Bugfixes, and a pvspinlock optimization

-----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.22 (GNU/Linux)
 
 iQEcBAABAgAGBQJdOEuhAAoJEL/70l94x66DX/IH/3c6ADaZkuwzUMtJZgib/slX
 V7h4ljoW33M85z3nCF5+kY3CNl8c9F2xKGcAIUlJF8MIsZW+zB3HjuU1LC4fCzuk
 TqpBf74DpQsKCsv1ngiV02lefPVQ7/VT/QFY7EXNuAqNRfgsBRNoi50244a0ZKpD
 KydzKTDKMD5HjE4lHb+bNr+guqkisPx0b0mZtsb4R9uuUSwXEa8DLmWQF2Do7zBj
 6G9UD6a1AP5XQBwRRbo5a78b5NZQcF5R9wVEzsmK7OGUw/yC4Em4HVt46z+oT5cm
 JK9m59XDqJaL6HMAWC2P/mXUj6o+PP+uBE2uuvkGCNcTLQZwWf+dq9961tWg81E=
 =DD/Z
 -----END PGP SIGNATURE-----

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

Pull KVM fixes from Paolo Bonzini:
 "Bugfixes, a pvspinlock optimization, and documentation moving"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: X86: Boost queue head vCPU to mitigate lock waiter preemption
  Documentation: move Documentation/virtual to Documentation/virt
  KVM: nVMX: Set cached_vmcs12 and cached_shadow_vmcs12 NULL after free
  KVM: X86: Dynamically allocate user_fpu
  KVM: X86: Fix fpu state crash in kvm guest
  Revert "kvm: x86: Use task structs fpu field for user"
  KVM: nVMX: Clear pending KVM_REQ_GET_VMCS12_PAGES when leaving nested

Documentation/admin-guide/kernel-parameters.txt

@@ -2545,7 +2545,7 @@
 			mem_encrypt=on:		Activate SME
 			mem_encrypt=off:	Do not activate SME
 
-			Refer to Documentation/virtual/kvm/amd-memory-encryption.rst
+			Refer to Documentation/virt/kvm/amd-memory-encryption.rst
 			for details on when memory encryption can be activated.
 
 	mem_sleep_default=	[SUSPEND] Default system suspend mode:

Documentation/virt/kvm/api.txt

@@ -3781,7 +3781,7 @@ encrypted VMs.
 
 Currently, this ioctl is used for issuing Secure Encrypted Virtualization
 (SEV) commands on AMD Processors. The SEV commands are defined in
-Documentation/virtual/kvm/amd-memory-encryption.rst.
+Documentation/virt/kvm/amd-memory-encryption.rst.
 
 4.111 KVM_MEMORY_ENCRYPT_REG_REGION
 

Documentation/virt/kvm/hypercalls.txt

@@ -18,7 +18,7 @@ S390:
   number in R1.
 
   For further information on the S390 diagnose call as supported by KVM,
-  refer to Documentation/virtual/kvm/s390-diag.txt.
+  refer to Documentation/virt/kvm/s390-diag.txt.
 
  PowerPC:
   It uses R3-R10 and hypercall number in R11. R4-R11 are used as output registers.
@@ -26,7 +26,7 @@ S390:
 
   KVM hypercalls uses 4 byte opcode, that are patched with 'hypercall-instructions'
   property inside the device tree's /hypervisor node.
-  For more information refer to Documentation/virtual/kvm/ppc-pv.txt
+  For more information refer to Documentation/virt/kvm/ppc-pv.txt
 
 MIPS:
   KVM hypercalls use the HYPCALL instruction with code 0 and the hypercall

Documentation/virt/kvm/mmu.txt

@@ -298,7 +298,7 @@ Handling a page fault is performed as follows:
      vcpu->arch.mmio_gfn, and call the emulator
  - If both P bit and R/W bit of error code are set, this could possibly
    be handled as a "fast page fault" (fixed without taking the MMU lock).  See
-   the description in Documentation/virtual/kvm/locking.txt.
+   the description in Documentation/virt/kvm/locking.txt.
  - if needed, walk the guest page tables to determine the guest translation
    (gva->gpa or ngpa->gpa)
    - if permissions are insufficient, reflect the fault back to the guest

Documentation/virt/kvm/review-checklist.txt

@@ -7,7 +7,7 @@ Review checklist for kvm patches
 2.  Patches should be against kvm.git master branch.
 
 3.  If the patch introduces or modifies a new userspace API:
-    - the API must be documented in Documentation/virtual/kvm/api.txt
+    - the API must be documented in Documentation/virt/kvm/api.txt
     - the API must be discoverable using KVM_CHECK_EXTENSION
 
 4.  New state must include support for save/restore.

MAINTAINERS

@@ -8808,7 +8808,7 @@ L:	kvm@vger.kernel.org
 W:	http://www.linux-kvm.org
 T:	git git://git.kernel.org/pub/scm/virt/kvm/kvm.git
 S:	Supported
-F:	Documentation/virtual/kvm/
+F:	Documentation/virt/kvm/
 F:	include/trace/events/kvm.h
 F:	include/uapi/asm-generic/kvm*
 F:	include/uapi/linux/kvm*
@@ -12137,7 +12137,7 @@ M:	Thomas Hellstrom <thellstrom@vmware.com>
 M:	"VMware, Inc." <pv-drivers@vmware.com>
 L:	virtualization@lists.linux-foundation.org
 S:	Supported
-F:	Documentation/virtual/paravirt_ops.txt
+F:	Documentation/virt/paravirt_ops.txt
 F:	arch/*/kernel/paravirt*
 F:	arch/*/include/asm/paravirt*.h
 F:	include/linux/hypervisor.h
@@ -16854,7 +16854,7 @@ W:	http://user-mode-linux.sourceforge.net
 Q:	https://patchwork.ozlabs.org/project/linux-um/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rw/uml.git
 S:	Maintained
-F:	Documentation/virtual/uml/
+F:	Documentation/virt/uml/
 F:	arch/um/
 F:	arch/x86/um/
 F:	fs/hostfs/

arch/powerpc/include/uapi/asm/kvm_para.h

@@ -31,7 +31,7 @@
  * Struct fields are always 32 or 64 bit aligned, depending on them being 32
  * or 64 bit wide respectively.
  *
- * See Documentation/virtual/kvm/ppc-pv.txt
+ * See Documentation/virt/kvm/ppc-pv.txt
  */
 struct kvm_vcpu_arch_shared {
 	__u64 scratch1;

arch/x86/include/asm/kvm_host.h

@@ -607,15 +607,16 @@ struct kvm_vcpu_arch {
 
 	/*
 	 * QEMU userspace and the guest each have their own FPU state.
-	 * In vcpu_run, we switch between the user, maintained in the
+	 * In vcpu_run, we switch between the user and guest FPU contexts.
-	 * task_struct struct, and guest FPU contexts. While running a VCPU,
+	 * While running a VCPU, the VCPU thread will have the guest FPU
-	 * the VCPU thread will have the guest FPU context.
+	 * context.
 	 *
 	 * Note that while the PKRU state lives inside the fpu registers,
 	 * it is switched out separately at VMENTER and VMEXIT time. The
 	 * "guest_fpu" state here contains the guest FPU context, with the
 	 * host PRKU bits.
 	 */
+	struct fpu *user_fpu;
 	struct fpu *guest_fpu;
 
 	u64 xcr0;

arch/x86/kvm/mmu.c

@@ -3466,7 +3466,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
 		/*
 		 * Currently, fast page fault only works for direct mapping
 		 * since the gfn is not stable for indirect shadow page. See
-		 * Documentation/virtual/kvm/locking.txt to get more detail.
+		 * Documentation/virt/kvm/locking.txt to get more detail.
 		 */
 		fault_handled = fast_pf_fix_direct_spte(vcpu, sp,
 							iterator.sptep, spte,

arch/x86/kvm/svm.c

@@ -2143,12 +2143,20 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 		goto out;
 	}
 
+	svm->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache,
+						     GFP_KERNEL_ACCOUNT);
+	if (!svm->vcpu.arch.user_fpu) {
+		printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n");
+		err = -ENOMEM;
+		goto free_partial_svm;
+	}
+
 	svm->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache,
 						     GFP_KERNEL_ACCOUNT);
 	if (!svm->vcpu.arch.guest_fpu) {
 		printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n");
 		err = -ENOMEM;
-		goto free_partial_svm;
+		goto free_user_fpu;
 	}
 
 	err = kvm_vcpu_init(&svm->vcpu, kvm, id);
@@ -2211,6 +2219,8 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 	kvm_vcpu_uninit(&svm->vcpu);
 free_svm:
 	kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu);
+free_user_fpu:
+	kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu);
 free_partial_svm:
 	kmem_cache_free(kvm_vcpu_cache, svm);
 out:
@@ -2241,6 +2251,7 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu)
 	__free_page(virt_to_page(svm->nested.hsave));
 	__free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER);
 	kvm_vcpu_uninit(vcpu);
+	kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu);
 	kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu);
 	kmem_cache_free(kvm_vcpu_cache, svm);
 }

arch/x86/kvm/vmx/nested.c

@@ -220,6 +220,8 @@ static void free_nested(struct kvm_vcpu *vcpu)
 	if (!vmx->nested.vmxon && !vmx->nested.smm.vmxon)
 		return;
 
+	kvm_clear_request(KVM_REQ_GET_VMCS12_PAGES, vcpu);
+
 	vmx->nested.vmxon = false;
 	vmx->nested.smm.vmxon = false;
 	free_vpid(vmx->nested.vpid02);
@@ -232,7 +234,9 @@ static void free_nested(struct kvm_vcpu *vcpu)
 		vmx->vmcs01.shadow_vmcs = NULL;
 	}
 	kfree(vmx->nested.cached_vmcs12);
+	vmx->nested.cached_vmcs12 = NULL;
 	kfree(vmx->nested.cached_shadow_vmcs12);
+	vmx->nested.cached_shadow_vmcs12 = NULL;
 	/* Unpin physical memory we referred to in the vmcs02 */
 	if (vmx->nested.apic_access_page) {
 		kvm_release_page_dirty(vmx->nested.apic_access_page);

arch/x86/kvm/vmx/vmx.c

@@ -6598,6 +6598,7 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
 	free_loaded_vmcs(vmx->loaded_vmcs);
 	kfree(vmx->guest_msrs);
 	kvm_vcpu_uninit(vcpu);
+	kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu);
 	kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu);
 	kmem_cache_free(kvm_vcpu_cache, vmx);
 }
@@ -6613,12 +6614,20 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	if (!vmx)
 		return ERR_PTR(-ENOMEM);
 
+	vmx->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache,
+			GFP_KERNEL_ACCOUNT);
+	if (!vmx->vcpu.arch.user_fpu) {
+		printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n");
+		err = -ENOMEM;
+		goto free_partial_vcpu;
+	}
+
 	vmx->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache,
 			GFP_KERNEL_ACCOUNT);
 	if (!vmx->vcpu.arch.guest_fpu) {
 		printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n");
 		err = -ENOMEM;
-		goto free_partial_vcpu;
+		goto free_user_fpu;
 	}
 
 	vmx->vpid = allocate_vpid();
@@ -6721,6 +6730,8 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 free_vcpu:
 	free_vpid(vmx->vpid);
 	kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu);
+free_user_fpu:
+	kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu);
 free_partial_vcpu:
 	kmem_cache_free(kvm_vcpu_cache, vmx);
 	return ERR_PTR(err);

arch/x86/kvm/x86.c

@@ -3306,6 +3306,10 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	kvm_x86_ops->vcpu_load(vcpu, cpu);
 
+	fpregs_assert_state_consistent();
+	if (test_thread_flag(TIF_NEED_FPU_LOAD))
+		switch_fpu_return();
+
 	/* Apply any externally detected TSC adjustments (due to suspend) */
 	if (unlikely(vcpu->arch.tsc_offset_adjustment)) {
 		adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment);
@@ -7202,7 +7206,7 @@ static void kvm_sched_yield(struct kvm *kvm, unsigned long dest_id)
 
 	rcu_read_unlock();
 
-	if (target)
+	if (target && READ_ONCE(target->ready))
 		kvm_vcpu_yield_to(target);
 }
 
@@ -7242,6 +7246,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 		break;
 	case KVM_HC_KICK_CPU:
 		kvm_pv_kick_cpu_op(vcpu->kvm, a0, a1);
+		kvm_sched_yield(vcpu->kvm, a1);
 		ret = 0;
 		break;
 #ifdef CONFIG_X86_64
@@ -7990,9 +7995,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	trace_kvm_entry(vcpu->vcpu_id);
 	guest_enter_irqoff();
 
-	fpregs_assert_state_consistent();
+	/* The preempt notifier should have taken care of the FPU already.  */
-	if (test_thread_flag(TIF_NEED_FPU_LOAD))
+	WARN_ON_ONCE(test_thread_flag(TIF_NEED_FPU_LOAD));
-		switch_fpu_return();
 
 	if (unlikely(vcpu->arch.switch_db_regs)) {
 		set_debugreg(0, 7);
@@ -8270,7 +8274,7 @@ static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 {
 	fpregs_lock();
 
-	copy_fpregs_to_fpstate(&current->thread.fpu);
+	copy_fpregs_to_fpstate(vcpu->arch.user_fpu);
 	/* PKRU is separately restored in kvm_x86_ops->run.  */
 	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state,
 				~XFEATURE_MASK_PKRU);
@@ -8287,7 +8291,7 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 	fpregs_lock();
 
 	copy_fpregs_to_fpstate(vcpu->arch.guest_fpu);
-	copy_kernel_to_fpregs(&current->thread.fpu.state);
+	copy_kernel_to_fpregs(&vcpu->arch.user_fpu->state);
 
 	fpregs_mark_activate();
 	fpregs_unlock();

include/uapi/linux/kvm.h

@@ -116,7 +116,7 @@ struct kvm_irq_level {
 	 * ACPI gsi notion of irq.
 	 * For IA-64 (APIC model) IOAPIC0: irq 0-23; IOAPIC1: irq 24-47..
 	 * For X86 (standard AT mode) PIC0/1: irq 0-15. IOAPIC0: 0-23..
-	 * For ARM: See Documentation/virtual/kvm/api.txt
+	 * For ARM: See Documentation/virt/kvm/api.txt
 	 */
 	union {
 		__u32 irq;
@@ -1086,7 +1086,7 @@ struct kvm_xen_hvm_config {
  *
  * KVM_IRQFD_FLAG_RESAMPLE indicates resamplefd is valid and specifies
  * the irqfd to operate in resampling mode for level triggered interrupt
- * emulation.  See Documentation/virtual/kvm/api.txt.
+ * emulation.  See Documentation/virt/kvm/api.txt.
  */
 #define KVM_IRQFD_FLAG_RESAMPLE (1 << 1)
 

tools/include/uapi/linux/kvm.h

@@ -116,7 +116,7 @@ struct kvm_irq_level {
 	 * ACPI gsi notion of irq.
 	 * For IA-64 (APIC model) IOAPIC0: irq 0-23; IOAPIC1: irq 24-47..
 	 * For X86 (standard AT mode) PIC0/1: irq 0-15. IOAPIC0: 0-23..
-	 * For ARM: See Documentation/virtual/kvm/api.txt
+	 * For ARM: See Documentation/virt/kvm/api.txt
 	 */
 	union {
 		__u32 irq;
@@ -1085,7 +1085,7 @@ struct kvm_xen_hvm_config {
  *
  * KVM_IRQFD_FLAG_RESAMPLE indicates resamplefd is valid and specifies
  * the irqfd to operate in resampling mode for level triggered interrupt
- * emulation.  See Documentation/virtual/kvm/api.txt.
+ * emulation.  See Documentation/virt/kvm/api.txt.
  */
 #define KVM_IRQFD_FLAG_RESAMPLE (1 << 1)
 

virt/kvm/arm/arm.c

@@ -727,7 +727,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		 * Ensure we set mode to IN_GUEST_MODE after we disable
 		 * interrupts and before the final VCPU requests check.
 		 * See the comment in kvm_vcpu_exiting_guest_mode() and
-		 * Documentation/virtual/kvm/vcpu-requests.rst
+		 * Documentation/virt/kvm/vcpu-requests.rst
 		 */
 		smp_store_mb(vcpu->mode, IN_GUEST_MODE);
 

virt/kvm/arm/vgic/vgic-mmio-v3.c

@@ -250,7 +250,7 @@ static unsigned long vgic_v3_uaccess_read_pending(struct kvm_vcpu *vcpu,
 	 * pending state of interrupt is latched in pending_latch variable.
 	 * Userspace will save and restore pending state and line_level
 	 * separately.
-	 * Refer to Documentation/virtual/kvm/devices/arm-vgic-v3.txt
+	 * Refer to Documentation/virt/kvm/devices/arm-vgic-v3.txt
 	 * for handling of ISPENDR and ICPENDR.
 	 */
 	for (i = 0; i < len * 8; i++) {

virt/kvm/arm/vgic/vgic.h

@@ -42,7 +42,7 @@
 			    VGIC_AFFINITY_LEVEL(val, 3))
 
 /*
- * As per Documentation/virtual/kvm/devices/arm-vgic-v3.txt,
+ * As per Documentation/virt/kvm/devices/arm-vgic-v3.txt,
  * below macros are defined for CPUREG encoding.
  */
 #define KVM_REG_ARM_VGIC_SYSREG_OP0_MASK   0x000000000000c000
@@ -63,7 +63,7 @@
 				      KVM_REG_ARM_VGIC_SYSREG_OP2_MASK)
 
 /*
- * As per Documentation/virtual/kvm/devices/arm-vgic-its.txt,
+ * As per Documentation/virt/kvm/devices/arm-vgic-its.txt,
  * below macros are defined for ITS table entry encoding.
  */
 #define KVM_ITS_CTE_VALID_SHIFT		63