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

Pull KVM updates from Paolo Bonzini:
 "ARM:
   - data abort report and injection
   - steal time support
   - GICv4 performance improvements
   - vgic ITS emulation fixes
   - simplify FWB handling
   - enable halt polling counters
   - make the emulated timer PREEMPT_RT compliant

  s390:
   - small fixes and cleanups
   - selftest improvements
   - yield improvements

  PPC:
   - add capability to tell userspace whether we can single-step the
     guest
   - improve the allocation of XIVE virtual processor IDs
   - rewrite interrupt synthesis code to deliver interrupts in virtual
     mode when appropriate.
   - minor cleanups and improvements.

  x86:
   - XSAVES support for AMD
   - more accurate report of nested guest TSC to the nested hypervisor
   - retpoline optimizations
   - support for nested 5-level page tables
   - PMU virtualization optimizations, and improved support for nested
     PMU virtualization
   - correct latching of INITs for nested virtualization
   - IOAPIC optimization
   - TSX_CTRL virtualization for more TAA happiness
   - improved allocation and flushing of SEV ASIDs
   - many bugfixes and cleanups"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (127 commits)
  kvm: nVMX: Relax guest IA32_FEATURE_CONTROL constraints
  KVM: x86: Grab KVM's srcu lock when setting nested state
  KVM: x86: Open code shared_msr_update() in its only caller
  KVM: Fix jump label out_free_* in kvm_init()
  KVM: x86: Remove a spurious export of a static function
  KVM: x86: create mmu/ subdirectory
  KVM: nVMX: Remove unnecessary TLB flushes on L1<->L2 switches when L1 use apic-access-page
  KVM: x86: remove set but not used variable 'called'
  KVM: nVMX: Do not mark vmcs02->apic_access_page as dirty when unpinning
  KVM: vmx: use MSR_IA32_TSX_CTRL to hard-disable TSX on guest that lack it
  KVM: vmx: implement MSR_IA32_TSX_CTRL disable RTM functionality
  KVM: x86: implement MSR_IA32_TSX_CTRL effect on CPUID
  KVM: x86: do not modify masked bits of shared MSRs
  KVM: x86: fix presentation of TSX feature in ARCH_CAPABILITIES
  KVM: PPC: Book3S HV: XIVE: Fix potential page leak on error path
  KVM: PPC: Book3S HV: XIVE: Free previous EQ page when setting up a new one
  KVM: nVMX: Assume TLB entries of L1 and L2 are tagged differently if L0 use EPT
  KVM: x86: Unexport kvm_vcpu_reload_apic_access_page()
  KVM: nVMX: add CR4_LA57 bit to nested CR4_FIXED1
  KVM: nVMX: Use semi-colon instead of comma for exit-handlers initialization
  ...

Author: torvalds

Documentation/admin-guide/kernel-parameters.txt

@@ -3110,9 +3110,9 @@
 			[X86,PV_OPS] Disable paravirtualized VMware scheduler
 			clock and use the default one.
 
-	no-steal-acc	[X86,KVM] Disable paravirtualized steal time accounting.
-			steal time is computed, but won't influence scheduler
-			behaviour
+	no-steal-acc	[X86,KVM,ARM64] Disable paravirtualized steal time
+			accounting. steal time is computed, but won't
+			influence scheduler behaviour
 
 	nolapic		[X86-32,APIC] Do not enable or use the local APIC.
 

Documentation/virt/kvm/api.txt

@@ -1002,12 +1002,18 @@ Specifying exception.has_esr on a system that does not support it will return
 -EINVAL. Setting anything other than the lower 24bits of exception.serror_esr
 will return -EINVAL.
 
+It is not possible to read back a pending external abort (injected via
+KVM_SET_VCPU_EVENTS or otherwise) because such an exception is always delivered
+directly to the virtual CPU).
+
+
 struct kvm_vcpu_events {
 	struct {
 		__u8 serror_pending;
 		__u8 serror_has_esr;
+		__u8 ext_dabt_pending;
 		/* Align it to 8 bytes */
-		__u8 pad[6];
+		__u8 pad[5];
 		__u64 serror_esr;
 	} exception;
 	__u32 reserved[12];
@@ -1051,9 +1057,23 @@ contain a valid state and shall be written into the VCPU.
 
 ARM/ARM64:
 
+User space may need to inject several types of events to the guest.
+
 Set the pending SError exception state for this VCPU. It is not possible to
 'cancel' an Serror that has been made pending.
 
+If the guest performed an access to I/O memory which could not be handled by
+userspace, for example because of missing instruction syndrome decode
+information or because there is no device mapped at the accessed IPA, then
+userspace can ask the kernel to inject an external abort using the address
+from the exiting fault on the VCPU. It is a programming error to set
+ext_dabt_pending after an exit which was not either KVM_EXIT_MMIO or
+KVM_EXIT_ARM_NISV. This feature is only available if the system supports
+KVM_CAP_ARM_INJECT_EXT_DABT. This is a helper which provides commonality in
+how userspace reports accesses for the above cases to guests, across different
+userspace implementations. Nevertheless, userspace can still emulate all Arm
+exceptions by manipulating individual registers using the KVM_SET_ONE_REG API.
+
 See KVM_GET_VCPU_EVENTS for the data structure.
 
 
@@ -2982,6 +3002,9 @@ can be determined by querying the KVM_CAP_GUEST_DEBUG_HW_BPS and
 KVM_CAP_GUEST_DEBUG_HW_WPS capabilities which return a positive number
 indicating the number of supported registers.
 
+For ppc, the KVM_CAP_PPC_GUEST_DEBUG_SSTEP capability indicates whether
+the single-step debug event (KVM_GUESTDBG_SINGLESTEP) is supported.
+
 When debug events exit the main run loop with the reason
 KVM_EXIT_DEBUG with the kvm_debug_exit_arch part of the kvm_run
 structure containing architecture specific debug information.
@@ -4468,6 +4491,39 @@ Hyper-V SynIC state change. Notification is used to remap SynIC
 event/message pages and to enable/disable SynIC messages/events processing
 in userspace.
 
+		/* KVM_EXIT_ARM_NISV */
+		struct {
+			__u64 esr_iss;
+			__u64 fault_ipa;
+		} arm_nisv;
+
+Used on arm and arm64 systems. If a guest accesses memory not in a memslot,
+KVM will typically return to userspace and ask it to do MMIO emulation on its
+behalf. However, for certain classes of instructions, no instruction decode
+(direction, length of memory access) is provided, and fetching and decoding
+the instruction from the VM is overly complicated to live in the kernel.
+
+Historically, when this situation occurred, KVM would print a warning and kill
+the VM. KVM assumed that if the guest accessed non-memslot memory, it was
+trying to do I/O, which just couldn't be emulated, and the warning message was
+phrased accordingly. However, what happened more often was that a guest bug
+caused access outside the guest memory areas which should lead to a more
+meaningful warning message and an external abort in the guest, if the access
+did not fall within an I/O window.
+
+Userspace implementations can query for KVM_CAP_ARM_NISV_TO_USER, and enable
+this capability at VM creation. Once this is done, these types of errors will
+instead return to userspace with KVM_EXIT_ARM_NISV, with the valid bits from
+the HSR (arm) and ESR_EL2 (arm64) in the esr_iss field, and the faulting IPA
+in the fault_ipa field. Userspace can either fix up the access if it's
+actually an I/O access by decoding the instruction from guest memory (if it's
+very brave) and continue executing the guest, or it can decide to suspend,
+dump, or restart the guest.
+
+Note that KVM does not skip the faulting instruction as it does for
+KVM_EXIT_MMIO, but userspace has to emulate any change to the processing state
+if it decides to decode and emulate the instruction.
+
 		/* Fix the size of the union. */
 		char padding[256];
 	};

Documentation/virt/kvm/arm/pvtime.rst

@@ -0,0 +1,80 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Paravirtualized time support for arm64
+======================================
+
+Arm specification DEN0057/A defines a standard for paravirtualised time
+support for AArch64 guests:
+
+https://developer.arm.com/docs/den0057/a
+
+KVM/arm64 implements the stolen time part of this specification by providing
+some hypervisor service calls to support a paravirtualized guest obtaining a
+view of the amount of time stolen from its execution.
+
+Two new SMCCC compatible hypercalls are defined:
+
+* PV_TIME_FEATURES: 0xC5000020
+* PV_TIME_ST:       0xC5000021
+
+These are only available in the SMC64/HVC64 calling convention as
+paravirtualized time is not available to 32 bit Arm guests. The existence of
+the PV_FEATURES hypercall should be probed using the SMCCC 1.1 ARCH_FEATURES
+mechanism before calling it.
+
+PV_TIME_FEATURES
+    ============= ========    ==========
+    Function ID:  (uint32)    0xC5000020
+    PV_call_id:   (uint32)    The function to query for support.
+                              Currently only PV_TIME_ST is supported.
+    Return value: (int64)     NOT_SUPPORTED (-1) or SUCCESS (0) if the relevant
+                              PV-time feature is supported by the hypervisor.
+    ============= ========    ==========
+
+PV_TIME_ST
+    ============= ========    ==========
+    Function ID:  (uint32)    0xC5000021
+    Return value: (int64)     IPA of the stolen time data structure for this
+                              VCPU. On failure:
+                              NOT_SUPPORTED (-1)
+    ============= ========    ==========
+
+The IPA returned by PV_TIME_ST should be mapped by the guest as normal memory
+with inner and outer write back caching attributes, in the inner shareable
+domain. A total of 16 bytes from the IPA returned are guaranteed to be
+meaningfully filled by the hypervisor (see structure below).
+
+PV_TIME_ST returns the structure for the calling VCPU.
+
+Stolen Time
+-----------
+
+The structure pointed to by the PV_TIME_ST hypercall is as follows:
+
++-------------+-------------+-------------+----------------------------+
+| Field       | Byte Length | Byte Offset | Description                |
++=============+=============+=============+============================+
+| Revision    |      4      |      0      | Must be 0 for version 1.0  |
++-------------+-------------+-------------+----------------------------+
+| Attributes  |      4      |      4      | Must be 0                  |
++-------------+-------------+-------------+----------------------------+
+| Stolen time |      8      |      8      | Stolen time in unsigned    |
+|             |             |             | nanoseconds indicating how |
+|             |             |             | much time this VCPU thread |
+|             |             |             | was involuntarily not      |
+|             |             |             | running on a physical CPU. |
++-------------+-------------+-------------+----------------------------+
+
+All values in the structure are stored little-endian.
+
+The structure will be updated by the hypervisor prior to scheduling a VCPU. It
+will be present within a reserved region of the normal memory given to the
+guest. The guest should not attempt to write into this memory. There is a
+structure per VCPU of the guest.
+
+It is advisable that one or more 64k pages are set aside for the purpose of
+these structures and not used for other purposes, this enables the guest to map
+the region using 64k pages and avoids conflicting attributes with other memory.
+
+For the user space interface see Documentation/virt/kvm/devices/vcpu.txt
+section "3. GROUP: KVM_ARM_VCPU_PVTIME_CTRL".

Documentation/virt/kvm/devices/vcpu.txt

@@ -60,3 +60,17 @@ time to use the number provided for a given timer, overwriting any previously
 configured values on other VCPUs.  Userspace should configure the interrupt
 numbers on at least one VCPU after creating all VCPUs and before running any
 VCPUs.
+
+3. GROUP: KVM_ARM_VCPU_PVTIME_CTRL
+Architectures: ARM64
+
+3.1 ATTRIBUTE: KVM_ARM_VCPU_PVTIME_IPA
+Parameters: 64-bit base address
+Returns: -ENXIO:  Stolen time not implemented
+         -EEXIST: Base address already set for this VCPU
+         -EINVAL: Base address not 64 byte aligned
+
+Specifies the base address of the stolen time structure for this VCPU. The
+base address must be 64 byte aligned and exist within a valid guest memory
+region. See Documentation/virt/kvm/arm/pvtime.txt for more information
+including the layout of the stolen time structure.

Documentation/virt/kvm/devices/xics.txt

@@ -3,9 +3,19 @@ XICS interrupt controller
 Device type supported: KVM_DEV_TYPE_XICS
 
 Groups:
-  KVM_DEV_XICS_SOURCES
+  1. KVM_DEV_XICS_GRP_SOURCES
   Attributes: One per interrupt source, indexed by the source number.
 
+  2. KVM_DEV_XICS_GRP_CTRL
+  Attributes:
+    2.1 KVM_DEV_XICS_NR_SERVERS (write only)
+  The kvm_device_attr.addr points to a __u32 value which is the number of
+  interrupt server numbers (ie, highest possible vcpu id plus one).
+  Errors:
+    -EINVAL: Value greater than KVM_MAX_VCPU_ID.
+    -EFAULT: Invalid user pointer for attr->addr.
+    -EBUSY:  A vcpu is already connected to the device.
+
 This device emulates the XICS (eXternal Interrupt Controller
 Specification) defined in PAPR.  The XICS has a set of interrupt
 sources, each identified by a 20-bit source number, and a set of
@@ -38,7 +48,7 @@ least-significant end of the word:
 
 Each source has 64 bits of state that can be read and written using
 the KVM_GET_DEVICE_ATTR and KVM_SET_DEVICE_ATTR ioctls, specifying the
-KVM_DEV_XICS_SOURCES attribute group, with the attribute number being
+KVM_DEV_XICS_GRP_SOURCES attribute group, with the attribute number being
 the interrupt source number.  The 64 bit state word has the following
 bitfields, starting from the least-significant end of the word:
 

Documentation/virt/kvm/devices/xive.txt

@@ -78,6 +78,14 @@ the legacy interrupt mode, referred as XICS (POWER7/8).
     migrating the VM.
     Errors: none
 
+    1.3 KVM_DEV_XIVE_NR_SERVERS (write only)
+    The kvm_device_attr.addr points to a __u32 value which is the number of
+    interrupt server numbers (ie, highest possible vcpu id plus one).
+    Errors:
+      -EINVAL: Value greater than KVM_MAX_VCPU_ID.
+      -EFAULT: Invalid user pointer for attr->addr.
+      -EBUSY:  A vCPU is already connected to the device.
+
   2. KVM_DEV_XIVE_GRP_SOURCE (write only)
   Initializes a new source in the XIVE device and mask it.
   Attributes:

arch/arm/include/asm/kvm_arm.h

@@ -162,6 +162,7 @@
 #define HSR_ISV		(_AC(1, UL) << HSR_ISV_SHIFT)
 #define HSR_SRT_SHIFT	(16)
 #define HSR_SRT_MASK	(0xf << HSR_SRT_SHIFT)
+#define HSR_CM		(1 << 8)
 #define HSR_FSC		(0x3f)
 #define HSR_FSC_TYPE	(0x3c)
 #define HSR_SSE		(1 << 21)

arch/arm/include/asm/kvm_emulate.h

@@ -95,12 +95,12 @@ static inline unsigned long *vcpu_hcr(const struct kvm_vcpu *vcpu)
 	return (unsigned long *)&vcpu->arch.hcr;
 }
 
-static inline void vcpu_clear_wfe_traps(struct kvm_vcpu *vcpu)
+static inline void vcpu_clear_wfx_traps(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hcr &= ~HCR_TWE;
 }
 
-static inline void vcpu_set_wfe_traps(struct kvm_vcpu *vcpu)
+static inline void vcpu_set_wfx_traps(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hcr |= HCR_TWE;
 }
@@ -167,6 +167,11 @@ static inline bool kvm_vcpu_dabt_isvalid(struct kvm_vcpu *vcpu)
 	return kvm_vcpu_get_hsr(vcpu) & HSR_ISV;
 }
 
+static inline unsigned long kvm_vcpu_dabt_iss_nisv_sanitized(const struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & (HSR_CM | HSR_WNR | HSR_FSC);
+}
+
 static inline bool kvm_vcpu_dabt_iswrite(struct kvm_vcpu *vcpu)
 {
 	return kvm_vcpu_get_hsr(vcpu) & HSR_WNR;

arch/arm/include/asm/kvm_host.h

@@ -7,6 +7,7 @@
 #ifndef __ARM_KVM_HOST_H__
 #define __ARM_KVM_HOST_H__
 
+#include <linux/arm-smccc.h>
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/kvm_types.h>
@@ -38,6 +39,7 @@
 	KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_IRQ_PENDING	KVM_ARCH_REQ(1)
 #define KVM_REQ_VCPU_RESET	KVM_ARCH_REQ(2)
+#define KVM_REQ_RECORD_STEAL	KVM_ARCH_REQ(3)
 
 DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
 
@@ -76,6 +78,14 @@ struct kvm_arch {
 
 	/* Mandated version of PSCI */
 	u32 psci_version;
+
+	/*
+	 * If we encounter a data abort without valid instruction syndrome
+	 * information, report this to user space.  User space can (and
+	 * should) opt in to this feature if KVM_CAP_ARM_NISV_TO_USER is
+	 * supported.
+	 */
+	bool return_nisv_io_abort_to_user;
 };
 
 #define KVM_NR_MEM_OBJS     40
@@ -323,6 +333,29 @@ static inline int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 int kvm_perf_init(void);
 int kvm_perf_teardown(void);
 
+static inline long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu)
+{
+	return SMCCC_RET_NOT_SUPPORTED;
+}
+
+static inline gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu)
+{
+	return GPA_INVALID;
+}
+
+static inline void kvm_update_stolen_time(struct kvm_vcpu *vcpu)
+{
+}
+
+static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch)
+{
+}
+
+static inline bool kvm_arm_is_pvtime_enabled(struct kvm_vcpu_arch *vcpu_arch)
+{
+	return false;
+}
+
 void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot);
 
 struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);

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

@@ -131,8 +131,9 @@ struct kvm_vcpu_events {
 	struct {
 		__u8 serror_pending;
 		__u8 serror_has_esr;
+		__u8 ext_dabt_pending;
 		/* Align it to 8 bytes */
-		__u8 pad[6];
+		__u8 pad[5];
 		__u64 serror_esr;
 	} exception;
 	__u32 reserved[12];