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

Pull kvm updates from Paolo Bonzini:
 "s390:

   - More phys_to_virt conversions

   - Improvement of AP management for VSIE (nested virtualization)

  ARM64:

   - Numerous fixes for the pathological lock inversion issue that
     plagued KVM/arm64 since... forever.

   - New framework allowing SMCCC-compliant hypercalls to be forwarded
     to userspace, hopefully paving the way for some more features being
     moved to VMMs rather than be implemented in the kernel.

   - Large rework of the timer code to allow a VM-wide offset to be
     applied to both virtual and physical counters as well as a
     per-timer, per-vcpu offset that complements the global one. This
     last part allows the NV timer code to be implemented on top.

   - A small set of fixes to make sure that we don't change anything
     affecting the EL1&0 translation regime just after having having
     taken an exception to EL2 until we have executed a DSB. This
     ensures that speculative walks started in EL1&0 have completed.

   - The usual selftest fixes and improvements.

  x86:

   - Optimize CR0.WP toggling by avoiding an MMU reload when TDP is
     enabled, and by giving the guest control of CR0.WP when EPT is
     enabled on VMX (VMX-only because SVM doesn't support per-bit
     controls)

   - Add CR0/CR4 helpers to query single bits, and clean up related code
     where KVM was interpreting kvm_read_cr4_bits()'s "unsigned long"
     return as a bool

   - Move AMD_PSFD to cpufeatures.h and purge KVM's definition

   - Avoid unnecessary writes+flushes when the guest is only adding new
     PTEs

   - Overhaul .sync_page() and .invlpg() to utilize .sync_page()'s
     optimizations when emulating invalidations

   - Clean up the range-based flushing APIs

   - Revamp the TDP MMU's reaping of Accessed/Dirty bits to clear a
     single A/D bit using a LOCK AND instead of XCHG, and skip all of
     the "handle changed SPTE" overhead associated with writing the
     entire entry

   - Track the number of "tail" entries in a pte_list_desc to avoid
     having to walk (potentially) all descriptors during insertion and
     deletion, which gets quite expensive if the guest is spamming
     fork()

   - Disallow virtualizing legacy LBRs if architectural LBRs are
     available, the two are mutually exclusive in hardware

   - Disallow writes to immutable feature MSRs (notably
     PERF_CAPABILITIES) after KVM_RUN, similar to CPUID features

   - Overhaul the vmx_pmu_caps selftest to better validate
     PERF_CAPABILITIES

   - Apply PMU filters to emulated events and add test coverage to the
     pmu_event_filter selftest

   - AMD SVM:
       - Add support for virtual NMIs
       - Fixes for edge cases related to virtual interrupts

   - Intel AMX:
       - Don't advertise XTILE_CFG in KVM_GET_SUPPORTED_CPUID if
         XTILE_DATA is not being reported due to userspace not opting in
         via prctl()
       - Fix a bug in emulation of ENCLS in compatibility mode
       - Allow emulation of NOP and PAUSE for L2
       - AMX selftests improvements
       - Misc cleanups

  MIPS:

   - Constify MIPS's internal callbacks (a leftover from the hardware
     enabling rework that landed in 6.3)

  Generic:

   - Drop unnecessary casts from "void *" throughout kvm_main.c

   - Tweak the layout of "struct kvm_mmu_memory_cache" to shrink the
     struct size by 8 bytes on 64-bit kernels by utilizing a padding
     hole

  Documentation:

   - Fix goof introduced by the conversion to rST"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (211 commits)
  KVM: s390: pci: fix virtual-physical confusion on module unload/load
  KVM: s390: vsie: clarifications on setting the APCB
  KVM: s390: interrupt: fix virtual-physical confusion for next alert GISA
  KVM: arm64: Have kvm_psci_vcpu_on() use WRITE_ONCE() to update mp_state
  KVM: arm64: Acquire mp_state_lock in kvm_arch_vcpu_ioctl_vcpu_init()
  KVM: selftests: Test the PMU event "Instructions retired"
  KVM: selftests: Copy full counter values from guest in PMU event filter test
  KVM: selftests: Use error codes to signal errors in PMU event filter test
  KVM: selftests: Print detailed info in PMU event filter asserts
  KVM: selftests: Add helpers for PMC asserts in PMU event filter test
  KVM: selftests: Add a common helper for the PMU event filter guest code
  KVM: selftests: Fix spelling mistake "perrmited" -> "permitted"
  KVM: arm64: vhe: Drop extra isb() on guest exit
  KVM: arm64: vhe: Synchronise with page table walker on MMU update
  KVM: arm64: pkvm: Document the side effects of kvm_flush_dcache_to_poc()
  KVM: arm64: nvhe: Synchronise with page table walker on TLBI
  KVM: arm64: Handle 32bit CNTPCTSS traps
  KVM: arm64: nvhe: Synchronise with page table walker on vcpu run
  KVM: arm64: vgic: Don't acquire its_lock before config_lock
  KVM: selftests: Add test to verify KVM's supported XCR0
  ...

1 files changed, 28 insertions, 57 deletions

diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c
index edeac2380591..35cfa268fd5d 100644
--- a/arch/arm64/kvm/vgic/vgic-kvm-device.c
+++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c
@@ -46,7 +46,7 @@ int kvm_set_legacy_vgic_v2_addr(struct kvm *kvm, struct kvm_arm_device_addr *dev
 	struct vgic_dist *vgic = &kvm->arch.vgic;
 	int r;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.config_lock);
 	switch (FIELD_GET(KVM_ARM_DEVICE_TYPE_MASK, dev_addr->id)) {
 	case KVM_VGIC_V2_ADDR_TYPE_DIST:
 		r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
@@ -68,7 +68,7 @@ int kvm_set_legacy_vgic_v2_addr(struct kvm *kvm, struct kvm_arm_device_addr *dev
 		r = -ENODEV;
 	}
 
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.config_lock);
 
 	return r;
 }
@@ -102,7 +102,7 @@ static int kvm_vgic_addr(struct kvm *kvm, struct kvm_device_attr *attr, bool wri
 		if (get_user(addr, uaddr))
 			return -EFAULT;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.config_lock);
 	switch (attr->attr) {
 	case KVM_VGIC_V2_ADDR_TYPE_DIST:
 		r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
@@ -191,7 +191,7 @@ static int kvm_vgic_addr(struct kvm *kvm, struct kvm_device_attr *attr, bool wri
 	}
 
 out:
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.config_lock);
 
 	if (!r && !write)
 		r =  put_user(addr, uaddr);
@@ -227,7 +227,7 @@ static int vgic_set_common_attr(struct kvm_device *dev,
 		    (val & 31))
 			return -EINVAL;
 
-		mutex_lock(&dev->kvm->lock);
+		mutex_lock(&dev->kvm->arch.config_lock);
 
 		if (vgic_ready(dev->kvm) || dev->kvm->arch.vgic.nr_spis)
 			ret = -EBUSY;
@@ -235,16 +235,16 @@ static int vgic_set_common_attr(struct kvm_device *dev,
 			dev->kvm->arch.vgic.nr_spis =
 				val - VGIC_NR_PRIVATE_IRQS;
 
-		mutex_unlock(&dev->kvm->lock);
+		mutex_unlock(&dev->kvm->arch.config_lock);
 
 		return ret;
 	}
 	case KVM_DEV_ARM_VGIC_GRP_CTRL: {
 		switch (attr->attr) {
 		case KVM_DEV_ARM_VGIC_CTRL_INIT:
-			mutex_lock(&dev->kvm->lock);
+			mutex_lock(&dev->kvm->arch.config_lock);
 			r = vgic_init(dev->kvm);
-			mutex_unlock(&dev->kvm->lock);
+			mutex_unlock(&dev->kvm->arch.config_lock);
 			return r;
 		case KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES:
 			/*
@@ -260,7 +260,10 @@ static int vgic_set_common_attr(struct kvm_device *dev,
 				mutex_unlock(&dev->kvm->lock);
 				return -EBUSY;
 			}
+
+			mutex_lock(&dev->kvm->arch.config_lock);
 			r = vgic_v3_save_pending_tables(dev->kvm);
+			mutex_unlock(&dev->kvm->arch.config_lock);
 			unlock_all_vcpus(dev->kvm);
 			mutex_unlock(&dev->kvm->lock);
 			return r;
@@ -342,44 +345,6 @@ int vgic_v2_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr,
 	return 0;
 }
 
-/* unlocks vcpus from @vcpu_lock_idx and smaller */
-static void unlock_vcpus(struct kvm *kvm, int vcpu_lock_idx)
-{
-	struct kvm_vcpu *tmp_vcpu;
-
-	for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) {
-		tmp_vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx);
-		mutex_unlock(&tmp_vcpu->mutex);
-	}
-}
-
-void unlock_all_vcpus(struct kvm *kvm)
-{
-	unlock_vcpus(kvm, atomic_read(&kvm->online_vcpus) - 1);
-}
-
-/* Returns true if all vcpus were locked, false otherwise */
-bool lock_all_vcpus(struct kvm *kvm)
-{
-	struct kvm_vcpu *tmp_vcpu;
-	unsigned long c;
-
-	/*
-	 * Any time a vcpu is run, vcpu_load is called which tries to grab the
-	 * vcpu->mutex.  By grabbing the vcpu->mutex of all VCPUs we ensure
-	 * that no other VCPUs are run and fiddle with the vgic state while we
-	 * access it.
-	 */
-	kvm_for_each_vcpu(c, tmp_vcpu, kvm) {
-		if (!mutex_trylock(&tmp_vcpu->mutex)) {
-			unlock_vcpus(kvm, c - 1);
-			return false;
-		}
-	}
-
-	return true;
-}
-
 /**
  * vgic_v2_attr_regs_access - allows user space to access VGIC v2 state
  *
@@ -411,15 +376,17 @@ static int vgic_v2_attr_regs_access(struct kvm_device *dev,
 
 	mutex_lock(&dev->kvm->lock);
 
+	if (!lock_all_vcpus(dev->kvm)) {
+		mutex_unlock(&dev->kvm->lock);
+		return -EBUSY;
+	}
+
+	mutex_lock(&dev->kvm->arch.config_lock);
+
 	ret = vgic_init(dev->kvm);
 	if (ret)
 		goto out;
 
-	if (!lock_all_vcpus(dev->kvm)) {
-		ret = -EBUSY;
-		goto out;
-	}
-
 	switch (attr->group) {
 	case KVM_DEV_ARM_VGIC_GRP_CPU_REGS:
 		ret = vgic_v2_cpuif_uaccess(vcpu, is_write, addr, &val);
@@ -432,8 +399,9 @@ static int vgic_v2_attr_regs_access(struct kvm_device *dev,
 		break;
 	}
 
-	unlock_all_vcpus(dev->kvm);
 out:
+	mutex_unlock(&dev->kvm->arch.config_lock);
+	unlock_all_vcpus(dev->kvm);
 	mutex_unlock(&dev->kvm->lock);
 
 	if (!ret && !is_write)
@@ -569,12 +537,14 @@ static int vgic_v3_attr_regs_access(struct kvm_device *dev,
 
 	mutex_lock(&dev->kvm->lock);
 
-	if (unlikely(!vgic_initialized(dev->kvm))) {
-		ret = -EBUSY;
-		goto out;
+	if (!lock_all_vcpus(dev->kvm)) {
+		mutex_unlock(&dev->kvm->lock);
+		return -EBUSY;
 	}
 
-	if (!lock_all_vcpus(dev->kvm)) {
+	mutex_lock(&dev->kvm->arch.config_lock);
+
+	if (unlikely(!vgic_initialized(dev->kvm))) {
 		ret = -EBUSY;
 		goto out;
 	}
@@ -609,8 +579,9 @@ static int vgic_v3_attr_regs_access(struct kvm_device *dev,
 		break;
 	}
 
-	unlock_all_vcpus(dev->kvm);
 out:
+	mutex_unlock(&dev->kvm->arch.config_lock);
+	unlock_all_vcpus(dev->kvm);
 	mutex_unlock(&dev->kvm->lock);
 
 	if (!ret && uaccess && !is_write) {