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

Pull KVM updates from Paolo Bonzini:
 "ARM:
   - support for SVE and Pointer Authentication in guests
   - PMU improvements

  POWER:
   - support for direct access to the POWER9 XIVE interrupt controller
   - memory and performance optimizations

  x86:
   - support for accessing memory not backed by struct page
   - fixes and refactoring

  Generic:
   - dirty page tracking improvements"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (155 commits)
  kvm: fix compilation on aarch64
  Revert "KVM: nVMX: Expose RDPMC-exiting only when guest supports PMU"
  kvm: x86: Fix L1TF mitigation for shadow MMU
  KVM: nVMX: Disable intercept for FS/GS base MSRs in vmcs02 when possible
  KVM: PPC: Book3S: Remove useless checks in 'release' method of KVM device
  KVM: PPC: Book3S HV: XIVE: Fix spelling mistake "acessing" -> "accessing"
  KVM: PPC: Book3S HV: Make sure to load LPID for radix VCPUs
  kvm: nVMX: Set nested_run_pending in vmx_set_nested_state after checks complete
  tests: kvm: Add tests for KVM_SET_NESTED_STATE
  KVM: nVMX: KVM_SET_NESTED_STATE - Tear down old EVMCS state before setting new state
  tests: kvm: Add tests for KVM_CAP_MAX_VCPUS and KVM_CAP_MAX_CPU_ID
  tests: kvm: Add tests to .gitignore
  KVM: Introduce KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2
  KVM: Fix kvm_clear_dirty_log_protect off-by-(minus-)one
  KVM: Fix the bitmap range to copy during clear dirty
  KVM: arm64: Fix ptrauth ID register masking logic
  KVM: x86: use direct accessors for RIP and RSP
  KVM: VMX: Use accessors for GPRs outside of dedicated caching logic
  KVM: x86: Omit caching logic for always-available GPRs
  kvm, x86: Properly check whether a pfn is an MMIO or not
  ...

4 files changed, 135 insertions, 10 deletions

diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index 1816ee48eadd..d3db3d7ed077 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -30,6 +30,7 @@ config KVM
 	select HAVE_KVM_IRQFD
 	select HAVE_KVM_IRQ_ROUTING
 	select HAVE_KVM_INVALID_WAKEUPS
+	select HAVE_KVM_NO_POLL
 	select SRCU
 	select KVM_VFIO
 	---help---
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 1fd706f6206c..9dde4d7d8704 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -14,6 +14,7 @@
 #include <linux/kvm_host.h>
 #include <linux/hrtimer.h>
 #include <linux/mmu_context.h>
+#include <linux/nospec.h>
 #include <linux/signal.h>
 #include <linux/slab.h>
 #include <linux/bitmap.h>
@@ -2307,6 +2308,7 @@ static struct s390_io_adapter *get_io_adapter(struct kvm *kvm, unsigned int id)
 {
 	if (id >= MAX_S390_IO_ADAPTERS)
 		return NULL;
+	id = array_index_nospec(id, MAX_S390_IO_ADAPTERS);
 	return kvm->arch.adapters[id];
 }
 
@@ -2320,8 +2322,13 @@ static int register_io_adapter(struct kvm_device *dev,
 			   (void __user *)attr->addr, sizeof(adapter_info)))
 		return -EFAULT;
 
-	if ((adapter_info.id >= MAX_S390_IO_ADAPTERS) ||
-	    (dev->kvm->arch.adapters[adapter_info.id] != NULL))
+	if (adapter_info.id >= MAX_S390_IO_ADAPTERS)
+		return -EINVAL;
+
+	adapter_info.id = array_index_nospec(adapter_info.id,
+					     MAX_S390_IO_ADAPTERS);
+
+	if (dev->kvm->arch.adapters[adapter_info.id] != NULL)
 		return -EINVAL;
 
 	adapter = kzalloc(sizeof(*adapter), GFP_KERNEL);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 4638303ba6a8..8d6d75db8de6 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -75,6 +75,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "halt_successful_poll", VCPU_STAT(halt_successful_poll) },
 	{ "halt_attempted_poll", VCPU_STAT(halt_attempted_poll) },
 	{ "halt_poll_invalid", VCPU_STAT(halt_poll_invalid) },
+	{ "halt_no_poll_steal", VCPU_STAT(halt_no_poll_steal) },
 	{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
 	{ "instruction_lctlg", VCPU_STAT(instruction_lctlg) },
 	{ "instruction_lctl", VCPU_STAT(instruction_lctl) },
@@ -177,6 +178,11 @@ static int hpage;
 module_param(hpage, int, 0444);
 MODULE_PARM_DESC(hpage, "1m huge page backing support");
 
+/* maximum percentage of steal time for polling.  >100 is treated like 100 */
+static u8 halt_poll_max_steal = 10;
+module_param(halt_poll_max_steal, byte, 0644);
+MODULE_PARM_DESC(hpage, "Maximum percentage of steal time to allow polling");
+
 /*
  * For now we handle at most 16 double words as this is what the s390 base
  * kernel handles and stores in the prefix page. If we ever need to go beyond
@@ -321,6 +327,22 @@ static inline int plo_test_bit(unsigned char nr)
 	return cc == 0;
 }
 
+static inline void __insn32_query(unsigned int opcode, u8 query[32])
+{
+	register unsigned long r0 asm("0") = 0;	/* query function */
+	register unsigned long r1 asm("1") = (unsigned long) query;
+
+	asm volatile(
+		/* Parameter regs are ignored */
+		"	.insn	rrf,%[opc] << 16,2,4,6,0\n"
+		: "=m" (*query)
+		: "d" (r0), "a" (r1), [opc] "i" (opcode)
+		: "cc");
+}
+
+#define INSN_SORTL 0xb938
+#define INSN_DFLTCC 0xb939
+
 static void kvm_s390_cpu_feat_init(void)
 {
 	int i;
@@ -368,6 +390,16 @@ static void kvm_s390_cpu_feat_init(void)
 		__cpacf_query(CPACF_KMA, (cpacf_mask_t *)
 			      kvm_s390_available_subfunc.kma);
 
+	if (test_facility(155)) /* MSA9 */
+		__cpacf_query(CPACF_KDSA, (cpacf_mask_t *)
+			      kvm_s390_available_subfunc.kdsa);
+
+	if (test_facility(150)) /* SORTL */
+		__insn32_query(INSN_SORTL, kvm_s390_available_subfunc.sortl);
+
+	if (test_facility(151)) /* DFLTCC */
+		__insn32_query(INSN_DFLTCC, kvm_s390_available_subfunc.dfltcc);
+
 	if (MACHINE_HAS_ESOP)
 		allow_cpu_feat(KVM_S390_VM_CPU_FEAT_ESOP);
 	/*
@@ -513,9 +545,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		else if (sclp.has_esca && sclp.has_64bscao)
 			r = KVM_S390_ESCA_CPU_SLOTS;
 		break;
-	case KVM_CAP_NR_MEMSLOTS:
-		r = KVM_USER_MEM_SLOTS;
-		break;
 	case KVM_CAP_S390_COW:
 		r = MACHINE_HAS_ESOP;
 		break;
@@ -657,6 +686,14 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 				set_kvm_facility(kvm->arch.model.fac_mask, 135);
 				set_kvm_facility(kvm->arch.model.fac_list, 135);
 			}
+			if (test_facility(148)) {
+				set_kvm_facility(kvm->arch.model.fac_mask, 148);
+				set_kvm_facility(kvm->arch.model.fac_list, 148);
+			}
+			if (test_facility(152)) {
+				set_kvm_facility(kvm->arch.model.fac_mask, 152);
+				set_kvm_facility(kvm->arch.model.fac_list, 152);
+			}
 			r = 0;
 		} else
 			r = -EINVAL;
@@ -1323,6 +1360,19 @@ static int kvm_s390_set_processor_subfunc(struct kvm *kvm,
 	VM_EVENT(kvm, 3, "SET: guest KMA    subfunc 0x%16.16lx.%16.16lx",
 		 ((unsigned long *) &kvm->arch.model.subfuncs.kma)[0],
 		 ((unsigned long *) &kvm->arch.model.subfuncs.kma)[1]);
+	VM_EVENT(kvm, 3, "SET: guest KDSA   subfunc 0x%16.16lx.%16.16lx",
+		 ((unsigned long *) &kvm->arch.model.subfuncs.kdsa)[0],
+		 ((unsigned long *) &kvm->arch.model.subfuncs.kdsa)[1]);
+	VM_EVENT(kvm, 3, "SET: guest SORTL  subfunc 0x%16.16lx.%16.16lx.%16.16lx.%16.16lx",
+		 ((unsigned long *) &kvm->arch.model.subfuncs.sortl)[0],
+		 ((unsigned long *) &kvm->arch.model.subfuncs.sortl)[1],
+		 ((unsigned long *) &kvm->arch.model.subfuncs.sortl)[2],
+		 ((unsigned long *) &kvm->arch.model.subfuncs.sortl)[3]);
+	VM_EVENT(kvm, 3, "SET: guest DFLTCC subfunc 0x%16.16lx.%16.16lx.%16.16lx.%16.16lx",
+		 ((unsigned long *) &kvm->arch.model.subfuncs.dfltcc)[0],
+		 ((unsigned long *) &kvm->arch.model.subfuncs.dfltcc)[1],
+		 ((unsigned long *) &kvm->arch.model.subfuncs.dfltcc)[2],
+		 ((unsigned long *) &kvm->arch.model.subfuncs.dfltcc)[3]);
 
 	return 0;
 }
@@ -1491,6 +1541,19 @@ static int kvm_s390_get_processor_subfunc(struct kvm *kvm,
 	VM_EVENT(kvm, 3, "GET: guest KMA    subfunc 0x%16.16lx.%16.16lx",
 		 ((unsigned long *) &kvm->arch.model.subfuncs.kma)[0],
 		 ((unsigned long *) &kvm->arch.model.subfuncs.kma)[1]);
+	VM_EVENT(kvm, 3, "GET: guest KDSA   subfunc 0x%16.16lx.%16.16lx",
+		 ((unsigned long *) &kvm->arch.model.subfuncs.kdsa)[0],
+		 ((unsigned long *) &kvm->arch.model.subfuncs.kdsa)[1]);
+	VM_EVENT(kvm, 3, "GET: guest SORTL  subfunc 0x%16.16lx.%16.16lx.%16.16lx.%16.16lx",
+		 ((unsigned long *) &kvm->arch.model.subfuncs.sortl)[0],
+		 ((unsigned long *) &kvm->arch.model.subfuncs.sortl)[1],
+		 ((unsigned long *) &kvm->arch.model.subfuncs.sortl)[2],
+		 ((unsigned long *) &kvm->arch.model.subfuncs.sortl)[3]);
+	VM_EVENT(kvm, 3, "GET: guest DFLTCC subfunc 0x%16.16lx.%16.16lx.%16.16lx.%16.16lx",
+		 ((unsigned long *) &kvm->arch.model.subfuncs.dfltcc)[0],
+		 ((unsigned long *) &kvm->arch.model.subfuncs.dfltcc)[1],
+		 ((unsigned long *) &kvm->arch.model.subfuncs.dfltcc)[2],
+		 ((unsigned long *) &kvm->arch.model.subfuncs.dfltcc)[3]);
 
 	return 0;
 }
@@ -1546,6 +1609,19 @@ static int kvm_s390_get_machine_subfunc(struct kvm *kvm,
 	VM_EVENT(kvm, 3, "GET: host  KMA    subfunc 0x%16.16lx.%16.16lx",
 		 ((unsigned long *) &kvm_s390_available_subfunc.kma)[0],
 		 ((unsigned long *) &kvm_s390_available_subfunc.kma)[1]);
+	VM_EVENT(kvm, 3, "GET: host  KDSA   subfunc 0x%16.16lx.%16.16lx",
+		 ((unsigned long *) &kvm_s390_available_subfunc.kdsa)[0],
+		 ((unsigned long *) &kvm_s390_available_subfunc.kdsa)[1]);
+	VM_EVENT(kvm, 3, "GET: host  SORTL  subfunc 0x%16.16lx.%16.16lx.%16.16lx.%16.16lx",
+		 ((unsigned long *) &kvm_s390_available_subfunc.sortl)[0],
+		 ((unsigned long *) &kvm_s390_available_subfunc.sortl)[1],
+		 ((unsigned long *) &kvm_s390_available_subfunc.sortl)[2],
+		 ((unsigned long *) &kvm_s390_available_subfunc.sortl)[3]);
+	VM_EVENT(kvm, 3, "GET: host  DFLTCC subfunc 0x%16.16lx.%16.16lx.%16.16lx.%16.16lx",
+		 ((unsigned long *) &kvm_s390_available_subfunc.dfltcc)[0],
+		 ((unsigned long *) &kvm_s390_available_subfunc.dfltcc)[1],
+		 ((unsigned long *) &kvm_s390_available_subfunc.dfltcc)[2],
+		 ((unsigned long *) &kvm_s390_available_subfunc.dfltcc)[3]);
 
 	return 0;
 }
@@ -2817,6 +2893,25 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 	vcpu->arch.enabled_gmap = vcpu->arch.gmap;
 }
 
+static bool kvm_has_pckmo_subfunc(struct kvm *kvm, unsigned long nr)
+{
+	if (test_bit_inv(nr, (unsigned long *)&kvm->arch.model.subfuncs.pckmo) &&
+	    test_bit_inv(nr, (unsigned long *)&kvm_s390_available_subfunc.pckmo))
+		return true;
+	return false;
+}
+
+static bool kvm_has_pckmo_ecc(struct kvm *kvm)
+{
+	/* At least one ECC subfunction must be present */
+	return kvm_has_pckmo_subfunc(kvm, 32) ||
+	       kvm_has_pckmo_subfunc(kvm, 33) ||
+	       kvm_has_pckmo_subfunc(kvm, 34) ||
+	       kvm_has_pckmo_subfunc(kvm, 40) ||
+	       kvm_has_pckmo_subfunc(kvm, 41);
+
+}
+
 static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu)
 {
 	/*
@@ -2829,13 +2924,19 @@ static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu)
 	vcpu->arch.sie_block->crycbd = vcpu->kvm->arch.crypto.crycbd;
 	vcpu->arch.sie_block->ecb3 &= ~(ECB3_AES | ECB3_DEA);
 	vcpu->arch.sie_block->eca &= ~ECA_APIE;
+	vcpu->arch.sie_block->ecd &= ~ECD_ECC;
 
 	if (vcpu->kvm->arch.crypto.apie)
 		vcpu->arch.sie_block->eca |= ECA_APIE;
 
 	/* Set up protected key support */
-	if (vcpu->kvm->arch.crypto.aes_kw)
+	if (vcpu->kvm->arch.crypto.aes_kw) {
 		vcpu->arch.sie_block->ecb3 |= ECB3_AES;
+		/* ecc is also wrapped with AES key */
+		if (kvm_has_pckmo_ecc(vcpu->kvm))
+			vcpu->arch.sie_block->ecd |= ECD_ECC;
+	}
+
 	if (vcpu->kvm->arch.crypto.dea_kw)
 		vcpu->arch.sie_block->ecb3 |= ECB3_DEA;
 }
@@ -3068,6 +3169,17 @@ static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start,
 	}
 }
 
+bool kvm_arch_no_poll(struct kvm_vcpu *vcpu)
+{
+	/* do not poll with more than halt_poll_max_steal percent of steal time */
+	if (S390_lowcore.avg_steal_timer * 100 / (TICK_USEC << 12) >=
+	    halt_poll_max_steal) {
+		vcpu->stat.halt_no_poll_steal++;
+		return true;
+	}
+	return false;
+}
+
 int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
 {
 	/* kvm common code refers to this, but never calls it */
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index d62fa148558b..076090f9e666 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -288,7 +288,9 @@ static int shadow_crycb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	const u32 crycb_addr = crycbd_o & 0x7ffffff8U;
 	unsigned long *b1, *b2;
 	u8 ecb3_flags;
+	u32 ecd_flags;
 	int apie_h;
+	int apie_s;
 	int key_msk = test_kvm_facility(vcpu->kvm, 76);
 	int fmt_o = crycbd_o & CRYCB_FORMAT_MASK;
 	int fmt_h = vcpu->arch.sie_block->crycbd & CRYCB_FORMAT_MASK;
@@ -297,7 +299,8 @@ static int shadow_crycb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	scb_s->crycbd = 0;
 
 	apie_h = vcpu->arch.sie_block->eca & ECA_APIE;
-	if (!apie_h && (!key_msk || fmt_o == CRYCB_FORMAT0))
+	apie_s = apie_h & scb_o->eca;
+	if (!apie_s && (!key_msk || (fmt_o == CRYCB_FORMAT0)))
 		return 0;
 
 	if (!crycb_addr)
@@ -308,7 +311,7 @@ static int shadow_crycb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 		    ((crycb_addr + 128) & PAGE_MASK))
 			return set_validity_icpt(scb_s, 0x003CU);
 
-	if (apie_h && (scb_o->eca & ECA_APIE)) {
+	if (apie_s) {
 		ret = setup_apcb(vcpu, &vsie_page->crycb, crycb_addr,
 				 vcpu->kvm->arch.crypto.crycb,
 				 fmt_o, fmt_h);
@@ -320,7 +323,8 @@ static int shadow_crycb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	/* we may only allow it if enabled for guest 2 */
 	ecb3_flags = scb_o->ecb3 & vcpu->arch.sie_block->ecb3 &
 		     (ECB3_AES | ECB3_DEA);
-	if (!ecb3_flags)
+	ecd_flags = scb_o->ecd & vcpu->arch.sie_block->ecd & ECD_ECC;
+	if (!ecb3_flags && !ecd_flags)
 		goto end;
 
 	/* copy only the wrapping keys */
@@ -329,6 +333,7 @@ static int shadow_crycb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 		return set_validity_icpt(scb_s, 0x0035U);
 
 	scb_s->ecb3 |= ecb3_flags;
+	scb_s->ecd |= ecd_flags;
 
 	/* xor both blocks in one run */
 	b1 = (unsigned long *) vsie_page->crycb.dea_wrapping_key_mask;
@@ -339,7 +344,7 @@ static int shadow_crycb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 end:
 	switch (ret) {
 	case -EINVAL:
-		return set_validity_icpt(scb_s, 0x0020U);
+		return set_validity_icpt(scb_s, 0x0022U);
 	case -EFAULT:
 		return set_validity_icpt(scb_s, 0x0035U);
 	case -EACCES: