Commit 73d7cf07 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

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

Pull KVM fixes from Paolo Bonzini:
 "Many patches, pretty much all of them small, that accumulated while I
  was on vacation.

  ARM:

   - Remove the last leftovers of the ill-fated FPSIMD host state
     mapping at EL2 stage-1

   - Fix unexpected advertisement to the guest of unimplemented S2 base
     granule sizes

   - Gracefully fail initialising pKVM if the interrupt controller isn't
     GICv3

   - Also gracefully fail initialising pKVM if the carveout allocation
     fails

   - Fix the computing of the minimum MMIO range required for the host
     on stage-2 fault

   - Fix the generation of the GICv3 Maintenance Interrupt in nested
     mode

  x86:

   - Reject SEV{-ES} intra-host migration if one or more vCPUs are
     actively being created, so as not to create a non-SEV{-ES} vCPU in
     an SEV{-ES} VM

   - Use a pre-allocated, per-vCPU buffer for handling de-sparsification
     of vCPU masks in Hyper-V hypercalls; fixes a "stack frame too
     large" issue

   - Allow out-of-range/invalid Xen event channel ports when configuring
     IRQ routing, to avoid dictating a specific ioctl() ordering to
     userspace

   - Conditionally reschedule when setting memory attributes to avoid
     soft lockups when userspace converts huge swaths of memory to/from
     private

   - Add back MWAIT as a required feature for the MONITOR/MWAIT selftest

   - Add a missing field in struct sev_data_snp_launch_start that
     resulted in the guest-visible workarounds field being filled at the
     wrong offset

   - Skip non-canonical address when processing Hyper-V PV TLB flushes
     to avoid VM-Fail on INVVPID

   - Advertise supported TDX TDVMCALLs to userspace

   - Pass SetupEventNotifyInterrupt arguments to userspace

   - Fix TSC frequency underflow"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: x86: avoid underflow when scaling TSC frequency
  KVM: arm64: Remove kvm_arch_vcpu_run_map_fp()
  KVM: arm64: Fix handling of FEAT_GTG for unimplemented granule sizes
  KVM: arm64: Don't free hyp pages with pKVM on GICv2
  KVM: arm64: Fix error path in init_hyp_mode()
  KVM: arm64: Adjust range correctly during host stage-2 faults
  KVM: arm64: nv: Fix MI line level calculation in vgic_v3_nested_update_mi()
  KVM: x86/hyper-v: Skip non-canonical addresses during PV TLB flush
  KVM: SVM: Add missing member in SNP_LAUNCH_START command structure
  Documentation: KVM: Fix unexpected unindent warnings
  KVM: selftests: Add back the missing check of MONITOR/MWAIT availability
  KVM: Allow CPU to reschedule while setting per-page memory attributes
  KVM: x86/xen: Allow 'out of range' event channel ports in IRQ routing table.
  KVM: x86/hyper-v: Use preallocated per-vCPU buffer for de-sparsified vCPU masks
  KVM: SVM: Initialize vmsa_pa in VMCB to INVALID_PAGE if VMSA page is NULL
  KVM: SVM: Reject SEV{-ES} intra host migration if vCPU creation is in-flight
  KVM: TDX: Report supported optional TDVMCALLs in TDX capabilities
  KVM: TDX: Exit to userspace for SetupEventNotifyInterrupt
parents 8c2e52eb 4578a747

Documentation/virt/kvm/api.rst

+22 −15
Original line number Diff line number Diff line
@@ -7196,6 +7196,10 @@ The valid value for 'flags' is: 
					u64 leaf;

					u64 r11, r12, r13, r14;

				} get_tdvmcall_info;

				struct {

					u64 ret;

					u64 vector;

				} setup_event_notify;

			};

		} tdx;
@@ -7226,6 +7230,9 @@ status of TDVMCALLs. The output values for the given leaf should be 
   placed in fields from ``r11`` to ``r14`` of the ``get_tdvmcall_info``

   field of the union.



* ``TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT``: the guest has requested to

set up a notification interrupt for vector ``vector``.



KVM may add support for more values in the future that may cause a userspace

exit, even without calls to ``KVM_ENABLE_CAP`` or similar.  In this case,

it will enter with output fields already valid; in the common case, the

Documentation/virt/kvm/x86/intel-tdx.rst

+14 −1
Original line number Diff line number Diff line
@@ -79,7 +79,20 @@ to be configured to the TDX guest. 
  struct kvm_tdx_capabilities {

        __u64 supported_attrs;

        __u64 supported_xfam;

        __u64 reserved[254];



        /* TDG.VP.VMCALL hypercalls executed in kernel and forwarded to

         * userspace, respectively

         */

        __u64 kernel_tdvmcallinfo_1_r11;

        __u64 user_tdvmcallinfo_1_r11;



        /* TDG.VP.VMCALL instruction executions subfunctions executed in kernel

         * and forwarded to userspace, respectively

         */

        __u64 kernel_tdvmcallinfo_1_r12;

        __u64 user_tdvmcallinfo_1_r12;



        __u64 reserved[250];



        /* Configurable CPUID bits for userspace */

        struct kvm_cpuid2 cpuid;

arch/arm64/include/asm/kvm_host.h

+0 −1
Original line number Diff line number Diff line
@@ -1480,7 +1480,6 @@ int kvm_vm_ioctl_get_reg_writable_masks(struct kvm *kvm, 
					struct reg_mask_range *range);



/* Guest/host FPSIMD coordination helpers */

int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu);

void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu);

void kvm_arch_vcpu_ctxflush_fp(struct kvm_vcpu *vcpu);

void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu);

arch/arm64/kvm/arm.c

+10 −6
Original line number Diff line number Diff line
@@ -825,10 +825,6 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu) 
	if (!kvm_arm_vcpu_is_finalized(vcpu))

		return -EPERM;



	ret = kvm_arch_vcpu_run_map_fp(vcpu);

	if (ret)

		return ret;



	if (likely(vcpu_has_run_once(vcpu)))

		return 0;
@@ -2129,7 +2125,7 @@ static void cpu_hyp_init(void *discard) 


static void cpu_hyp_uninit(void *discard)

{

	if (__this_cpu_read(kvm_hyp_initialized)) {

	if (!is_protected_kvm_enabled() && __this_cpu_read(kvm_hyp_initialized)) {

		cpu_hyp_reset();

		__this_cpu_write(kvm_hyp_initialized, 0);

	}
@@ -2345,8 +2341,13 @@ static void __init teardown_hyp_mode(void) 


	free_hyp_pgds();

	for_each_possible_cpu(cpu) {

		if (per_cpu(kvm_hyp_initialized, cpu))

			continue;



		free_pages(per_cpu(kvm_arm_hyp_stack_base, cpu), NVHE_STACK_SHIFT - PAGE_SHIFT);

		free_pages(kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu], nvhe_percpu_order());



		if (!kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu])

			continue;



		if (free_sve) {

			struct cpu_sve_state *sve_state;
@@ -2354,6 +2355,9 @@ static void __init teardown_hyp_mode(void) 
			sve_state = per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state;

			free_pages((unsigned long) sve_state, pkvm_host_sve_state_order());

		}



		free_pages(kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu], nvhe_percpu_order());



	}

}

arch/arm64/kvm/fpsimd.c

+0 −26
Original line number Diff line number Diff line
@@ -14,32 +14,6 @@ 
#include <asm/kvm_mmu.h>

#include <asm/sysreg.h>



/*

 * Called on entry to KVM_RUN unless this vcpu previously ran at least

 * once and the most recent prior KVM_RUN for this vcpu was called from

 * the same task as current (highly likely).

 *

 * This is guaranteed to execute before kvm_arch_vcpu_load_fp(vcpu),

 * such that on entering hyp the relevant parts of current are already

 * mapped.

 */

int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu)

{

	struct user_fpsimd_state *fpsimd = &current->thread.uw.fpsimd_state;

	int ret;



	/* pKVM has its own tracking of the host fpsimd state. */

	if (is_protected_kvm_enabled())

		return 0;



	/* Make sure the host task fpsimd state is visible to hyp: */

	ret = kvm_share_hyp(fpsimd, fpsimd + 1);

	if (ret)

		return ret;



	return 0;

}



/*

 * Prepare vcpu for saving the host's FPSIMD state and loading the guest's.

 * The actual loading is done by the FPSIMD access trap taken to hyp.