Commit 74bd160f 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
 "This is a pretty large diffstat for this time of the release. The main
  culprit is a reorganization of the AMD assembly trampoline, allowing
  percpu variables to be accessed early.

  This is needed for the return stack depth tracking retbleed mitigation
  that will be in 6.2, but it also makes it possible to tighten the IBRS
  restore on vmexit. The latter change is a long tail of the
  spectrev2/retbleed patches (the corresponding Intel change was simpler
  and went in already last June), which is why I am including it right
  now instead of sharing a topic branch with tip.

  Being assembly and being rich in comments makes the line count balloon
  a bit, but I am pretty confident in the change (famous last words)
  because the reorganization actually makes everything simpler and more
  understandable than before. It has also had external review and has
  been tested on the aforementioned 6.2 changes, which explode quite
  brutally without the fix.

  Apart from this, things are pretty normal.

  s390:

   - PCI fix

   - PV clock fix

  x86:

   - Fix clash between PMU MSRs and other MSRs

   - Prepare SVM assembly trampoline for 6.2 retbleed mitigation and
     for...

   - ... tightening IBRS restore on vmexit, moving it before the first
     RET or indirect branch

   - Fix log level for VMSA dump

   - Block all page faults during kvm_zap_gfn_range()

  Tools:

   - kvm_stat: fix incorrect detection of debugfs

   - kvm_stat: update vmexit definitions"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: x86/mmu: Block all page faults during kvm_zap_gfn_range()
  KVM: x86/pmu: Limit the maximum number of supported AMD GP counters
  KVM: x86/pmu: Limit the maximum number of supported Intel GP counters
  KVM: x86/pmu: Do not speculatively query Intel GP PMCs that don't exist yet
  KVM: SVM: Only dump VMSA to klog at KERN_DEBUG level
  tools/kvm_stat: update exit reasons for vmx/svm/aarch64/userspace
  tools/kvm_stat: fix incorrect detection of debugfs
  x86, KVM: remove unnecessary argument to x86_virt_spec_ctrl and callers
  KVM: SVM: move MSR_IA32_SPEC_CTRL save/restore to assembly
  KVM: SVM: restore host save area from assembly
  KVM: SVM: move guest vmsave/vmload back to assembly
  KVM: SVM: do not allocate struct svm_cpu_data dynamically
  KVM: SVM: remove dead field from struct svm_cpu_data
  KVM: SVM: remove unused field from struct vcpu_svm
  KVM: SVM: retrieve VMCB from assembly
  KVM: SVM: adjust register allocation for __svm_vcpu_run()
  KVM: SVM: replace regs argument of __svm_vcpu_run() with vcpu_svm
  KVM: x86: use a separate asm-offsets.c file
  KVM: s390: pci: Fix allocation size of aift kzdev elements
  KVM: s390: pv: don't allow userspace to set the clock under PV
parents 5be07b3f 6d3085e4

Documentation/virt/kvm/devices/vm.rst

+3 −0
Original line number Diff line number Diff line
@@ -215,6 +215,7 @@ KVM_S390_VM_TOD_EXT). 
:Parameters: address of a buffer in user space to store the data (u8) to

:Returns:   -EFAULT if the given address is not accessible from kernel space;

	    -EINVAL if setting the TOD clock extension to != 0 is not supported

	    -EOPNOTSUPP for a PV guest (TOD managed by the ultravisor)



3.2. ATTRIBUTE: KVM_S390_VM_TOD_LOW

-----------------------------------
@@ -224,6 +225,7 @@ the POP (u64). 


:Parameters: address of a buffer in user space to store the data (u64) to

:Returns:    -EFAULT if the given address is not accessible from kernel space

	     -EOPNOTSUPP for a PV guest (TOD managed by the ultravisor)



3.3. ATTRIBUTE: KVM_S390_VM_TOD_EXT

-----------------------------------
@@ -237,6 +239,7 @@ it, it is stored as 0 and not allowed to be set to a value != 0. 
	     (kvm_s390_vm_tod_clock) to

:Returns:   -EFAULT if the given address is not accessible from kernel space;

	    -EINVAL if setting the TOD clock extension to != 0 is not supported

	    -EOPNOTSUPP for a PV guest (TOD managed by the ultravisor)



4. GROUP: KVM_S390_VM_CRYPTO

============================

arch/s390/kvm/kvm-s390.c

+17 −9
Original line number Diff line number Diff line
@@ -1207,6 +1207,8 @@ static int kvm_s390_vm_get_migration(struct kvm *kvm, 
	return 0;

}



static void __kvm_s390_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod);



static int kvm_s390_set_tod_ext(struct kvm *kvm, struct kvm_device_attr *attr)

{

	struct kvm_s390_vm_tod_clock gtod;
@@ -1216,7 +1218,7 @@ static int kvm_s390_set_tod_ext(struct kvm *kvm, struct kvm_device_attr *attr) 


	if (!test_kvm_facility(kvm, 139) && gtod.epoch_idx)

		return -EINVAL;

	kvm_s390_set_tod_clock(kvm, &gtod);

	__kvm_s390_set_tod_clock(kvm, &gtod);



	VM_EVENT(kvm, 3, "SET: TOD extension: 0x%x, TOD base: 0x%llx",

		gtod.epoch_idx, gtod.tod);
@@ -1247,7 +1249,7 @@ static int kvm_s390_set_tod_low(struct kvm *kvm, struct kvm_device_attr *attr) 
			   sizeof(gtod.tod)))

		return -EFAULT;



	kvm_s390_set_tod_clock(kvm, &gtod);

	__kvm_s390_set_tod_clock(kvm, &gtod);

	VM_EVENT(kvm, 3, "SET: TOD base: 0x%llx", gtod.tod);

	return 0;

}
@@ -1259,6 +1261,16 @@ static int kvm_s390_set_tod(struct kvm *kvm, struct kvm_device_attr *attr) 
	if (attr->flags)

		return -EINVAL;



	mutex_lock(&kvm->lock);

	/*

	 * For protected guests, the TOD is managed by the ultravisor, so trying

	 * to change it will never bring the expected results.

	 */

	if (kvm_s390_pv_is_protected(kvm)) {

		ret = -EOPNOTSUPP;

		goto out_unlock;

	}



	switch (attr->attr) {

	case KVM_S390_VM_TOD_EXT:

		ret = kvm_s390_set_tod_ext(kvm, attr);
@@ -1273,6 +1285,9 @@ static int kvm_s390_set_tod(struct kvm *kvm, struct kvm_device_attr *attr) 
		ret = -ENXIO;

		break;

	}



out_unlock:

	mutex_unlock(&kvm->lock);

	return ret;

}
@@ -4377,13 +4392,6 @@ static void __kvm_s390_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_t 
	preempt_enable();

}



void kvm_s390_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod)

{

	mutex_lock(&kvm->lock);

	__kvm_s390_set_tod_clock(kvm, gtod);

	mutex_unlock(&kvm->lock);

}



int kvm_s390_try_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod)

{

	if (!mutex_trylock(&kvm->lock))

arch/s390/kvm/kvm-s390.h

+0 −1
Original line number Diff line number Diff line
@@ -363,7 +363,6 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu); 
int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu);



/* implemented in kvm-s390.c */

void kvm_s390_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod);

int kvm_s390_try_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod);

long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable);

int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr);

arch/s390/kvm/pci.c

+1 −1
Original line number Diff line number Diff line
@@ -126,7 +126,7 @@ int kvm_s390_pci_aen_init(u8 nisc) 
		return -EPERM;



	mutex_lock(&aift->aift_lock);

	aift->kzdev = kcalloc(ZPCI_NR_DEVICES, sizeof(struct kvm_zdev),

	aift->kzdev = kcalloc(ZPCI_NR_DEVICES, sizeof(struct kvm_zdev *),

			      GFP_KERNEL);

	if (!aift->kzdev) {

		rc = -ENOMEM;

arch/x86/include/asm/kvm_host.h

+6 −1
Original line number Diff line number Diff line
@@ -501,7 +501,12 @@ struct kvm_pmc { 
	bool intr;

};



/* More counters may conflict with other existing Architectural MSRs */

#define KVM_INTEL_PMC_MAX_GENERIC	8

#define MSR_ARCH_PERFMON_PERFCTR_MAX	(MSR_ARCH_PERFMON_PERFCTR0 + KVM_INTEL_PMC_MAX_GENERIC - 1)

#define MSR_ARCH_PERFMON_EVENTSEL_MAX	(MSR_ARCH_PERFMON_EVENTSEL0 + KVM_INTEL_PMC_MAX_GENERIC - 1)

#define KVM_PMC_MAX_FIXED	3

#define KVM_AMD_PMC_MAX_GENERIC	6

struct kvm_pmu {

	unsigned nr_arch_gp_counters;

	unsigned nr_arch_fixed_counters;
@@ -516,7 +521,7 @@ struct kvm_pmu { 
	u64 reserved_bits;

	u64 raw_event_mask;

	u8 version;

	struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC];

	struct kvm_pmc gp_counters[KVM_INTEL_PMC_MAX_GENERIC];

	struct kvm_pmc fixed_counters[KVM_PMC_MAX_FIXED];

	struct irq_work irq_work;

	DECLARE_BITMAP(reprogram_pmi, X86_PMC_IDX_MAX);