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

Pull kvm updates from Paolo Bonzini:
 "S390:

   - Changes to FPU handling came in via the main s390 pull request

   - Only deliver to the guest the SCLP events that userspace has
     requested

   - More virtual vs physical address fixes (only a cleanup since
     virtual and physical address spaces are currently the same)

   - Fix selftests undefined behavior

  x86:

   - Fix a restriction that the guest can't program a PMU event whose
     encoding matches an architectural event that isn't included in the
     guest CPUID. The enumeration of an architectural event only says
     that if a CPU supports an architectural event, then the event can
     be programmed *using the architectural encoding*. The enumeration
     does NOT say anything about the encoding when the CPU doesn't
     report support the event *in general*. It might support it, and it
     might support it using the same encoding that made it into the
     architectural PMU spec

   - Fix a variety of bugs in KVM's emulation of RDPMC (more details on
     individual commits) and add a selftest to verify KVM correctly
     emulates RDMPC, counter availability, and a variety of other
     PMC-related behaviors that depend on guest CPUID and therefore are
     easier to validate with selftests than with custom guests (aka
     kvm-unit-tests)

   - Zero out PMU state on AMD if the virtual PMU is disabled, it does
     not cause any bug but it wastes time in various cases where KVM
     would check if a PMC event needs to be synthesized

   - Optimize triggering of emulated events, with a nice ~10%
     performance improvement in VM-Exit microbenchmarks when a vPMU is
     exposed to the guest

   - Tighten the check for "PMI in guest" to reduce false positives if
     an NMI arrives in the host while KVM is handling an IRQ VM-Exit

   - Fix a bug where KVM would report stale/bogus exit qualification
     information when exiting to userspace with an internal error exit
     code

   - Add a VMX flag in /proc/cpuinfo to report 5-level EPT support

   - Rework TDP MMU root unload, free, and alloc to run with mmu_lock
     held for read, e.g. to avoid serializing vCPUs when userspace
     deletes a memslot

   - Tear down TDP MMU page tables at 4KiB granularity (used to be
     1GiB). KVM doesn't support yielding in the middle of processing a
     zap, and 1GiB granularity resulted in multi-millisecond lags that
     are quite impolite for CONFIG_PREEMPT kernels

   - Allocate write-tracking metadata on-demand to avoid the memory
     overhead when a kernel is built with i915 virtualization support
     but the workloads use neither shadow paging nor i915 virtualization

   - Explicitly initialize a variety of on-stack variables in the
     emulator that triggered KMSAN false positives

   - Fix the debugregs ABI for 32-bit KVM

   - Rework the "force immediate exit" code so that vendor code
     ultimately decides how and when to force the exit, which allowed
     some optimization for both Intel and AMD

   - Fix a long-standing bug where kvm_has_noapic_vcpu could be left
     elevated if vCPU creation ultimately failed, causing extra
     unnecessary work

   - Cleanup the logic for checking if the currently loaded vCPU is
     in-kernel

   - Harden against underflowing the active mmu_notifier invalidation
     count, so that "bad" invalidations (usually due to bugs elsehwere
     in the kernel) are detected earlier and are less likely to hang the
     kernel

  x86 Xen emulation:

   - Overlay pages can now be cached based on host virtual address,
     instead of guest physical addresses. This removes the need to
     reconfigure and invalidate the cache if the guest changes the gpa
     but the underlying host virtual address remains the same

   - When possible, use a single host TSC value when computing the
     deadline for Xen timers in order to improve the accuracy of the
     timer emulation

   - Inject pending upcall events when the vCPU software-enables its
     APIC to fix a bug where an upcall can be lost (and to follow Xen's
     behavior)

   - Fall back to the slow path instead of warning if "fast" IRQ
     delivery of Xen events fails, e.g. if the guest has aliased xAPIC
     IDs

  RISC-V:

   - Support exception and interrupt handling in selftests

   - New self test for RISC-V architectural timer (Sstc extension)

   - New extension support (Ztso, Zacas)

   - Support userspace emulation of random number seed CSRs

  ARM:

   - Infrastructure for building KVM's trap configuration based on the
     architectural features (or lack thereof) advertised in the VM's ID
     registers

   - Support for mapping vfio-pci BARs as Normal-NC (vaguely similar to
     x86's WC) at stage-2, improving the performance of interacting with
     assigned devices that can tolerate it

   - Conversion of KVM's representation of LPIs to an xarray, utilized
     to address serialization some of the serialization on the LPI
     injection path

   - Support for _architectural_ VHE-only systems, advertised through
     the absence of FEAT_E2H0 in the CPU's ID register

   - Miscellaneous cleanups, fixes, and spelling corrections to KVM and
     selftests

  LoongArch:

   - Set reserved bits as zero in CPUCFG

   - Start SW timer only when vcpu is blocking

   - Do not restart SW timer when it is expired

   - Remove unnecessary CSR register saving during enter guest

   - Misc cleanups and fixes as usual

  Generic:

   - Clean up Kconfig by removing CONFIG_HAVE_KVM, which was basically
     always true on all architectures except MIPS (where Kconfig
     determines the available depending on CPU capabilities). It is
     replaced either by an architecture-dependent symbol for MIPS, and
     IS_ENABLED(CONFIG_KVM) everywhere else

   - Factor common "select" statements in common code instead of
     requiring each architecture to specify it

   - Remove thoroughly obsolete APIs from the uapi headers

   - Move architecture-dependent stuff to uapi/asm/kvm.h

   - Always flush the async page fault workqueue when a work item is
     being removed, especially during vCPU destruction, to ensure that
     there are no workers running in KVM code when all references to
     KVM-the-module are gone, i.e. to prevent a very unlikely
     use-after-free if kvm.ko is unloaded

   - Grab a reference to the VM's mm_struct in the async #PF worker
     itself instead of gifting the worker a reference, so that there's
     no need to remember to *conditionally* clean up after the worker

  Selftests:

   - Reduce boilerplate especially when utilize selftest TAP
     infrastructure

   - Add basic smoke tests for SEV and SEV-ES, along with a pile of
     library support for handling private/encrypted/protected memory

   - Fix benign bugs where tests neglect to close() guest_memfd files"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (246 commits)
  selftests: kvm: remove meaningless assignments in Makefiles
  KVM: riscv: selftests: Add Zacas extension to get-reg-list test
  RISC-V: KVM: Allow Zacas extension for Guest/VM
  KVM: riscv: selftests: Add Ztso extension to get-reg-list test
  RISC-V: KVM: Allow Ztso extension for Guest/VM
  RISC-V: KVM: Forward SEED CSR access to user space
  KVM: riscv: selftests: Add sstc timer test
  KVM: riscv: selftests: Change vcpu_has_ext to a common function
  KVM: riscv: selftests: Add guest helper to get vcpu id
  KVM: riscv: selftests: Add exception handling support
  LoongArch: KVM: Remove unnecessary CSR register saving during enter guest
  LoongArch: KVM: Do not restart SW timer when it is expired
  LoongArch: KVM: Start SW timer only when vcpu is blocking
  LoongArch: KVM: Set reserved bits as zero in CPUCFG
  KVM: selftests: Explicitly close guest_memfd files in some gmem tests
  KVM: x86/xen: fix recursive deadlock in timer injection
  KVM: pfncache: simplify locking and make more self-contained
  KVM: x86/xen: remove WARN_ON_ONCE() with false positives in evtchn delivery
  KVM: x86/xen: inject vCPU upcall vector when local APIC is enabled
  KVM: x86/xen: improve accuracy of Xen timers
  ...

2 files changed, 278 insertions, 9 deletions

diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index a448d0964fc0..ad29984d5e39 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -7,6 +7,8 @@
  *
  */
 
+#include <linux/const.h>
+#include <linux/bits.h>
 #include <linux/types.h>
 #include <linux/ioctl.h>
 #include <linux/stddef.h>
@@ -40,7 +42,6 @@
 #define __KVM_HAVE_IRQ_LINE
 #define __KVM_HAVE_MSI
 #define __KVM_HAVE_USER_NMI
-#define __KVM_HAVE_GUEST_DEBUG
 #define __KVM_HAVE_MSIX
 #define __KVM_HAVE_MCE
 #define __KVM_HAVE_PIT_STATE2
@@ -49,7 +50,6 @@
 #define __KVM_HAVE_DEBUGREGS
 #define __KVM_HAVE_XSAVE
 #define __KVM_HAVE_XCRS
-#define __KVM_HAVE_READONLY_MEM
 
 /* Architectural interrupt line count. */
 #define KVM_NR_INTERRUPTS 256
@@ -526,9 +526,278 @@ struct kvm_pmu_event_filter {
 #define KVM_PMU_EVENT_ALLOW 0
 #define KVM_PMU_EVENT_DENY 1
 
-#define KVM_PMU_EVENT_FLAG_MASKED_EVENTS BIT(0)
+#define KVM_PMU_EVENT_FLAG_MASKED_EVENTS _BITUL(0)
 #define KVM_PMU_EVENT_FLAGS_VALID_MASK (KVM_PMU_EVENT_FLAG_MASKED_EVENTS)
 
+/* for KVM_CAP_MCE */
+struct kvm_x86_mce {
+	__u64 status;
+	__u64 addr;
+	__u64 misc;
+	__u64 mcg_status;
+	__u8 bank;
+	__u8 pad1[7];
+	__u64 pad2[3];
+};
+
+/* for KVM_CAP_XEN_HVM */
+#define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR	(1 << 0)
+#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL	(1 << 1)
+#define KVM_XEN_HVM_CONFIG_SHARED_INFO		(1 << 2)
+#define KVM_XEN_HVM_CONFIG_RUNSTATE		(1 << 3)
+#define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL	(1 << 4)
+#define KVM_XEN_HVM_CONFIG_EVTCHN_SEND		(1 << 5)
+#define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG	(1 << 6)
+#define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE	(1 << 7)
+#define KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA	(1 << 8)
+
+struct kvm_xen_hvm_config {
+	__u32 flags;
+	__u32 msr;
+	__u64 blob_addr_32;
+	__u64 blob_addr_64;
+	__u8 blob_size_32;
+	__u8 blob_size_64;
+	__u8 pad2[30];
+};
+
+struct kvm_xen_hvm_attr {
+	__u16 type;
+	__u16 pad[3];
+	union {
+		__u8 long_mode;
+		__u8 vector;
+		__u8 runstate_update_flag;
+		union {
+			__u64 gfn;
+#define KVM_XEN_INVALID_GFN ((__u64)-1)
+			__u64 hva;
+		} shared_info;
+		struct {
+			__u32 send_port;
+			__u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */
+			__u32 flags;
+#define KVM_XEN_EVTCHN_DEASSIGN		(1 << 0)
+#define KVM_XEN_EVTCHN_UPDATE		(1 << 1)
+#define KVM_XEN_EVTCHN_RESET		(1 << 2)
+			/*
+			 * Events sent by the guest are either looped back to
+			 * the guest itself (potentially on a different port#)
+			 * or signalled via an eventfd.
+			 */
+			union {
+				struct {
+					__u32 port;
+					__u32 vcpu;
+					__u32 priority;
+				} port;
+				struct {
+					__u32 port; /* Zero for eventfd */
+					__s32 fd;
+				} eventfd;
+				__u32 padding[4];
+			} deliver;
+		} evtchn;
+		__u32 xen_version;
+		__u64 pad[8];
+	} u;
+};
+
+
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
+#define KVM_XEN_ATTR_TYPE_LONG_MODE		0x0
+#define KVM_XEN_ATTR_TYPE_SHARED_INFO		0x1
+#define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR		0x2
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */
+#define KVM_XEN_ATTR_TYPE_EVTCHN		0x3
+#define KVM_XEN_ATTR_TYPE_XEN_VERSION		0x4
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG */
+#define KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG	0x5
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA */
+#define KVM_XEN_ATTR_TYPE_SHARED_INFO_HVA	0x6
+
+struct kvm_xen_vcpu_attr {
+	__u16 type;
+	__u16 pad[3];
+	union {
+		__u64 gpa;
+#define KVM_XEN_INVALID_GPA ((__u64)-1)
+		__u64 hva;
+		__u64 pad[8];
+		struct {
+			__u64 state;
+			__u64 state_entry_time;
+			__u64 time_running;
+			__u64 time_runnable;
+			__u64 time_blocked;
+			__u64 time_offline;
+		} runstate;
+		__u32 vcpu_id;
+		struct {
+			__u32 port;
+			__u32 priority;
+			__u64 expires_ns;
+		} timer;
+		__u8 vector;
+	} u;
+};
+
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
+#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO	0x0
+#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO	0x1
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR	0x2
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT	0x3
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA	0x4
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST	0x5
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */
+#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID		0x6
+#define KVM_XEN_VCPU_ATTR_TYPE_TIMER		0x7
+#define KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR	0x8
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA */
+#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO_HVA	0x9
+
+/* Secure Encrypted Virtualization command */
+enum sev_cmd_id {
+	/* Guest initialization commands */
+	KVM_SEV_INIT = 0,
+	KVM_SEV_ES_INIT,
+	/* Guest launch commands */
+	KVM_SEV_LAUNCH_START,
+	KVM_SEV_LAUNCH_UPDATE_DATA,
+	KVM_SEV_LAUNCH_UPDATE_VMSA,
+	KVM_SEV_LAUNCH_SECRET,
+	KVM_SEV_LAUNCH_MEASURE,
+	KVM_SEV_LAUNCH_FINISH,
+	/* Guest migration commands (outgoing) */
+	KVM_SEV_SEND_START,
+	KVM_SEV_SEND_UPDATE_DATA,
+	KVM_SEV_SEND_UPDATE_VMSA,
+	KVM_SEV_SEND_FINISH,
+	/* Guest migration commands (incoming) */
+	KVM_SEV_RECEIVE_START,
+	KVM_SEV_RECEIVE_UPDATE_DATA,
+	KVM_SEV_RECEIVE_UPDATE_VMSA,
+	KVM_SEV_RECEIVE_FINISH,
+	/* Guest status and debug commands */
+	KVM_SEV_GUEST_STATUS,
+	KVM_SEV_DBG_DECRYPT,
+	KVM_SEV_DBG_ENCRYPT,
+	/* Guest certificates commands */
+	KVM_SEV_CERT_EXPORT,
+	/* Attestation report */
+	KVM_SEV_GET_ATTESTATION_REPORT,
+	/* Guest Migration Extension */
+	KVM_SEV_SEND_CANCEL,
+
+	KVM_SEV_NR_MAX,
+};
+
+struct kvm_sev_cmd {
+	__u32 id;
+	__u64 data;
+	__u32 error;
+	__u32 sev_fd;
+};
+
+struct kvm_sev_launch_start {
+	__u32 handle;
+	__u32 policy;
+	__u64 dh_uaddr;
+	__u32 dh_len;
+	__u64 session_uaddr;
+	__u32 session_len;
+};
+
+struct kvm_sev_launch_update_data {
+	__u64 uaddr;
+	__u32 len;
+};
+
+
+struct kvm_sev_launch_secret {
+	__u64 hdr_uaddr;
+	__u32 hdr_len;
+	__u64 guest_uaddr;
+	__u32 guest_len;
+	__u64 trans_uaddr;
+	__u32 trans_len;
+};
+
+struct kvm_sev_launch_measure {
+	__u64 uaddr;
+	__u32 len;
+};
+
+struct kvm_sev_guest_status {
+	__u32 handle;
+	__u32 policy;
+	__u32 state;
+};
+
+struct kvm_sev_dbg {
+	__u64 src_uaddr;
+	__u64 dst_uaddr;
+	__u32 len;
+};
+
+struct kvm_sev_attestation_report {
+	__u8 mnonce[16];
+	__u64 uaddr;
+	__u32 len;
+};
+
+struct kvm_sev_send_start {
+	__u32 policy;
+	__u64 pdh_cert_uaddr;
+	__u32 pdh_cert_len;
+	__u64 plat_certs_uaddr;
+	__u32 plat_certs_len;
+	__u64 amd_certs_uaddr;
+	__u32 amd_certs_len;
+	__u64 session_uaddr;
+	__u32 session_len;
+};
+
+struct kvm_sev_send_update_data {
+	__u64 hdr_uaddr;
+	__u32 hdr_len;
+	__u64 guest_uaddr;
+	__u32 guest_len;
+	__u64 trans_uaddr;
+	__u32 trans_len;
+};
+
+struct kvm_sev_receive_start {
+	__u32 handle;
+	__u32 policy;
+	__u64 pdh_uaddr;
+	__u32 pdh_len;
+	__u64 session_uaddr;
+	__u32 session_len;
+};
+
+struct kvm_sev_receive_update_data {
+	__u64 hdr_uaddr;
+	__u32 hdr_len;
+	__u64 guest_uaddr;
+	__u32 guest_len;
+	__u64 trans_uaddr;
+	__u32 trans_len;
+};
+
+#define KVM_X2APIC_API_USE_32BIT_IDS            (1ULL << 0)
+#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK  (1ULL << 1)
+
+struct kvm_hyperv_eventfd {
+	__u32 conn_id;
+	__s32 fd;
+	__u32 flags;
+	__u32 padding[3];
+};
+
+#define KVM_HYPERV_CONN_ID_MASK		0x00ffffff
+#define KVM_HYPERV_EVENTFD_DEASSIGN	(1 << 0)
+
 /*
  * Masked event layout.
  * Bits   Description
@@ -549,10 +818,10 @@ struct kvm_pmu_event_filter {
 	((__u64)(!!(exclude)) << 55))
 
 #define KVM_PMU_MASKED_ENTRY_EVENT_SELECT \
-	(GENMASK_ULL(7, 0) | GENMASK_ULL(35, 32))
-#define KVM_PMU_MASKED_ENTRY_UMASK_MASK		(GENMASK_ULL(63, 56))
-#define KVM_PMU_MASKED_ENTRY_UMASK_MATCH	(GENMASK_ULL(15, 8))
-#define KVM_PMU_MASKED_ENTRY_EXCLUDE		(BIT_ULL(55))
+	(__GENMASK_ULL(7, 0) | __GENMASK_ULL(35, 32))
+#define KVM_PMU_MASKED_ENTRY_UMASK_MASK		(__GENMASK_ULL(63, 56))
+#define KVM_PMU_MASKED_ENTRY_UMASK_MATCH	(__GENMASK_ULL(15, 8))
+#define KVM_PMU_MASKED_ENTRY_EXCLUDE		(_BITULL(55))
 #define KVM_PMU_MASKED_ENTRY_UMASK_MASK_SHIFT	(56)
 
 /* for KVM_{GET,SET,HAS}_DEVICE_ATTR */
@@ -560,7 +829,7 @@ struct kvm_pmu_event_filter {
 #define   KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */
 
 /* x86-specific KVM_EXIT_HYPERCALL flags. */
-#define KVM_EXIT_HYPERCALL_LONG_MODE	BIT(0)
+#define KVM_EXIT_HYPERCALL_LONG_MODE	_BITULL(0)
 
 #define KVM_X86_DEFAULT_VM	0
 #define KVM_X86_SW_PROTECTED_VM	1
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 6e64b27b2c1e..6bc3456a8ebf 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -92,7 +92,7 @@ struct kvm_clock_pairing {
 #define KVM_ASYNC_PF_DELIVERY_AS_INT		(1 << 3)
 
 /* MSR_KVM_ASYNC_PF_INT */
-#define KVM_ASYNC_PF_VEC_MASK			GENMASK(7, 0)
+#define KVM_ASYNC_PF_VEC_MASK			__GENMASK(7, 0)
 
 /* MSR_KVM_MIGRATION_CONTROL */
 #define KVM_MIGRATION_READY		(1 << 0)