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

Pull kvm updates from Paolo Bonzini:
 "RISCV:

   - Use common KVM implementation of MMU memory caches

   - SBI v0.2 support for Guest

   - Initial KVM selftests support

   - Fix to avoid spurious virtual interrupts after clearing hideleg CSR

   - Update email address for Anup and Atish

  ARM:

   - Simplification of the 'vcpu first run' by integrating it into KVM's
     'pid change' flow

   - Refactoring of the FP and SVE state tracking, also leading to a
     simpler state and less shared data between EL1 and EL2 in the nVHE
     case

   - Tidy up the header file usage for the nvhe hyp object

   - New HYP unsharing mechanism, finally allowing pages to be unmapped
     from the Stage-1 EL2 page-tables

   - Various pKVM cleanups around refcounting and sharing

   - A couple of vgic fixes for bugs that would trigger once the vcpu
     xarray rework is merged, but not sooner

   - Add minimal support for ARMv8.7's PMU extension

   - Rework kvm_pgtable initialisation ahead of the NV work

   - New selftest for IRQ injection

   - Teach selftests about the lack of default IPA space and page sizes

   - Expand sysreg selftest to deal with Pointer Authentication

   - The usual bunch of cleanups and doc update

  s390:

   - fix sigp sense/start/stop/inconsistency

   - cleanups

  x86:

   - Clean up some function prototypes more

   - improved gfn_to_pfn_cache with proper invalidation, used by Xen
     emulation

   - add KVM_IRQ_ROUTING_XEN_EVTCHN and event channel delivery

   - completely remove potential TOC/TOU races in nested SVM consistency
     checks

   - update some PMCs on emulated instructions

   - Intel AMX support (joint work between Thomas and Intel)

   - large MMU cleanups

   - module parameter to disable PMU virtualization

   - cleanup register cache

   - first part of halt handling cleanups

   - Hyper-V enlightened MSR bitmap support for nested hypervisors

  Generic:

   - clean up Makefiles

   - introduce CONFIG_HAVE_KVM_DIRTY_RING

   - optimize memslot lookup using a tree

   - optimize vCPU array usage by converting to xarray"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (268 commits)
  x86/fpu: Fix inline prefix warnings
  selftest: kvm: Add amx selftest
  selftest: kvm: Move struct kvm_x86_state to header
  selftest: kvm: Reorder vcpu_load_state steps for AMX
  kvm: x86: Disable interception for IA32_XFD on demand
  x86/fpu: Provide fpu_sync_guest_vmexit_xfd_state()
  kvm: selftests: Add support for KVM_CAP_XSAVE2
  kvm: x86: Add support for getting/setting expanded xstate buffer
  x86/fpu: Add uabi_size to guest_fpu
  kvm: x86: Add CPUID support for Intel AMX
  kvm: x86: Add XCR0 support for Intel AMX
  kvm: x86: Disable RDMSR interception of IA32_XFD_ERR
  kvm: x86: Emulate IA32_XFD_ERR for guest
  kvm: x86: Intercept #NM for saving IA32_XFD_ERR
  x86/fpu: Prepare xfd_err in struct fpu_guest
  kvm: x86: Add emulation for IA32_XFD
  x86/fpu: Provide fpu_update_guest_xfd() for IA32_XFD emulation
  kvm: x86: Enable dynamic xfeatures at KVM_SET_CPUID2
  x86/fpu: Provide fpu_enable_guest_xfd_features() for KVM
  x86/fpu: Add guest support to xfd_enable_feature()
  ...

3 files changed, 204 insertions, 61 deletions

diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index dd3777ac0443..8dea01ffc5c1 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -206,7 +206,27 @@ void fpu_reset_from_exception_fixup(void)
 }
 
 #if IS_ENABLED(CONFIG_KVM)
-static void __fpstate_reset(struct fpstate *fpstate);
+static void __fpstate_reset(struct fpstate *fpstate, u64 xfd);
+
+static void fpu_init_guest_permissions(struct fpu_guest *gfpu)
+{
+	struct fpu_state_perm *fpuperm;
+	u64 perm;
+
+	if (!IS_ENABLED(CONFIG_X86_64))
+		return;
+
+	spin_lock_irq(&current->sighand->siglock);
+	fpuperm = &current->group_leader->thread.fpu.guest_perm;
+	perm = fpuperm->__state_perm;
+
+	/* First fpstate allocation locks down permissions. */
+	WRITE_ONCE(fpuperm->__state_perm, perm | FPU_GUEST_PERM_LOCKED);
+
+	spin_unlock_irq(&current->sighand->siglock);
+
+	gfpu->perm = perm & ~FPU_GUEST_PERM_LOCKED;
+}
 
 bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu)
 {
@@ -218,12 +238,18 @@ bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu)
 	if (!fpstate)
 		return false;
 
-	__fpstate_reset(fpstate);
+	/* Leave xfd to 0 (the reset value defined by spec) */
+	__fpstate_reset(fpstate, 0);
 	fpstate_init_user(fpstate);
 	fpstate->is_valloc	= true;
 	fpstate->is_guest	= true;
 
-	gfpu->fpstate = fpstate;
+	gfpu->fpstate		= fpstate;
+	gfpu->xfeatures		= fpu_user_cfg.default_features;
+	gfpu->perm		= fpu_user_cfg.default_features;
+	gfpu->uabi_size		= fpu_user_cfg.default_size;
+	fpu_init_guest_permissions(gfpu);
+
 	return true;
 }
 EXPORT_SYMBOL_GPL(fpu_alloc_guest_fpstate);
@@ -243,6 +269,64 @@ void fpu_free_guest_fpstate(struct fpu_guest *gfpu)
 }
 EXPORT_SYMBOL_GPL(fpu_free_guest_fpstate);
 
+/*
+  * fpu_enable_guest_xfd_features - Check xfeatures against guest perm and enable
+  * @guest_fpu:         Pointer to the guest FPU container
+  * @xfeatures:         Features requested by guest CPUID
+  *
+  * Enable all dynamic xfeatures according to guest perm and requested CPUID.
+  *
+  * Return: 0 on success, error code otherwise
+  */
+int fpu_enable_guest_xfd_features(struct fpu_guest *guest_fpu, u64 xfeatures)
+{
+	lockdep_assert_preemption_enabled();
+
+	/* Nothing to do if all requested features are already enabled. */
+	xfeatures &= ~guest_fpu->xfeatures;
+	if (!xfeatures)
+		return 0;
+
+	return __xfd_enable_feature(xfeatures, guest_fpu);
+}
+EXPORT_SYMBOL_GPL(fpu_enable_guest_xfd_features);
+
+#ifdef CONFIG_X86_64
+void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd)
+{
+	fpregs_lock();
+	guest_fpu->fpstate->xfd = xfd;
+	if (guest_fpu->fpstate->in_use)
+		xfd_update_state(guest_fpu->fpstate);
+	fpregs_unlock();
+}
+EXPORT_SYMBOL_GPL(fpu_update_guest_xfd);
+
+/**
+ * fpu_sync_guest_vmexit_xfd_state - Synchronize XFD MSR and software state
+ *
+ * Must be invoked from KVM after a VMEXIT before enabling interrupts when
+ * XFD write emulation is disabled. This is required because the guest can
+ * freely modify XFD and the state at VMEXIT is not guaranteed to be the
+ * same as the state on VMENTER. So software state has to be udpated before
+ * any operation which depends on it can take place.
+ *
+ * Note: It can be invoked unconditionally even when write emulation is
+ * enabled for the price of a then pointless MSR read.
+ */
+void fpu_sync_guest_vmexit_xfd_state(void)
+{
+	struct fpstate *fps = current->thread.fpu.fpstate;
+
+	lockdep_assert_irqs_disabled();
+	if (fpu_state_size_dynamic()) {
+		rdmsrl(MSR_IA32_XFD, fps->xfd);
+		__this_cpu_write(xfd_state, fps->xfd);
+	}
+}
+EXPORT_SYMBOL_GPL(fpu_sync_guest_vmexit_xfd_state);
+#endif /* CONFIG_X86_64 */
+
 int fpu_swap_kvm_fpstate(struct fpu_guest *guest_fpu, bool enter_guest)
 {
 	struct fpstate *guest_fps = guest_fpu->fpstate;
@@ -437,26 +521,28 @@ void fpstate_init_user(struct fpstate *fpstate)
 		fpstate_init_fstate(fpstate);
 }
 
-static void __fpstate_reset(struct fpstate *fpstate)
+static void __fpstate_reset(struct fpstate *fpstate, u64 xfd)
 {
 	/* Initialize sizes and feature masks */
 	fpstate->size		= fpu_kernel_cfg.default_size;
 	fpstate->user_size	= fpu_user_cfg.default_size;
 	fpstate->xfeatures	= fpu_kernel_cfg.default_features;
 	fpstate->user_xfeatures	= fpu_user_cfg.default_features;
-	fpstate->xfd		= init_fpstate.xfd;
+	fpstate->xfd		= xfd;
 }
 
 void fpstate_reset(struct fpu *fpu)
 {
 	/* Set the fpstate pointer to the default fpstate */
 	fpu->fpstate = &fpu->__fpstate;
-	__fpstate_reset(fpu->fpstate);
+	__fpstate_reset(fpu->fpstate, init_fpstate.xfd);
 
 	/* Initialize the permission related info in fpu */
 	fpu->perm.__state_perm		= fpu_kernel_cfg.default_features;
 	fpu->perm.__state_size		= fpu_kernel_cfg.default_size;
 	fpu->perm.__user_state_size	= fpu_user_cfg.default_size;
+	/* Same defaults for guests */
+	fpu->guest_perm = fpu->perm;
 }
 
 static inline void fpu_inherit_perms(struct fpu *dst_fpu)
@@ -467,6 +553,7 @@ static inline void fpu_inherit_perms(struct fpu *dst_fpu)
 		spin_lock_irq(&current->sighand->siglock);
 		/* Fork also inherits the permissions of the parent */
 		dst_fpu->perm = src_fpu->perm;
+		dst_fpu->guest_perm = src_fpu->guest_perm;
 		spin_unlock_irq(&current->sighand->siglock);
 	}
 }
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index d28829403ed0..02b3ddaf4f75 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -1500,35 +1500,13 @@ void fpstate_free(struct fpu *fpu)
 }
 
 /**
- * fpu_install_fpstate - Update the active fpstate in the FPU
- *
- * @fpu:	A struct fpu * pointer
- * @newfps:	A struct fpstate * pointer
- *
- * Returns:	A null pointer if the last active fpstate is the embedded
- *		one or the new fpstate is already installed;
- *		otherwise, a pointer to the old fpstate which has to
- *		be freed by the caller.
- */
-static struct fpstate *fpu_install_fpstate(struct fpu *fpu,
-					   struct fpstate *newfps)
-{
-	struct fpstate *oldfps = fpu->fpstate;
-
-	if (fpu->fpstate == newfps)
-		return NULL;
-
-	fpu->fpstate = newfps;
-	return oldfps != &fpu->__fpstate ? oldfps : NULL;
-}
-
-/**
  * fpstate_realloc - Reallocate struct fpstate for the requested new features
  *
  * @xfeatures:	A bitmap of xstate features which extend the enabled features
  *		of that task
  * @ksize:	The required size for the kernel buffer
  * @usize:	The required size for user space buffers
+ * @guest_fpu:	Pointer to a guest FPU container. NULL for host allocations
  *
  * Note vs. vmalloc(): If the task with a vzalloc()-allocated buffer
  * terminates quickly, vfree()-induced IPIs may be a concern, but tasks
@@ -1537,13 +1515,13 @@ static struct fpstate *fpu_install_fpstate(struct fpu *fpu,
  * Returns: 0 on success, -ENOMEM on allocation error.
  */
 static int fpstate_realloc(u64 xfeatures, unsigned int ksize,
-			   unsigned int usize)
+			   unsigned int usize, struct fpu_guest *guest_fpu)
 {
 	struct fpu *fpu = &current->thread.fpu;
 	struct fpstate *curfps, *newfps = NULL;
 	unsigned int fpsize;
+	bool in_use;
 
-	curfps = fpu->fpstate;
 	fpsize = ksize + ALIGN(offsetof(struct fpstate, regs), 64);
 
 	newfps = vzalloc(fpsize);
@@ -1553,28 +1531,56 @@ static int fpstate_realloc(u64 xfeatures, unsigned int ksize,
 	newfps->user_size = usize;
 	newfps->is_valloc = true;
 
+	/*
+	 * When a guest FPU is supplied, use @guest_fpu->fpstate
+	 * as reference independent whether it is in use or not.
+	 */
+	curfps = guest_fpu ? guest_fpu->fpstate : fpu->fpstate;
+
+	/* Determine whether @curfps is the active fpstate */
+	in_use = fpu->fpstate == curfps;
+
+	if (guest_fpu) {
+		newfps->is_guest = true;
+		newfps->is_confidential = curfps->is_confidential;
+		newfps->in_use = curfps->in_use;
+		guest_fpu->xfeatures |= xfeatures;
+		guest_fpu->uabi_size = usize;
+	}
+
 	fpregs_lock();
 	/*
-	 * Ensure that the current state is in the registers before
-	 * swapping fpstate as that might invalidate it due to layout
-	 * changes.
+	 * If @curfps is in use, ensure that the current state is in the
+	 * registers before swapping fpstate as that might invalidate it
+	 * due to layout changes.
 	 */
-	if (test_thread_flag(TIF_NEED_FPU_LOAD))
+	if (in_use && test_thread_flag(TIF_NEED_FPU_LOAD))
 		fpregs_restore_userregs();
 
 	newfps->xfeatures = curfps->xfeatures | xfeatures;
 	newfps->user_xfeatures = curfps->user_xfeatures | xfeatures;
 	newfps->xfd = curfps->xfd & ~xfeatures;
 
-	curfps = fpu_install_fpstate(fpu, newfps);
-
 	/* Do the final updates within the locked region */
 	xstate_init_xcomp_bv(&newfps->regs.xsave, newfps->xfeatures);
-	xfd_update_state(newfps);
 
+	if (guest_fpu) {
+		guest_fpu->fpstate = newfps;
+		/* If curfps is active, update the FPU fpstate pointer */
+		if (in_use)
+			fpu->fpstate = newfps;
+	} else {
+		fpu->fpstate = newfps;
+	}
+
+	if (in_use)
+		xfd_update_state(fpu->fpstate);
 	fpregs_unlock();
 
-	vfree(curfps);
+	/* Only free valloc'ed state */
+	if (curfps && curfps->is_valloc)
+		vfree(curfps);
+
 	return 0;
 }
 
@@ -1595,7 +1601,7 @@ static int validate_sigaltstack(unsigned int usize)
 	return 0;
 }
 
-static int __xstate_request_perm(u64 permitted, u64 requested)
+static int __xstate_request_perm(u64 permitted, u64 requested, bool guest)
 {
 	/*
 	 * This deliberately does not exclude !XSAVES as we still might
@@ -1605,9 +1611,10 @@ static int __xstate_request_perm(u64 permitted, u64 requested)
 	 */
 	bool compacted = cpu_feature_enabled(X86_FEATURE_XSAVES);
 	struct fpu *fpu = &current->group_leader->thread.fpu;
+	struct fpu_state_perm *perm;
 	unsigned int ksize, usize;
 	u64 mask;
-	int ret;
+	int ret = 0;
 
 	/* Check whether fully enabled */
 	if ((permitted & requested) == requested)
@@ -1621,15 +1628,18 @@ static int __xstate_request_perm(u64 permitted, u64 requested)
 	mask &= XFEATURE_MASK_USER_SUPPORTED;
 	usize = xstate_calculate_size(mask, false);
 
-	ret = validate_sigaltstack(usize);
-	if (ret)
-		return ret;
+	if (!guest) {
+		ret = validate_sigaltstack(usize);
+		if (ret)
+			return ret;
+	}
 
+	perm = guest ? &fpu->guest_perm : &fpu->perm;
 	/* Pairs with the READ_ONCE() in xstate_get_group_perm() */
-	WRITE_ONCE(fpu->perm.__state_perm, requested);
+	WRITE_ONCE(perm->__state_perm, requested);
 	/* Protected by sighand lock */
-	fpu->perm.__state_size = ksize;
-	fpu->perm.__user_state_size = usize;
+	perm->__state_size = ksize;
+	perm->__user_state_size = usize;
 	return ret;
 }
 
@@ -1640,7 +1650,7 @@ static const u64 xstate_prctl_req[XFEATURE_MAX] = {
 	[XFEATURE_XTILE_DATA] = XFEATURE_MASK_XTILE_DATA,
 };
 
-static int xstate_request_perm(unsigned long idx)
+static int xstate_request_perm(unsigned long idx, bool guest)
 {
 	u64 permitted, requested;
 	int ret;
@@ -1661,26 +1671,33 @@ static int xstate_request_perm(unsigned long idx)
 		return -EOPNOTSUPP;
 
 	/* Lockless quick check */
-	permitted = xstate_get_host_group_perm();
+	permitted = xstate_get_group_perm(guest);
 	if ((permitted & requested) == requested)
 		return 0;
 
 	/* Protect against concurrent modifications */
 	spin_lock_irq(&current->sighand->siglock);
-	permitted = xstate_get_host_group_perm();
-	ret = __xstate_request_perm(permitted, requested);
+	permitted = xstate_get_group_perm(guest);
+
+	/* First vCPU allocation locks the permissions. */
+	if (guest && (permitted & FPU_GUEST_PERM_LOCKED))
+		ret = -EBUSY;
+	else
+		ret = __xstate_request_perm(permitted, requested, guest);
 	spin_unlock_irq(&current->sighand->siglock);
 	return ret;
 }
 
-int xfd_enable_feature(u64 xfd_err)
+int __xfd_enable_feature(u64 xfd_err, struct fpu_guest *guest_fpu)
 {
 	u64 xfd_event = xfd_err & XFEATURE_MASK_USER_DYNAMIC;
+	struct fpu_state_perm *perm;
 	unsigned int ksize, usize;
 	struct fpu *fpu;
 
 	if (!xfd_event) {
-		pr_err_once("XFD: Invalid xfd error: %016llx\n", xfd_err);
+		if (!guest_fpu)
+			pr_err_once("XFD: Invalid xfd error: %016llx\n", xfd_err);
 		return 0;
 	}
 
@@ -1688,14 +1705,16 @@ int xfd_enable_feature(u64 xfd_err)
 	spin_lock_irq(&current->sighand->siglock);
 
 	/* If not permitted let it die */
-	if ((xstate_get_host_group_perm() & xfd_event) != xfd_event) {
+	if ((xstate_get_group_perm(!!guest_fpu) & xfd_event) != xfd_event) {
 		spin_unlock_irq(&current->sighand->siglock);
 		return -EPERM;
 	}
 
 	fpu = &current->group_leader->thread.fpu;
-	ksize = fpu->perm.__state_size;
-	usize = fpu->perm.__user_state_size;
+	perm = guest_fpu ? &fpu->guest_perm : &fpu->perm;
+	ksize = perm->__state_size;
+	usize = perm->__user_state_size;
+
 	/*
 	 * The feature is permitted. State size is sufficient.  Dropping
 	 * the lock is safe here even if more features are added from
@@ -1708,17 +1727,29 @@ int xfd_enable_feature(u64 xfd_err)
 	 * Try to allocate a new fpstate. If that fails there is no way
 	 * out.
 	 */
-	if (fpstate_realloc(xfd_event, ksize, usize))
+	if (fpstate_realloc(xfd_event, ksize, usize, guest_fpu))
 		return -EFAULT;
 	return 0;
 }
+
+int xfd_enable_feature(u64 xfd_err)
+{
+	return __xfd_enable_feature(xfd_err, NULL);
+}
+
 #else /* CONFIG_X86_64 */
-static inline int xstate_request_perm(unsigned long idx)
+static inline int xstate_request_perm(unsigned long idx, bool guest)
 {
 	return -EPERM;
 }
 #endif  /* !CONFIG_X86_64 */
 
+u64 xstate_get_guest_group_perm(void)
+{
+	return xstate_get_group_perm(true);
+}
+EXPORT_SYMBOL_GPL(xstate_get_guest_group_perm);
+
 /**
  * fpu_xstate_prctl - xstate permission operations
  * @tsk:	Redundant pointer to current
@@ -1742,6 +1773,7 @@ long fpu_xstate_prctl(struct task_struct *tsk, int option, unsigned long arg2)
 	u64 __user *uptr = (u64 __user *)arg2;
 	u64 permitted, supported;
 	unsigned long idx = arg2;
+	bool guest = false;
 
 	if (tsk != current)
 		return -EPERM;
@@ -1760,11 +1792,20 @@ long fpu_xstate_prctl(struct task_struct *tsk, int option, unsigned long arg2)
 		permitted &= XFEATURE_MASK_USER_SUPPORTED;
 		return put_user(permitted, uptr);
 
+	case ARCH_GET_XCOMP_GUEST_PERM:
+		permitted = xstate_get_guest_group_perm();
+		permitted &= XFEATURE_MASK_USER_SUPPORTED;
+		return put_user(permitted, uptr);
+
+	case ARCH_REQ_XCOMP_GUEST_PERM:
+		guest = true;
+		fallthrough;
+
 	case ARCH_REQ_XCOMP_PERM:
 		if (!IS_ENABLED(CONFIG_X86_64))
 			return -EOPNOTSUPP;
 
-		return xstate_request_perm(idx);
+		return xstate_request_perm(idx, guest);
 
 	default:
 		return -EINVAL;
diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h
index e0c9264b1dd0..d22ace092ca2 100644
--- a/arch/x86/kernel/fpu/xstate.h
+++ b/arch/x86/kernel/fpu/xstate.h
@@ -20,10 +20,19 @@ static inline void xstate_init_xcomp_bv(struct xregs_state *xsave, u64 mask)
 		xsave->header.xcomp_bv = mask | XCOMP_BV_COMPACTED_FORMAT;
 }
 
-static inline u64 xstate_get_host_group_perm(void)
+static inline u64 xstate_get_group_perm(bool guest)
 {
+	struct fpu *fpu = &current->group_leader->thread.fpu;
+	struct fpu_state_perm *perm;
+
 	/* Pairs with WRITE_ONCE() in xstate_request_perm() */
-	return READ_ONCE(current->group_leader->thread.fpu.perm.__state_perm);
+	perm = guest ? &fpu->guest_perm : &fpu->perm;
+	return READ_ONCE(perm->__state_perm);
+}
+
+static inline u64 xstate_get_host_group_perm(void)
+{
+	return xstate_get_group_perm(false);
 }
 
 enum xstate_copy_mode {
@@ -145,8 +154,14 @@ static inline void xfd_update_state(struct fpstate *fpstate)
 		}
 	}
 }
+
+extern int __xfd_enable_feature(u64 which, struct fpu_guest *guest_fpu);
 #else
 static inline void xfd_update_state(struct fpstate *fpstate) { }
+
+static inline int __xfd_enable_feature(u64 which, struct fpu_guest *guest_fpu) {
+	return -EPERM;
+}
 #endif
 
 /*