST_ASSERT(!(xstate->header.xstate_bv & XFEATURE_MASK_XTILE_DATA));
 	GUEST_ASSERT(xstate->header.xcomp_bv & XFEATURE_MASK_XTILE_DATA);
 
+	/* #NM test */
+
 	/* xfd=0x40000, disable amx tiledata */
 	wrmsr(MSR_IA32_XFD, XFEATURE_MASK_XTILE_DATA);
 
@@ -166,32 +199,33 @@ static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg,
 	GUEST_ASSERT(!(xstate->header.xstate_bv & XFEATURE_MASK_XTILE_DATA));
 	GUEST_ASSERT((xstate->header.xcomp_bv & XFEATURE_MASK_XTILE_DATA));
 
-	GUEST_SYNC(6);
+	GUEST_SYNC(TEST_SAVE_RESTORE);
 	GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILE_DATA);
 	set_tilecfg(amx_cfg);
 	__ldtilecfg(amx_cfg);
-	/* Trigger #NM exception */
-	__tileloadd(tiledata);
-	GUEST_SYNC(10);
 
-	GUEST_DONE();
-}
+	/* Trigger #NM exception */
+	vector = tileloadd_safe(tiledata);
+	__GUEST_ASSERT(vector == NM_VECTOR,
+		       "Wanted #NM on tileloadd with XFD[18]=1, got %s",
+		       ex_str(vector));
 
-void guest_nm_handler(struct ex_regs *regs)
-{
-	/* Check if #NM is triggered by XFEATURE_MASK_XTILE_DATA */
-	GUEST_SYNC(7);
 	GUEST_ASSERT(!(get_cr0() & X86_CR0_TS));
 	GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILE_DATA);
 	GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILE_DATA);
-	GUEST_SYNC(8);
+	GUEST_SYNC(TEST_SAVE_RESTORE);
 	GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILE_DATA);
 	GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILE_DATA);
 	/* Clear xfd_err */
 	wrmsr(MSR_IA32_XFD_ERR, 0);
 	/* xfd=0, enable amx */
 	wrmsr(MSR_IA32_XFD, 0);
-	GUEST_SYNC(9);
+	GUEST_SYNC(TEST_SAVE_RESTORE);
+
+	__tileloadd(tiledata);
+	GUEST_SYNC(TEST_COMPARE_TILEDATA | TEST_SAVE_RESTORE);
+
+	GUEST_DONE();
 }
 
 int main(int argc, char *argv[])
@@ -200,10 +234,10 @@ int main(int argc, char *argv[])
 	struct kvm_vcpu *vcpu;
 	struct kvm_vm *vm;
 	struct kvm_x86_state *state;
+	struct kvm_x86_state *tile_state = NULL;
 	int xsave_restore_size;
 	vm_vaddr_t amx_cfg, tiledata, xstate;
 	struct ucall uc;
-	u32 amx_offset;
 	int ret;
 
 	/*
@@ -228,9 +262,6 @@ int main(int argc, char *argv[])
 
 	vcpu_regs_get(vcpu, &regs1);
 
-	/* Register #NM handler */
-	vm_install_exception_handler(vm, NM_VECTOR, guest_nm_handler);
-
 	/* amx cfg for guest_code */
 	amx_cfg = vm_vaddr_alloc_page(vm);
 	memset(addr_gva2hva(vm, amx_cfg), 0x0, getpagesize());
@@ -244,6 +275,7 @@ int main(int argc, char *argv[])
 	memset(addr_gva2hva(vm, xstate), 0, PAGE_SIZE * DIV_ROUND_UP(XSAVE_SIZE, PAGE_SIZE));
 	vcpu_args_set(vcpu, 3, amx_cfg, tiledata, xstate);
 
+	int iter = 0;
 	for (;;) {
 		vcpu_run(vcpu);
 		TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
@@ -253,37 +285,47 @@ int main(int argc, char *argv[])
 			REPORT_GUEST_ASSERT(uc);
 			/* NOT REACHED */
 		case UCALL_SYNC:
-			switch (uc.args[1]) {
-			case 1:
-			case 2:
-			case 3:
-			case 5:
-			case 6:
-			case 7:
-			case 8:
-				fprintf(stderr, "GUEST_SYNC(%ld)\n", uc.args[1]);
-				break;
-			case 4:
-			case 10:
-				fprintf(stderr,
-				"GUEST_SYNC(%ld), check save/restore status\n", uc.args[1]);
+			++iter;
+			if (uc.args[1] & TEST_SAVE_TILEDATA) {
+				fprintf(stderr, "GUEST_SYNC #%d, save tiledata\n", iter);
+				tile_state = vcpu_save_state(vcpu);
+			}
+			if (uc.args[1] & TEST_COMPARE_TILEDATA) {
+				fprintf(stderr, "GUEST_SYNC #%d, check TMM0 contents\n", iter);
 
 				/* Compacted mode, get amx offset by xsave area
 				 * size subtract 8K amx size.
 				 */
-				amx_offset = xsave_restore_size - NUM_TILES*TILE_SIZE;
-				state = vcpu_save_state(vcpu);
-				void *amx_start = (void *)state->xsave + amx_offset;
+				u32 amx_offset = xsave_restore_size - NUM_TILES*TILE_SIZE;
+				void *amx_start = (void *)tile_state->xsave + amx_offset;
 				void *tiles_data = (void *)addr_gva2hva(vm, tiledata);
 				/* Only check TMM0 register, 1 tile */
 				ret = memcmp(amx_start, tiles_data, TILE_SIZE);
 				TEST_ASSERT(ret == 0, "memcmp failed, ret=%d", ret);
+			}
+			if (uc.args[1] & TEST_RESTORE_TILEDATA) {
+				fprintf(stderr, "GUEST_SYNC #%d, before KVM_SET_XSAVE\n", iter);
+				vcpu_xsave_set(vcpu, tile_state->xsave);
+				fprintf(stderr, "GUEST_SYNC #%d, after KVM_SET_XSAVE\n", iter);
+			}
+			if (uc.args[1] & TEST_SAVE_RESTORE) {
+				fprintf(stderr, "GUEST_SYNC #%d, save/restore VM state\n", iter);
+				state = vcpu_save_state(vcpu);
+				memset(&regs1, 0, sizeof(regs1));
+				vcpu_regs_get(vcpu, &regs1);
+
+				kvm_vm_release(vm);
+
+				/* Restore state in a new VM.  */
+				vcpu = vm_recreate_with_one_vcpu(vm);
+				vcpu_load_state(vcpu, state);
 				kvm_x86_state_cleanup(state);
-				break;
-			case 9:
-				fprintf(stderr,
-				"GUEST_SYNC(%ld), #NM exception and enable amx\n", uc.args[1]);
-				break;
+
+				memset(&regs2, 0, sizeof(regs2));
+				vcpu_regs_get(vcpu, &regs2);
+				TEST_ASSERT(!memcmp(&regs1, &regs2, sizeof(regs2)),
+					    "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx",
+					    (ulong) regs2.rdi, (ulong) regs2.rsi);
 			}
 			break;
 		case UCALL_DONE:
@@ -293,22 +335,6 @@ int main(int argc, char *argv[])
 			TEST_FAIL("Unknown ucall %lu", uc.cmd);
 		}
 
-		state = vcpu_save_state(vcpu);
-		memset(&regs1, 0, sizeof(regs1));
-		vcpu_regs_get(vcpu, &regs1);
-
-		kvm_vm_release(vm);
-
-		/* Restore state in a new VM.  */
-		vcpu = vm_recreate_with_one_vcpu(vm);
-		vcpu_load_state(vcpu, state);
-		kvm_x86_state_cleanup(state);
-
-		memset(&regs2, 0, sizeof(regs2));
-		vcpu_regs_get(vcpu, &regs2);
-		TEST_ASSERT(!memcmp(&regs1, &regs2, sizeof(regs2)),
-			    "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx",
-			    (ulong) regs2.rdi, (ulong) regs2.rsi);
 	}
 done:
 	kvm_vm_free(vm);