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

Pull kvm updates from Paolo Bonzini:
 "S390:

   - ultravisor communication device driver

   - fix TEID on terminating storage key ops

  RISC-V:

   - Added Sv57x4 support for G-stage page table

   - Added range based local HFENCE functions

   - Added remote HFENCE functions based on VCPU requests

   - Added ISA extension registers in ONE_REG interface

   - Updated KVM RISC-V maintainers entry to cover selftests support

  ARM:

   - Add support for the ARMv8.6 WFxT extension

   - Guard pages for the EL2 stacks

   - Trap and emulate AArch32 ID registers to hide unsupported features

   - Ability to select and save/restore the set of hypercalls exposed to
     the guest

   - Support for PSCI-initiated suspend in collaboration with userspace

   - GICv3 register-based LPI invalidation support

   - Move host PMU event merging into the vcpu data structure

   - GICv3 ITS save/restore fixes

   - The usual set of small-scale cleanups and fixes

  x86:

   - New ioctls to get/set TSC frequency for a whole VM

   - Allow userspace to opt out of hypercall patching

   - Only do MSR filtering for MSRs accessed by rdmsr/wrmsr

  AMD SEV improvements:

   - Add KVM_EXIT_SHUTDOWN metadata for SEV-ES

   - V_TSC_AUX support

  Nested virtualization improvements for AMD:

   - Support for "nested nested" optimizations (nested vVMLOAD/VMSAVE,
     nested vGIF)

   - Allow AVIC to co-exist with a nested guest running

   - Fixes for LBR virtualizations when a nested guest is running, and
     nested LBR virtualization support

   - PAUSE filtering for nested hypervisors

  Guest support:

   - Decoupling of vcpu_is_preempted from PV spinlocks"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (199 commits)
  KVM: x86: Fix the intel_pt PMI handling wrongly considered from guest
  KVM: selftests: x86: Sync the new name of the test case to .gitignore
  Documentation: kvm: reorder ARM-specific section about KVM_SYSTEM_EVENT_SUSPEND
  x86, kvm: use correct GFP flags for preemption disabled
  KVM: LAPIC: Drop pending LAPIC timer injection when canceling the timer
  x86/kvm: Alloc dummy async #PF token outside of raw spinlock
  KVM: x86: avoid calling x86 emulator without a decoded instruction
  KVM: SVM: Use kzalloc for sev ioctl interfaces to prevent kernel data leak
  x86/fpu: KVM: Set the base guest FPU uABI size to sizeof(struct kvm_xsave)
  s390/uv_uapi: depend on CONFIG_S390
  KVM: selftests: x86: Fix test failure on arch lbr capable platforms
  KVM: LAPIC: Trace LAPIC timer expiration on every vmentry
  KVM: s390: selftest: Test suppression indication on key prot exception
  KVM: s390: Don't indicate suppression on dirtying, failing memop
  selftests: drivers/s390x: Add uvdevice tests
  drivers/s390/char: Add Ultravisor io device
  MAINTAINERS: Update KVM RISC-V entry to cover selftests support
  RISC-V: KVM: Introduce ISA extension register
  RISC-V: KVM: Cleanup stale TLB entries when host CPU changes
  RISC-V: KVM: Add remote HFENCE functions based on VCPU requests
  ...

4 files changed, 85 insertions, 56 deletions

diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index b14533af7676..9b698215d261 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -5,7 +5,7 @@
 
 #include <asm/ia32.h>
 
-#if defined(CONFIG_KVM_GUEST) && defined(CONFIG_PARAVIRT_SPINLOCKS)
+#if defined(CONFIG_KVM_GUEST)
 #include <asm/kvm_para.h>
 #endif
 
@@ -20,7 +20,7 @@ int main(void)
 	BLANK();
 #endif
 
-#if defined(CONFIG_KVM_GUEST) && defined(CONFIG_PARAVIRT_SPINLOCKS)
+#if defined(CONFIG_KVM_GUEST)
 	OFFSET(KVM_STEAL_TIME_preempted, kvm_steal_time, preempted);
 	BLANK();
 #endif
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index e28ab0ecc537..0fdc807ae13f 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -14,6 +14,8 @@
 #include <asm/traps.h>
 #include <asm/irq_regs.h>
 
+#include <uapi/asm/kvm.h>
+
 #include <linux/hardirq.h>
 #include <linux/pkeys.h>
 #include <linux/vmalloc.h>
@@ -232,7 +234,20 @@ bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu)
 	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;
+
+	/*
+	 * KVM sets the FP+SSE bits in the XSAVE header when copying FPU state
+	 * to userspace, even when XSAVE is unsupported, so that restoring FPU
+	 * state on a different CPU that does support XSAVE can cleanly load
+	 * the incoming state using its natural XSAVE.  In other words, KVM's
+	 * uABI size may be larger than this host's default size.  Conversely,
+	 * the default size should never be larger than KVM's base uABI size;
+	 * all features that can expand the uABI size must be opt-in.
+	 */
+	gfpu->uabi_size		= sizeof(struct kvm_xsave);
+	if (WARN_ON_ONCE(fpu_user_cfg.default_size > gfpu->uabi_size))
+		gfpu->uabi_size = fpu_user_cfg.default_size;
+
 	fpu_init_guest_permissions(gfpu);
 
 	return true;
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 8b1c45c9cda8..1a3658f7e6d9 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -191,7 +191,7 @@ void kvm_async_pf_task_wake(u32 token)
 {
 	u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS);
 	struct kvm_task_sleep_head *b = &async_pf_sleepers[key];
-	struct kvm_task_sleep_node *n;
+	struct kvm_task_sleep_node *n, *dummy = NULL;
 
 	if (token == ~0) {
 		apf_task_wake_all();
@@ -203,28 +203,41 @@ again:
 	n = _find_apf_task(b, token);
 	if (!n) {
 		/*
-		 * async PF was not yet handled.
-		 * Add dummy entry for the token.
+		 * Async #PF not yet handled, add a dummy entry for the token.
+		 * Allocating the token must be down outside of the raw lock
+		 * as the allocator is preemptible on PREEMPT_RT kernels.
 		 */
-		n = kzalloc(sizeof(*n), GFP_ATOMIC);
-		if (!n) {
+		if (!dummy) {
+			raw_spin_unlock(&b->lock);
+			dummy = kzalloc(sizeof(*dummy), GFP_ATOMIC);
+
 			/*
-			 * Allocation failed! Busy wait while other cpu
-			 * handles async PF.
+			 * Continue looping on allocation failure, eventually
+			 * the async #PF will be handled and allocating a new
+			 * node will be unnecessary.
+			 */
+			if (!dummy)
+				cpu_relax();
+
+			/*
+			 * Recheck for async #PF completion before enqueueing
+			 * the dummy token to avoid duplicate list entries.
 			 */
-			raw_spin_unlock(&b->lock);
-			cpu_relax();
 			goto again;
 		}
-		n->token = token;
-		n->cpu = smp_processor_id();
-		init_swait_queue_head(&n->wq);
-		hlist_add_head(&n->link, &b->list);
+		dummy->token = token;
+		dummy->cpu = smp_processor_id();
+		init_swait_queue_head(&dummy->wq);
+		hlist_add_head(&dummy->link, &b->list);
+		dummy = NULL;
 	} else {
 		apf_task_wake_one(n);
 	}
 	raw_spin_unlock(&b->lock);
-	return;
+
+	/* A dummy token might be allocated and ultimately not used.  */
+	if (dummy)
+		kfree(dummy);
 }
 EXPORT_SYMBOL_GPL(kvm_async_pf_task_wake);
 
@@ -765,6 +778,42 @@ static void kvm_crash_shutdown(struct pt_regs *regs)
 }
 #endif
 
+#if defined(CONFIG_X86_32) || !defined(CONFIG_SMP)
+bool __kvm_vcpu_is_preempted(long cpu);
+
+__visible bool __kvm_vcpu_is_preempted(long cpu)
+{
+	struct kvm_steal_time *src = &per_cpu(steal_time, cpu);
+
+	return !!(src->preempted & KVM_VCPU_PREEMPTED);
+}
+PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted);
+
+#else
+
+#include <asm/asm-offsets.h>
+
+extern bool __raw_callee_save___kvm_vcpu_is_preempted(long);
+
+/*
+ * Hand-optimize version for x86-64 to avoid 8 64-bit register saving and
+ * restoring to/from the stack.
+ */
+asm(
+".pushsection .text;"
+".global __raw_callee_save___kvm_vcpu_is_preempted;"
+".type __raw_callee_save___kvm_vcpu_is_preempted, @function;"
+"__raw_callee_save___kvm_vcpu_is_preempted:"
+ASM_ENDBR
+"movq	__per_cpu_offset(,%rdi,8), %rax;"
+"cmpb	$0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax);"
+"setne	%al;"
+ASM_RET
+".size __raw_callee_save___kvm_vcpu_is_preempted, .-__raw_callee_save___kvm_vcpu_is_preempted;"
+".popsection");
+
+#endif
+
 static void __init kvm_guest_init(void)
 {
 	int i;
@@ -777,6 +826,9 @@ static void __init kvm_guest_init(void)
 	if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
 		has_steal_clock = 1;
 		static_call_update(pv_steal_clock, kvm_steal_clock);
+
+		pv_ops.lock.vcpu_is_preempted =
+			PV_CALLEE_SAVE(__kvm_vcpu_is_preempted);
 	}
 
 	if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
@@ -1018,40 +1070,6 @@ static void kvm_wait(u8 *ptr, u8 val)
 	}
 }
 
-#ifdef CONFIG_X86_32
-__visible bool __kvm_vcpu_is_preempted(long cpu)
-{
-	struct kvm_steal_time *src = &per_cpu(steal_time, cpu);
-
-	return !!(src->preempted & KVM_VCPU_PREEMPTED);
-}
-PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted);
-
-#else
-
-#include <asm/asm-offsets.h>
-
-extern bool __raw_callee_save___kvm_vcpu_is_preempted(long);
-
-/*
- * Hand-optimize version for x86-64 to avoid 8 64-bit register saving and
- * restoring to/from the stack.
- */
-asm(
-".pushsection .text;"
-".global __raw_callee_save___kvm_vcpu_is_preempted;"
-".type __raw_callee_save___kvm_vcpu_is_preempted, @function;"
-"__raw_callee_save___kvm_vcpu_is_preempted:"
-ASM_ENDBR
-"movq	__per_cpu_offset(,%rdi,8), %rax;"
-"cmpb	$0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax);"
-"setne	%al;"
-ASM_RET
-".size __raw_callee_save___kvm_vcpu_is_preempted, .-__raw_callee_save___kvm_vcpu_is_preempted;"
-".popsection");
-
-#endif
-
 /*
  * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present.
  */
@@ -1095,10 +1113,6 @@ void __init kvm_spinlock_init(void)
 	pv_ops.lock.wait = kvm_wait;
 	pv_ops.lock.kick = kvm_kick_cpu;
 
-	if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
-		pv_ops.lock.vcpu_is_preempted =
-			PV_CALLEE_SAVE(__kvm_vcpu_is_preempted);
-	}
 	/*
 	 * When PV spinlock is enabled which is preferred over
 	 * virt_spin_lock(), virt_spin_lock_key's value is meaningless.
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index c5caa7311bd8..16333ba1904b 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -239,7 +239,7 @@ static void __init kvmclock_init_mem(void)
 
 static int __init kvm_setup_vsyscall_timeinfo(void)
 {
-	if (!kvm_para_available() || !kvmclock)
+	if (!kvm_para_available() || !kvmclock || nopv)
 		return 0;
 
 	kvmclock_init_mem();