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

Pull KVM fixes from Radim Krčmář:
 "ARM:
   - PSCI selection API, a leftover from 4.16 (for stable)
   - Kick vcpu on active interrupt affinity change
   - Plug a VMID allocation race on oversubscribed systems
   - Silence debug messages
   - Update Christoffer's email address (linaro -> arm)

  x86:
   - Expose userspace-relevant bits of a newly added feature
   - Fix TLB flushing on VMX with VPID, but without EPT"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  x86/headers/UAPI: Move DISABLE_EXITS KVM capability bits to the UAPI
  kvm: apic: Flush TLB after APIC mode/address change if VPIDs are in use
  arm/arm64: KVM: Add PSCI version selection API
  KVM: arm/arm64: vgic: Kick new VCPU on interrupt migration
  arm64: KVM: Demote SVE and LORegion warnings to debug only
  MAINTAINERS: Update e-mail address for Christoffer Dall
  KVM: arm/arm64: Close VMID generation race

Documentation/virtual/kvm/api.txt

@@ -1960,6 +1960,9 @@ ARM 32-bit VFP control registers have the following id bit patterns:
 ARM 64-bit FP registers have the following id bit patterns:
   0x4030 0000 0012 0 <regno:12>
 
+ARM firmware pseudo-registers have the following bit pattern:
+  0x4030 0000 0014 <regno:16>
+
 
 arm64 registers are mapped using the lower 32 bits. The upper 16 of
 that is the register group type, or coprocessor number:
@@ -1976,6 +1979,9 @@ arm64 CCSIDR registers are demultiplexed by CSSELR value:
 arm64 system registers have the following id bit patterns:
   0x6030 0000 0013 <op0:2> <op1:3> <crn:4> <crm:4> <op2:3>
 
+arm64 firmware pseudo-registers have the following bit pattern:
+  0x6030 0000 0014 <regno:16>
+
 
 MIPS registers are mapped using the lower 32 bits.  The upper 16 of that is
 the register group type:
@@ -2510,7 +2516,8 @@ Possible features:
 	  and execute guest code when KVM_RUN is called.
 	- KVM_ARM_VCPU_EL1_32BIT: Starts the CPU in a 32bit mode.
 	  Depends on KVM_CAP_ARM_EL1_32BIT (arm64 only).
-	- KVM_ARM_VCPU_PSCI_0_2: Emulate PSCI v0.2 for the CPU.
+	- KVM_ARM_VCPU_PSCI_0_2: Emulate PSCI v0.2 (or a future revision
+          backward compatible with v0.2) for the CPU.
 	  Depends on KVM_CAP_ARM_PSCI_0_2.
 	- KVM_ARM_VCPU_PMU_V3: Emulate PMUv3 for the CPU.
 	  Depends on KVM_CAP_ARM_PMU_V3.

Documentation/virtual/kvm/arm/psci.txt

@@ -0,0 +1,30 @@
+KVM implements the PSCI (Power State Coordination Interface)
+specification in order to provide services such as CPU on/off, reset
+and power-off to the guest.
+
+The PSCI specification is regularly updated to provide new features,
+and KVM implements these updates if they make sense from a virtualization
+point of view.
+
+This means that a guest booted on two different versions of KVM can
+observe two different "firmware" revisions. This could cause issues if
+a given guest is tied to a particular PSCI revision (unlikely), or if
+a migration causes a different PSCI version to be exposed out of the
+blue to an unsuspecting guest.
+
+In order to remedy this situation, KVM exposes a set of "firmware
+pseudo-registers" that can be manipulated using the GET/SET_ONE_REG
+interface. These registers can be saved/restored by userspace, and set
+to a convenient value if required.
+
+The following register is defined:
+
+* KVM_REG_ARM_PSCI_VERSION:
+
+  - Only valid if the vcpu has the KVM_ARM_VCPU_PSCI_0_2 feature set
+    (and thus has already been initialized)
+  - Returns the current PSCI version on GET_ONE_REG (defaulting to the
+    highest PSCI version implemented by KVM and compatible with v0.2)
+  - Allows any PSCI version implemented by KVM and compatible with
+    v0.2 to be set with SET_ONE_REG
+  - Affects the whole VM (even if the register view is per-vcpu)

MAINTAINERS

@@ -7744,7 +7744,7 @@ F:	arch/x86/include/asm/svm.h
 F:	arch/x86/kvm/svm.c
 
 KERNEL VIRTUAL MACHINE FOR ARM (KVM/arm)
-M:	Christoffer Dall <christoffer.dall@linaro.org>
+M:	Christoffer Dall <christoffer.dall@arm.com>
 M:	Marc Zyngier <[email protected]>
 L:	[email protected] (moderated for non-subscribers)
 L:	[email protected]
@@ -7758,7 +7758,7 @@ F:	virt/kvm/arm/
 F:	include/kvm/arm_*
 
 KERNEL VIRTUAL MACHINE FOR ARM64 (KVM/arm64)
-M:	Christoffer Dall <christoffer.dall@linaro.org>
+M:	Christoffer Dall <christoffer.dall@arm.com>
 M:	Marc Zyngier <[email protected]>
 L:	[email protected] (moderated for non-subscribers)
 L:	[email protected]

arch/arm/include/asm/kvm_host.h

@@ -77,6 +77,9 @@ struct kvm_arch {
 	/* Interrupt controller */
 	struct vgic_dist	vgic;
 	int max_vcpus;
+
+	/* Mandated version of PSCI */
+	u32 psci_version;
 };
 
 #define KVM_NR_MEM_OBJS     40

arch/arm/include/uapi/asm/kvm.h

@@ -195,6 +195,12 @@ struct kvm_arch_memory_slot {
 #define KVM_REG_ARM_VFP_FPINST		0x1009
 #define KVM_REG_ARM_VFP_FPINST2		0x100A
 
+/* KVM-as-firmware specific pseudo-registers */
+#define KVM_REG_ARM_FW			(0x0014 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_FW_REG(r)		(KVM_REG_ARM | KVM_REG_SIZE_U64 | \
+					 KVM_REG_ARM_FW | ((r) & 0xffff))
+#define KVM_REG_ARM_PSCI_VERSION	KVM_REG_ARM_FW_REG(0)
+
 /* Device Control API: ARM VGIC */
 #define KVM_DEV_ARM_VGIC_GRP_ADDR	0
 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS	1

arch/arm/kvm/guest.c

@@ -22,6 +22,7 @@
 #include <linux/module.h>
 #include <linux/vmalloc.h>
 #include <linux/fs.h>
+#include <kvm/arm_psci.h>
 #include <asm/cputype.h>
 #include <linux/uaccess.h>
 #include <asm/kvm.h>
@@ -176,6 +177,7 @@ static unsigned long num_core_regs(void)
 unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu)
 {
 	return num_core_regs() + kvm_arm_num_coproc_regs(vcpu)
+		+ kvm_arm_get_fw_num_regs(vcpu)
 		+ NUM_TIMER_REGS;
 }
 
@@ -196,6 +198,11 @@ int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
 		uindices++;
 	}
 
+	ret = kvm_arm_copy_fw_reg_indices(vcpu, uindices);
+	if (ret)
+		return ret;
+	uindices += kvm_arm_get_fw_num_regs(vcpu);
+
 	ret = copy_timer_indices(vcpu, uindices);
 	if (ret)
 		return ret;
@@ -214,6 +221,9 @@ int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
 		return get_core_reg(vcpu, reg);
 
+	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW)
+		return kvm_arm_get_fw_reg(vcpu, reg);
+
 	if (is_timer_reg(reg->id))
 		return get_timer_reg(vcpu, reg);
 
@@ -230,6 +240,9 @@ int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
 		return set_core_reg(vcpu, reg);
 
+	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW)
+		return kvm_arm_set_fw_reg(vcpu, reg);
+
 	if (is_timer_reg(reg->id))
 		return set_timer_reg(vcpu, reg);
 

arch/arm64/include/asm/kvm_host.h

@@ -75,6 +75,9 @@ struct kvm_arch {
 
 	/* Interrupt controller */
 	struct vgic_dist	vgic;
+
+	/* Mandated version of PSCI */
+	u32 psci_version;
 };
 
 #define KVM_NR_MEM_OBJS     40

arch/arm64/include/uapi/asm/kvm.h

@@ -206,6 +206,12 @@ struct kvm_arch_memory_slot {
 #define KVM_REG_ARM_TIMER_CNT		ARM64_SYS_REG(3, 3, 14, 3, 2)
 #define KVM_REG_ARM_TIMER_CVAL		ARM64_SYS_REG(3, 3, 14, 0, 2)
 
+/* KVM-as-firmware specific pseudo-registers */
+#define KVM_REG_ARM_FW			(0x0014 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_FW_REG(r)		(KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \
+					 KVM_REG_ARM_FW | ((r) & 0xffff))
+#define KVM_REG_ARM_PSCI_VERSION	KVM_REG_ARM_FW_REG(0)
+
 /* Device Control API: ARM VGIC */
 #define KVM_DEV_ARM_VGIC_GRP_ADDR	0
 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS	1

arch/arm64/kvm/guest.c

@@ -25,6 +25,7 @@
 #include <linux/module.h>
 #include <linux/vmalloc.h>
 #include <linux/fs.h>
+#include <kvm/arm_psci.h>
 #include <asm/cputype.h>
 #include <linux/uaccess.h>
 #include <asm/kvm.h>
@@ -205,7 +206,7 @@ static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu)
 {
 	return num_core_regs() + kvm_arm_num_sys_reg_descs(vcpu)
-                + NUM_TIMER_REGS;
+		+ kvm_arm_get_fw_num_regs(vcpu)	+ NUM_TIMER_REGS;
 }
 
 /**
@@ -225,6 +226,11 @@ int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
 		uindices++;
 	}
 
+	ret = kvm_arm_copy_fw_reg_indices(vcpu, uindices);
+	if (ret)
+		return ret;
+	uindices += kvm_arm_get_fw_num_regs(vcpu);
+
 	ret = copy_timer_indices(vcpu, uindices);
 	if (ret)
 		return ret;
@@ -243,6 +249,9 @@ int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
 		return get_core_reg(vcpu, reg);
 
+	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW)
+		return kvm_arm_get_fw_reg(vcpu, reg);
+
 	if (is_timer_reg(reg->id))
 		return get_timer_reg(vcpu, reg);
 
@@ -259,6 +268,9 @@ int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
 		return set_core_reg(vcpu, reg);
 
+	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW)
+		return kvm_arm_set_fw_reg(vcpu, reg);
+
 	if (is_timer_reg(reg->id))
 		return set_timer_reg(vcpu, reg);
 

arch/arm64/kvm/sys_regs.c

@@ -996,14 +996,12 @@ static u64 read_id_reg(struct sys_reg_desc const *r, bool raz)
 
 	if (id == SYS_ID_AA64PFR0_EL1) {
 		if (val & (0xfUL << ID_AA64PFR0_SVE_SHIFT))
-			pr_err_once("kvm [%i]: SVE unsupported for guests, suppressing\n",
-				    task_pid_nr(current));
+			kvm_debug("SVE unsupported for guests, suppressing\n");
 
 		val &= ~(0xfUL << ID_AA64PFR0_SVE_SHIFT);
 	} else if (id == SYS_ID_AA64MMFR1_EL1) {
 		if (val & (0xfUL << ID_AA64MMFR1_LOR_SHIFT))
-			pr_err_once("kvm [%i]: LORegions unsupported for guests, suppressing\n",
-				    task_pid_nr(current));
+			kvm_debug("LORegions unsupported for guests, suppressing\n");
 
 		val &= ~(0xfUL << ID_AA64MMFR1_LOR_SHIFT);
 	}

arch/x86/kvm/vmx.c

@@ -4544,12 +4544,6 @@ static void vmx_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa)
 	__vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid, invalidate_gpa);
 }
 
-static void vmx_flush_tlb_ept_only(struct kvm_vcpu *vcpu)
-{
-	if (enable_ept)
-		vmx_flush_tlb(vcpu, true);
-}
-
 static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
 {
 	ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits;
@@ -9278,7 +9272,7 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
 	} else {
 		sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
 		sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
-		vmx_flush_tlb_ept_only(vcpu);
+		vmx_flush_tlb(vcpu, true);
 	}
 	vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control);
 
@@ -9306,7 +9300,7 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa)
 	    !nested_cpu_has2(get_vmcs12(&vmx->vcpu),
 			     SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
 		vmcs_write64(APIC_ACCESS_ADDR, hpa);
-		vmx_flush_tlb_ept_only(vcpu);
+		vmx_flush_tlb(vcpu, true);
 	}
 }
 
@@ -11220,7 +11214,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 		}
 	} else if (nested_cpu_has2(vmcs12,
 				   SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
-		vmx_flush_tlb_ept_only(vcpu);
+		vmx_flush_tlb(vcpu, true);
 	}
 
 	/*
@@ -12073,7 +12067,7 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	} else if (!nested_cpu_has_ept(vmcs12) &&
 		   nested_cpu_has2(vmcs12,
 				   SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
-		vmx_flush_tlb_ept_only(vcpu);
+		vmx_flush_tlb(vcpu, true);
 	}
 
 	/* This is needed for same reason as it was needed in prepare_vmcs02 */

arch/x86/kvm/x86.h

@@ -302,13 +302,6 @@ static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
 	    __rem;						\
 	 })
 
-#define KVM_X86_DISABLE_EXITS_MWAIT          (1 << 0)
-#define KVM_X86_DISABLE_EXITS_HTL            (1 << 1)
-#define KVM_X86_DISABLE_EXITS_PAUSE          (1 << 2)
-#define KVM_X86_DISABLE_VALID_EXITS          (KVM_X86_DISABLE_EXITS_MWAIT | \
-                                              KVM_X86_DISABLE_EXITS_HTL | \
-                                              KVM_X86_DISABLE_EXITS_PAUSE)
-
 static inline bool kvm_mwait_in_guest(struct kvm *kvm)
 {
 	return kvm->arch.mwait_in_guest;

include/kvm/arm_psci.h

@@ -37,15 +37,27 @@ static inline int kvm_psci_version(struct kvm_vcpu *vcpu, struct kvm *kvm)
 	 * Our PSCI implementation stays the same across versions from
 	 * v0.2 onward, only adding the few mandatory functions (such
 	 * as FEATURES with 1.0) that are required by newer
-	 * revisions. It is thus safe to return the latest.
+	 * revisions. It is thus safe to return the latest, unless
+	 * userspace has instructed us otherwise.
 	 */
-	if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features))
+	if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features)) {
+		if (vcpu->kvm->arch.psci_version)
+			return vcpu->kvm->arch.psci_version;
+
 		return KVM_ARM_PSCI_LATEST;
+	}
 
 	return KVM_ARM_PSCI_0_1;
 }
 
 
 int kvm_hvc_call_handler(struct kvm_vcpu *vcpu);
 
+struct kvm_one_reg;
+
+int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu);
+int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices);
+int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
+int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
+
 #endif /* __KVM_ARM_PSCI_H__ */

include/uapi/linux/kvm.h

@@ -676,6 +676,13 @@ struct kvm_ioeventfd {
 	__u8  pad[36];
 };
 
+#define KVM_X86_DISABLE_EXITS_MWAIT          (1 << 0)
+#define KVM_X86_DISABLE_EXITS_HTL            (1 << 1)
+#define KVM_X86_DISABLE_EXITS_PAUSE          (1 << 2)
+#define KVM_X86_DISABLE_VALID_EXITS          (KVM_X86_DISABLE_EXITS_MWAIT | \
+                                              KVM_X86_DISABLE_EXITS_HTL | \
+                                              KVM_X86_DISABLE_EXITS_PAUSE)
+
 /* for KVM_ENABLE_CAP */
 struct kvm_enable_cap {
 	/* in */

virt/kvm/arm/arm.c

@@ -63,7 +63,7 @@ static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_arm_running_vcpu);
 static atomic64_t kvm_vmid_gen = ATOMIC64_INIT(1);
 static u32 kvm_next_vmid;
 static unsigned int kvm_vmid_bits __read_mostly;
-static DEFINE_SPINLOCK(kvm_vmid_lock);
+static DEFINE_RWLOCK(kvm_vmid_lock);
 
 static bool vgic_present;
 
@@ -473,19 +473,24 @@ static void update_vttbr(struct kvm *kvm)
 {
 	phys_addr_t pgd_phys;
 	u64 vmid;
+	bool new_gen;
 
-	if (!need_new_vmid_gen(kvm))
+	read_lock(&kvm_vmid_lock);
+	new_gen = need_new_vmid_gen(kvm);
+	read_unlock(&kvm_vmid_lock);
+
+	if (!new_gen)
 		return;
 
-	spin_lock(&kvm_vmid_lock);
+	write_lock(&kvm_vmid_lock);
 
 	/*
 	 * We need to re-check the vmid_gen here to ensure that if another vcpu
 	 * already allocated a valid vmid for this vm, then this vcpu should
 	 * use the same vmid.
 	 */
 	if (!need_new_vmid_gen(kvm)) {
-		spin_unlock(&kvm_vmid_lock);
+		write_unlock(&kvm_vmid_lock);
 		return;
 	}
 
@@ -519,7 +524,7 @@ static void update_vttbr(struct kvm *kvm)
 	vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK(kvm_vmid_bits);
 	kvm->arch.vttbr = kvm_phys_to_vttbr(pgd_phys) | vmid;
 
-	spin_unlock(&kvm_vmid_lock);
+	write_unlock(&kvm_vmid_lock);
 }
 
 static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)