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
  ...

4 files changed, 35 insertions, 28 deletions

diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 9250fde1f97d..da6dac36e959 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -305,7 +305,7 @@ static inline u8 gisa_get_ipm_or_restore_iam(struct kvm_s390_gisa_interrupt *gi)
 
 static inline int gisa_in_alert_list(struct kvm_s390_gisa *gisa)
 {
-	return READ_ONCE(gisa->next_alert) != (u32)(u64)gisa;
+	return READ_ONCE(gisa->next_alert) != (u32)virt_to_phys(gisa);
 }
 
 static inline void gisa_set_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc)
@@ -3168,7 +3168,7 @@ void kvm_s390_gisa_init(struct kvm *kvm)
 	hrtimer_init(&gi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	gi->timer.function = gisa_vcpu_kicker;
 	memset(gi->origin, 0, sizeof(struct kvm_s390_gisa));
-	gi->origin->next_alert = (u32)(u64)gi->origin;
+	gi->origin->next_alert = (u32)virt_to_phys(gi->origin);
 	VM_EVENT(kvm, 3, "gisa 0x%pK initialized", gi->origin);
 }
 
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 1eeb9ae57879..17b81659cdb2 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1990,7 +1990,7 @@ static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr)
 	return ret;
 }
 
-static long kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
+static int kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 {
 	uint8_t *keys;
 	uint64_t hva;
@@ -2038,7 +2038,7 @@ static long kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 	return r;
 }
 
-static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
+static int kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 {
 	uint8_t *keys;
 	uint64_t hva;
@@ -2899,8 +2899,7 @@ static int kvm_s390_vm_mem_op(struct kvm *kvm, struct kvm_s390_mem_op *mop)
 	}
 }
 
-long kvm_arch_vm_ioctl(struct file *filp,
-		       unsigned int ioctl, unsigned long arg)
+int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 {
 	struct kvm *kvm = filp->private_data;
 	void __user *argp = (void __user *)arg;
diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c
index b124d586db55..7dab00f1e833 100644
--- a/arch/s390/kvm/pci.c
+++ b/arch/s390/kvm/pci.c
@@ -112,7 +112,7 @@ static int zpci_reset_aipb(u8 nisc)
 		return -EINVAL;
 
 	aift->sbv = zpci_aif_sbv;
-	aift->gait = (struct zpci_gaite *)zpci_aipb->aipb.gait;
+	aift->gait = phys_to_virt(zpci_aipb->aipb.gait);
 
 	return 0;
 }
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index b6a0219e470a..8d6b765abf29 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -138,11 +138,15 @@ static int prepare_cpuflags(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 }
 /* Copy to APCB FORMAT1 from APCB FORMAT0 */
 static int setup_apcb10(struct kvm_vcpu *vcpu, struct kvm_s390_apcb1 *apcb_s,
-			unsigned long apcb_o, struct kvm_s390_apcb1 *apcb_h)
+			unsigned long crycb_gpa, struct kvm_s390_apcb1 *apcb_h)
 {
 	struct kvm_s390_apcb0 tmp;
+	unsigned long apcb_gpa;
 
-	if (read_guest_real(vcpu, apcb_o, &tmp, sizeof(struct kvm_s390_apcb0)))
+	apcb_gpa = crycb_gpa + offsetof(struct kvm_s390_crypto_cb, apcb0);
+
+	if (read_guest_real(vcpu, apcb_gpa, &tmp,
+			    sizeof(struct kvm_s390_apcb0)))
 		return -EFAULT;
 
 	apcb_s->apm[0] = apcb_h->apm[0] & tmp.apm[0];
@@ -157,15 +161,19 @@ static int setup_apcb10(struct kvm_vcpu *vcpu, struct kvm_s390_apcb1 *apcb_s,
  * setup_apcb00 - Copy to APCB FORMAT0 from APCB FORMAT0
  * @vcpu: pointer to the virtual CPU
  * @apcb_s: pointer to start of apcb in the shadow crycb
- * @apcb_o: pointer to start of original apcb in the guest2
+ * @crycb_gpa: guest physical address to start of original guest crycb
  * @apcb_h: pointer to start of apcb in the guest1
  *
  * Returns 0 and -EFAULT on error reading guest apcb
  */
 static int setup_apcb00(struct kvm_vcpu *vcpu, unsigned long *apcb_s,
-			unsigned long apcb_o, unsigned long *apcb_h)
+			unsigned long crycb_gpa, unsigned long *apcb_h)
 {
-	if (read_guest_real(vcpu, apcb_o, apcb_s,
+	unsigned long apcb_gpa;
+
+	apcb_gpa = crycb_gpa + offsetof(struct kvm_s390_crypto_cb, apcb0);
+
+	if (read_guest_real(vcpu, apcb_gpa, apcb_s,
 			    sizeof(struct kvm_s390_apcb0)))
 		return -EFAULT;
 
@@ -178,16 +186,20 @@ static int setup_apcb00(struct kvm_vcpu *vcpu, unsigned long *apcb_s,
  * setup_apcb11 - Copy the FORMAT1 APCB from the guest to the shadow CRYCB
  * @vcpu: pointer to the virtual CPU
  * @apcb_s: pointer to start of apcb in the shadow crycb
- * @apcb_o: pointer to start of original guest apcb
+ * @crycb_gpa: guest physical address to start of original guest crycb
  * @apcb_h: pointer to start of apcb in the host
  *
  * Returns 0 and -EFAULT on error reading guest apcb
  */
 static int setup_apcb11(struct kvm_vcpu *vcpu, unsigned long *apcb_s,
-			unsigned long apcb_o,
+			unsigned long crycb_gpa,
 			unsigned long *apcb_h)
 {
-	if (read_guest_real(vcpu, apcb_o, apcb_s,
+	unsigned long apcb_gpa;
+
+	apcb_gpa = crycb_gpa + offsetof(struct kvm_s390_crypto_cb, apcb1);
+
+	if (read_guest_real(vcpu, apcb_gpa, apcb_s,
 			    sizeof(struct kvm_s390_apcb1)))
 		return -EFAULT;
 
@@ -200,7 +212,7 @@ static int setup_apcb11(struct kvm_vcpu *vcpu, unsigned long *apcb_s,
  * setup_apcb - Create a shadow copy of the apcb.
  * @vcpu: pointer to the virtual CPU
  * @crycb_s: pointer to shadow crycb
- * @crycb_o: pointer to original guest crycb
+ * @crycb_gpa: guest physical address of original guest crycb
  * @crycb_h: pointer to the host crycb
  * @fmt_o: format of the original guest crycb.
  * @fmt_h: format of the host crycb.
@@ -211,50 +223,46 @@ static int setup_apcb11(struct kvm_vcpu *vcpu, unsigned long *apcb_s,
  * Return 0 or an error number if the guest and host crycb are incompatible.
  */
 static int setup_apcb(struct kvm_vcpu *vcpu, struct kvm_s390_crypto_cb *crycb_s,
-	       const u32 crycb_o,
+	       const u32 crycb_gpa,
 	       struct kvm_s390_crypto_cb *crycb_h,
 	       int fmt_o, int fmt_h)
 {
-	struct kvm_s390_crypto_cb *crycb;
-
-	crycb = (struct kvm_s390_crypto_cb *) (unsigned long)crycb_o;
-
 	switch (fmt_o) {
 	case CRYCB_FORMAT2:
-		if ((crycb_o & PAGE_MASK) != ((crycb_o + 256) & PAGE_MASK))
+		if ((crycb_gpa & PAGE_MASK) != ((crycb_gpa + 256) & PAGE_MASK))
 			return -EACCES;
 		if (fmt_h != CRYCB_FORMAT2)
 			return -EINVAL;
 		return setup_apcb11(vcpu, (unsigned long *)&crycb_s->apcb1,
-				    (unsigned long) &crycb->apcb1,
+				    crycb_gpa,
 				    (unsigned long *)&crycb_h->apcb1);
 	case CRYCB_FORMAT1:
 		switch (fmt_h) {
 		case CRYCB_FORMAT2:
 			return setup_apcb10(vcpu, &crycb_s->apcb1,
-					    (unsigned long) &crycb->apcb0,
+					    crycb_gpa,
 					    &crycb_h->apcb1);
 		case CRYCB_FORMAT1:
 			return setup_apcb00(vcpu,
 					    (unsigned long *) &crycb_s->apcb0,
-					    (unsigned long) &crycb->apcb0,
+					    crycb_gpa,
 					    (unsigned long *) &crycb_h->apcb0);
 		}
 		break;
 	case CRYCB_FORMAT0:
-		if ((crycb_o & PAGE_MASK) != ((crycb_o + 32) & PAGE_MASK))
+		if ((crycb_gpa & PAGE_MASK) != ((crycb_gpa + 32) & PAGE_MASK))
 			return -EACCES;
 
 		switch (fmt_h) {
 		case CRYCB_FORMAT2:
 			return setup_apcb10(vcpu, &crycb_s->apcb1,
-					    (unsigned long) &crycb->apcb0,
+					    crycb_gpa,
 					    &crycb_h->apcb1);
 		case CRYCB_FORMAT1:
 		case CRYCB_FORMAT0:
 			return setup_apcb00(vcpu,
 					    (unsigned long *) &crycb_s->apcb0,
-					    (unsigned long) &crycb->apcb0,
+					    crycb_gpa,
 					    (unsigned long *) &crycb_h->apcb0);
 		}
 	}