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

Pull KVM fixes from Paolo Bonzini:

 - miscellaneous fixes for MIPS and s390

 - one new kvm_stat for s390

 - correctly disable VT-d posted interrupts with the rest of posted
   interrupts

 - "make randconfig" fix for x86 AMD

 - off-by-one in irq route check (the "good" kind that errors out a bit
   too early!)

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  kvm: vmx: check apicv is active before using VT-d posted interrupt
  kvm: Fix irq route entries exceeding KVM_MAX_IRQ_ROUTES
  kvm: svm: Do not support AVIC if not CONFIG_X86_LOCAL_APIC
  kvm: svm: Fix implicit declaration for __default_cpu_present_to_apicid()
  MIPS: KVM: Fix CACHE triggered exception emulation
  MIPS: KVM: Don't unwind PC when emulating CACHE
  MIPS: KVM: Include bit 31 in segment matches
  MIPS: KVM: Fix modular KVM under QEMU
  KVM: s390: Add stats for PEI events
  KVM: s390: ignore IBC if zero

12 files changed, 67 insertions, 23 deletions

diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index 6733ac575da4fd..36a391d289aa09 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -74,7 +74,7 @@
 #define KVM_GUEST_KUSEG			0x00000000UL
 #define KVM_GUEST_KSEG0			0x40000000UL
 #define KVM_GUEST_KSEG23		0x60000000UL
-#define KVM_GUEST_KSEGX(a)		((_ACAST32_(a)) & 0x60000000)
+#define KVM_GUEST_KSEGX(a)		((_ACAST32_(a)) & 0xe0000000)
 #define KVM_GUEST_CPHYSADDR(a)		((_ACAST32_(a)) & 0x1fffffff)
 
 #define KVM_GUEST_CKSEG0ADDR(a)		(KVM_GUEST_CPHYSADDR(a) | KVM_GUEST_KSEG0)
@@ -338,6 +338,7 @@ struct kvm_mips_tlb {
 #define KVM_MIPS_GUEST_TLB_SIZE	64
 struct kvm_vcpu_arch {
 	void *host_ebase, *guest_ebase;
+	int (*vcpu_run)(struct kvm_run *run, struct kvm_vcpu *vcpu);
 	unsigned long host_stack;
 	unsigned long host_gp;
 
diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c
index 396df6eb0a12d9..645c8a1982a7b2 100644
--- a/arch/mips/kvm/emulate.c
+++ b/arch/mips/kvm/emulate.c
@@ -1636,6 +1636,7 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc,
 		if (index < 0) {
 			vcpu->arch.host_cp0_entryhi = (va & VPN2_MASK);
 			vcpu->arch.host_cp0_badvaddr = va;
+			vcpu->arch.pc = curr_pc;
 			er = kvm_mips_emulate_tlbmiss_ld(cause, NULL, run,
 							 vcpu);
 			preempt_enable();
@@ -1647,6 +1648,8 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc,
 			 * invalid exception to the guest
 			 */
 			if (!TLB_IS_VALID(*tlb, va)) {
+				vcpu->arch.host_cp0_badvaddr = va;
+				vcpu->arch.pc = curr_pc;
 				er = kvm_mips_emulate_tlbinv_ld(cause, NULL,
 								run, vcpu);
 				preempt_enable();
@@ -1666,7 +1669,7 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc,
 			cache, op, base, arch->gprs[base], offset);
 		er = EMULATE_FAIL;
 		preempt_enable();
-		goto dont_update_pc;
+		goto done;
 
 	}
 
@@ -1694,16 +1697,20 @@ skip_fault:
 		kvm_err("NO-OP CACHE (cache: %#x, op: %#x, base[%d]: %#lx, offset: %#x\n",
 			cache, op, base, arch->gprs[base], offset);
 		er = EMULATE_FAIL;
-		preempt_enable();
-		goto dont_update_pc;
 	}
 
 	preempt_enable();
+done:
+	/* Rollback PC only if emulation was unsuccessful */
+	if (er == EMULATE_FAIL)
+		vcpu->arch.pc = curr_pc;
 
 dont_update_pc:
-	/* Rollback PC */
-	vcpu->arch.pc = curr_pc;
-done:
+	/*
+	 * This is for exceptions whose emulation updates the PC, so do not
+	 * overwrite the PC under any circumstances
+	 */
+
 	return er;
 }
 
diff --git a/arch/mips/kvm/interrupt.h b/arch/mips/kvm/interrupt.h
index 4ab4bdfad703e5..2143884709e476 100644
--- a/arch/mips/kvm/interrupt.h
+++ b/arch/mips/kvm/interrupt.h
@@ -28,6 +28,7 @@
 #define MIPS_EXC_MAX                12
 /* XXXSL More to follow */
 
+extern char __kvm_mips_vcpu_run_end[];
 extern char mips32_exception[], mips32_exceptionEnd[];
 extern char mips32_GuestException[], mips32_GuestExceptionEnd[];
 
diff --git a/arch/mips/kvm/locore.S b/arch/mips/kvm/locore.S
index 3ef03009de5f65..828fcfc1cd7fe9 100644
--- a/arch/mips/kvm/locore.S
+++ b/arch/mips/kvm/locore.S
@@ -202,6 +202,7 @@ FEXPORT(__kvm_mips_load_k0k1)
 
 	/* Jump to guest */
 	eret
+EXPORT(__kvm_mips_vcpu_run_end)
 
 VECTOR(MIPSX(exception), unknown)
 /* Find out what mode we came from and jump to the proper handler. */
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index dc052fb5c7a2f8..44da5259f39027 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -315,6 +315,15 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 	memcpy(gebase + offset, mips32_GuestException,
 	       mips32_GuestExceptionEnd - mips32_GuestException);
 
+#ifdef MODULE
+	offset += mips32_GuestExceptionEnd - mips32_GuestException;
+	memcpy(gebase + offset, (char *)__kvm_mips_vcpu_run,
+	       __kvm_mips_vcpu_run_end - (char *)__kvm_mips_vcpu_run);
+	vcpu->arch.vcpu_run = gebase + offset;
+#else
+	vcpu->arch.vcpu_run = __kvm_mips_vcpu_run;
+#endif
+
 	/* Invalidate the icache for these ranges */
 	local_flush_icache_range((unsigned long)gebase,
 				(unsigned long)gebase + ALIGN(size, PAGE_SIZE));
@@ -404,7 +413,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	/* Disable hardware page table walking while in guest */
 	htw_stop();
 
-	r = __kvm_mips_vcpu_run(run, vcpu);
+	r = vcpu->arch.vcpu_run(run, vcpu);
 
 	/* Re-enable HTW before enabling interrupts */
 	htw_start();
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 37b9017c6a96b7..ac82e8eb936dc6 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -245,6 +245,7 @@ struct kvm_vcpu_stat {
 	u32 exit_stop_request;
 	u32 exit_validity;
 	u32 exit_instruction;
+	u32 exit_pei;
 	u32 halt_successful_poll;
 	u32 halt_attempted_poll;
 	u32 halt_poll_invalid;
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 2e6b54e4d3f955..252157181302e4 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -341,6 +341,8 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu)
 
 static int handle_partial_execution(struct kvm_vcpu *vcpu)
 {
+	vcpu->stat.exit_pei++;
+
 	if (vcpu->arch.sie_block->ipa == 0xb254)	/* MVPG */
 		return handle_mvpg_pei(vcpu);
 	if (vcpu->arch.sie_block->ipa >> 8 == 0xae)	/* SIGP */
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 6d8ec3ac9dd8ec..43f2a2b80490ce 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -61,6 +61,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "exit_external_request", VCPU_STAT(exit_external_request) },
 	{ "exit_external_interrupt", VCPU_STAT(exit_external_interrupt) },
 	{ "exit_instruction", VCPU_STAT(exit_instruction) },
+	{ "exit_pei", VCPU_STAT(exit_pei) },
 	{ "exit_program_interruption", VCPU_STAT(exit_program_interruption) },
 	{ "exit_instr_and_program_int", VCPU_STAT(exit_instr_and_program) },
 	{ "halt_successful_poll", VCPU_STAT(halt_successful_poll) },
@@ -657,7 +658,7 @@ static int kvm_s390_set_processor(struct kvm *kvm, struct kvm_device_attr *attr)
 		kvm->arch.model.cpuid = proc->cpuid;
 		lowest_ibc = sclp.ibc >> 16 & 0xfff;
 		unblocked_ibc = sclp.ibc & 0xfff;
-		if (lowest_ibc) {
+		if (lowest_ibc && proc->ibc) {
 			if (proc->ibc > unblocked_ibc)
 				kvm->arch.model.ibc = unblocked_ibc;
 			else if (proc->ibc < lowest_ibc)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index e0fbe7e70dc193..69e62862b6222e 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -27,6 +27,7 @@
 #include <linux/irqbypass.h>
 #include <linux/hyperv.h>
 
+#include <asm/apic.h>
 #include <asm/pvclock-abi.h>
 #include <asm/desc.h>
 #include <asm/mtrr.h>
@@ -1368,4 +1369,14 @@ static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
 
 static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}
 
+static inline int kvm_cpu_get_apicid(int mps_cpu)
+{
+#ifdef CONFIG_X86_LOCAL_APIC
+	return __default_cpu_present_to_apicid(mps_cpu);
+#else
+	WARN_ON_ONCE(1);
+	return BAD_APICID;
+#endif
+}
+
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 1163e8173e5a71..16ef31b8745221 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -238,7 +238,9 @@ module_param(nested, int, S_IRUGO);
 
 /* enable / disable AVIC */
 static int avic;
+#ifdef CONFIG_X86_LOCAL_APIC
 module_param(avic, int, S_IRUGO);
+#endif
 
 static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
 static void svm_flush_tlb(struct kvm_vcpu *vcpu);
@@ -981,11 +983,14 @@ static __init int svm_hardware_setup(void)
 	} else
 		kvm_disable_tdp();
 
-	if (avic && (!npt_enabled || !boot_cpu_has(X86_FEATURE_AVIC)))
-		avic = false;
-
-	if (avic)
-		pr_info("AVIC enabled\n");
+	if (avic) {
+		if (!npt_enabled ||
+		    !boot_cpu_has(X86_FEATURE_AVIC) ||
+		    !IS_ENABLED(CONFIG_X86_LOCAL_APIC))
+			avic = false;
+		else
+			pr_info("AVIC enabled\n");
+	}
 
 	return 0;
 
@@ -1324,7 +1329,7 @@ free_avic:
 static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run)
 {
 	u64 entry;
-	int h_physical_id = __default_cpu_present_to_apicid(vcpu->cpu);
+	int h_physical_id = kvm_cpu_get_apicid(vcpu->cpu);
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	if (!kvm_vcpu_apicv_active(vcpu))
@@ -1349,7 +1354,7 @@ static void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	u64 entry;
 	/* ID = 0xff (broadcast), ID > 0xff (reserved) */
-	int h_physical_id = __default_cpu_present_to_apicid(cpu);
+	int h_physical_id = kvm_cpu_get_apicid(cpu);
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	if (!kvm_vcpu_apicv_active(vcpu))
@@ -4236,7 +4241,7 @@ static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
 
 	if (avic_vcpu_is_running(vcpu))
 		wrmsrl(SVM_AVIC_DOORBELL,
-		       __default_cpu_present_to_apicid(vcpu->cpu));
+		       kvm_cpu_get_apicid(vcpu->cpu));
 	else
 		kvm_vcpu_wake_up(vcpu);
 }
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index fb93010beaa4df..003618e324ce4b 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2072,7 +2072,8 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
 	unsigned int dest;
 
 	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP))
+		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
+		!kvm_vcpu_apicv_active(vcpu))
 		return;
 
 	do {
@@ -2180,7 +2181,8 @@ static void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu)
 	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
 
 	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP))
+		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
+		!kvm_vcpu_apicv_active(vcpu))
 		return;
 
 	/* Set SN when the vCPU is preempted */
@@ -10714,7 +10716,8 @@ static int vmx_pre_block(struct kvm_vcpu *vcpu)
 	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
 
 	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP))
+		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
+		!kvm_vcpu_apicv_active(vcpu))
 		return 0;
 
 	vcpu->pre_pcpu = vcpu->cpu;
@@ -10780,7 +10783,8 @@ static void vmx_post_block(struct kvm_vcpu *vcpu)
 	unsigned long flags;
 
 	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP))
+		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
+		!kvm_vcpu_apicv_active(vcpu))
 		return;
 
 	do {
@@ -10833,7 +10837,8 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
 	int idx, ret = -EINVAL;
 
 	if (!kvm_arch_has_assigned_device(kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP))
+		!irq_remapping_cap(IRQ_POSTING_CAP) ||
+		!kvm_vcpu_apicv_active(kvm->vcpus[0]))
 		return 0;
 
 	idx = srcu_read_lock(&kvm->irq_srcu);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 02e98f3131bda1..48bd520fc702c9 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2941,7 +2941,7 @@ static long kvm_vm_ioctl(struct file *filp,
 		if (copy_from_user(&routing, argp, sizeof(routing)))
 			goto out;
 		r = -EINVAL;
-		if (routing.nr >= KVM_MAX_IRQ_ROUTES)
+		if (routing.nr > KVM_MAX_IRQ_ROUTES)
 			goto out;
 		if (routing.flags)
 			goto out;