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

Pull KVM updates from Paolo Bonzini:
 "First batch of KVM changes for 4.4.

  s390:
     A bunch of fixes and optimizations for interrupt and time handling.

  PPC:
     Mostly bug fixes.

  ARM:
     No big features, but many small fixes and prerequisites including:

      - a number of fixes for the arch-timer

      - introducing proper level-triggered semantics for the arch-timers

      - a series of patches to synchronously halt a guest (prerequisite
        for IRQ forwarding)

      - some tracepoint improvements

      - a tweak for the EL2 panic handlers

      - some more VGIC cleanups getting rid of redundant state

  x86:
     Quite a few changes:

      - support for VT-d posted interrupts (i.e. PCI devices can inject
        interrupts directly into vCPUs).  This introduces a new
        component (in virt/lib/) that connects VFIO and KVM together.
        The same infrastructure will be used for ARM interrupt
        forwarding as well.

      - more Hyper-V features, though the main one Hyper-V synthetic
        interrupt controller will have to wait for 4.5.  These will let
        KVM expose Hyper-V devices.

      - nested virtualization now supports VPID (same as PCID but for
        vCPUs) which makes it quite a bit faster

      - for future hardware that supports NVDIMM, there is support for
        clflushopt, clwb, pcommit

      - support for "split irqchip", i.e.  LAPIC in kernel +
        IOAPIC/PIC/PIT in userspace, which reduces the attack surface of
        the hypervisor

      - obligatory smattering of SMM fixes

      - on the guest side, stable scheduler clock support was rewritten
        to not require help from the hypervisor"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (123 commits)
  KVM: VMX: Fix commit which broke PML
  KVM: x86: obey KVM_X86_QUIRK_CD_NW_CLEARED in kvm_set_cr0()
  KVM: x86: allow RSM from 64-bit mode
  KVM: VMX: fix SMEP and SMAP without EPT
  KVM: x86: move kvm_set_irq_inatomic to legacy device assignment
  KVM: device assignment: remove pointless #ifdefs
  KVM: x86: merge kvm_arch_set_irq with kvm_set_msi_inatomic
  KVM: x86: zero apic_arb_prio on reset
  drivers/hv: share Hyper-V SynIC constants with userspace
  KVM: x86: handle SMBASE as physical address in RSM
  KVM: x86: add read_phys to x86_emulate_ops
  KVM: x86: removing unused variable
  KVM: don't pointlessly leave KVM_COMPAT=y in non-KVM configs
  KVM: arm/arm64: Merge vgic_set_lr() and vgic_sync_lr_elrsr()
  KVM: arm/arm64: Clean up vgic_retire_lr() and surroundings
  KVM: arm/arm64: Optimize away redundant LR tracking
  KVM: s390: use simple switch statement as multiplexer
  KVM: s390: drop useless newline in debugging data
  KVM: s390: SCA must not cross page boundaries
  KVM: arm: Do not indent the arguments of DECLARE_BITMAP
  ...

7 files changed, 52 insertions, 11 deletions

diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 1f9c0a17f445..10722b1e38b5 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -70,7 +70,8 @@ long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp)
 	}
 
 	/* Lastly try successively smaller sizes from the page allocator */
-	while (!hpt && order > PPC_MIN_HPT_ORDER) {
+	/* Only do this if userspace didn't specify a size via ioctl */
+	while (!hpt && order > PPC_MIN_HPT_ORDER && !htab_orderp) {
 		hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT|
 				       __GFP_NOWARN, order - PAGE_SHIFT);
 		if (!hpt)
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index c1df9bb1e413..97e7f8c853d8 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -470,6 +470,8 @@ long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags,
 	note_hpte_modification(kvm, rev);
 	unlock_hpte(hpte, 0);
 
+	if (v & HPTE_V_ABSENT)
+		v = (v & ~HPTE_V_ABSENT) | HPTE_V_VALID;
 	hpret[0] = v;
 	hpret[1] = r;
 	return H_SUCCESS;
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index b98889e9851d..b1dab8d1d885 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -150,6 +150,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	cmpwi	cr1, r12, BOOK3S_INTERRUPT_MACHINE_CHECK
 	cmpwi	r12, BOOK3S_INTERRUPT_EXTERNAL
 	beq	11f
+	cmpwi	r12, BOOK3S_INTERRUPT_H_DOORBELL
+	beq 	15f	/* Invoke the H_DOORBELL handler */
 	cmpwi	cr2, r12, BOOK3S_INTERRUPT_HMI
 	beq	cr2, 14f			/* HMI check */
 
@@ -174,6 +176,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	mtspr	SPRN_HSRR1, r7
 	b	hmi_exception_after_realmode
 
+15:	mtspr SPRN_HSRR0, r8
+	mtspr SPRN_HSRR1, r7
+	ba    0xe80
+
 kvmppc_primary_no_guest:
 	/* We handle this much like a ceded vcpu */
 	/* put the HDEC into the DEC, since HDEC interrupts don't wake us */
@@ -2377,7 +2383,6 @@ machine_check_realmode:
 	mr	r3, r9		/* get vcpu pointer */
 	bl	kvmppc_realmode_machine_check
 	nop
-	cmpdi	r3, 0		/* Did we handle MCE ? */
 	ld	r9, HSTATE_KVM_VCPU(r13)
 	li	r12, BOOK3S_INTERRUPT_MACHINE_CHECK
 	/*
@@ -2390,13 +2395,18 @@ machine_check_realmode:
 	 * The old code used to return to host for unhandled errors which
 	 * was causing guest to hang with soft lockups inside guest and
 	 * makes it difficult to recover guest instance.
+	 *
+	 * if we receive machine check with MSR(RI=0) then deliver it to
+	 * guest as machine check causing guest to crash.
 	 */
-	ld	r10, VCPU_PC(r9)
 	ld	r11, VCPU_MSR(r9)
+	andi.	r10, r11, MSR_RI	/* check for unrecoverable exception */
+	beq	1f			/* Deliver a machine check to guest */
+	ld	r10, VCPU_PC(r9)
+	cmpdi	r3, 0		/* Did we handle MCE ? */
 	bne	2f	/* Continue guest execution. */
 	/* If not, deliver a machine check.  SRR0/1 are already set */
-	li	r10, BOOK3S_INTERRUPT_MACHINE_CHECK
-	ld	r11, VCPU_MSR(r9)
+1:	li	r10, BOOK3S_INTERRUPT_MACHINE_CHECK
 	bl	kvmppc_msr_interrupt
 2:	b	fast_interrupt_c_return
 
@@ -2436,14 +2446,19 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 
 	/* hypervisor doorbell */
 3:	li	r12, BOOK3S_INTERRUPT_H_DOORBELL
+
+	/*
+	 * Clear the doorbell as we will invoke the handler
+	 * explicitly in the guest exit path.
+	 */
+	lis	r6, (PPC_DBELL_SERVER << (63-36))@h
+	PPC_MSGCLR(6)
 	/* see if it's a host IPI */
 	li	r3, 1
 	lbz	r0, HSTATE_HOST_IPI(r13)
 	cmpwi	r0, 0
 	bnelr
-	/* if not, clear it and return -1 */
-	lis	r6, (PPC_DBELL_SERVER << (63-36))@h
-	PPC_MSGCLR(6)
+	/* if not, return -1 */
 	li	r3, -1
 	blr
 
diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
index b29ce752c7d6..32fdab57d604 100644
--- a/arch/powerpc/kvm/e500.c
+++ b/arch/powerpc/kvm/e500.c
@@ -237,7 +237,8 @@ void kvmppc_e500_tlbil_one(struct kvmppc_vcpu_e500 *vcpu_e500,
                            struct kvm_book3e_206_tlb_entry *gtlbe)
 {
 	struct vcpu_id_table *idt = vcpu_e500->idt;
-	unsigned int pr, tid, ts, pid;
+	unsigned int pr, tid, ts;
+	int pid;
 	u32 val, eaddr;
 	unsigned long flags;
 
diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c
index ce7291c79f6c..990db69a1d0b 100644
--- a/arch/powerpc/kvm/e500_emulate.c
+++ b/arch/powerpc/kvm/e500_emulate.c
@@ -15,6 +15,7 @@
 #include <asm/kvm_ppc.h>
 #include <asm/disassemble.h>
 #include <asm/dbell.h>
+#include <asm/reg_booke.h>
 
 #include "booke.h"
 #include "e500.h"
@@ -22,6 +23,7 @@
 #define XOP_DCBTLS  166
 #define XOP_MSGSND  206
 #define XOP_MSGCLR  238
+#define XOP_MFTMR   366
 #define XOP_TLBIVAX 786
 #define XOP_TLBSX   914
 #define XOP_TLBRE   946
@@ -113,6 +115,19 @@ static int kvmppc_e500_emul_dcbtls(struct kvm_vcpu *vcpu)
 	return EMULATE_DONE;
 }
 
+static int kvmppc_e500_emul_mftmr(struct kvm_vcpu *vcpu, unsigned int inst,
+				  int rt)
+{
+	/* Expose one thread per vcpu */
+	if (get_tmrn(inst) == TMRN_TMCFG0) {
+		kvmppc_set_gpr(vcpu, rt,
+			       1 | (1 << TMRN_TMCFG0_NATHRD_SHIFT));
+		return EMULATE_DONE;
+	}
+
+	return EMULATE_FAIL;
+}
+
 int kvmppc_core_emulate_op_e500(struct kvm_run *run, struct kvm_vcpu *vcpu,
 				unsigned int inst, int *advance)
 {
@@ -165,6 +180,10 @@ int kvmppc_core_emulate_op_e500(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			emulated = kvmppc_e500_emul_tlbivax(vcpu, ea);
 			break;
 
+		case XOP_MFTMR:
+			emulated = kvmppc_e500_emul_mftmr(vcpu, inst, rt);
+			break;
+
 		case XOP_EHPRIV:
 			emulated = kvmppc_e500_emul_ehpriv(run, vcpu, inst,
 							   advance);
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index 4d33e199edcc..5e2102c19586 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -406,7 +406,7 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 
 			for (; tsize > BOOK3E_PAGESZ_4K; tsize -= 2) {
 				unsigned long gfn_start, gfn_end;
-				tsize_pages = 1 << (tsize - 2);
+				tsize_pages = 1UL << (tsize - 2);
 
 				gfn_start = gfn & ~(tsize_pages - 1);
 				gfn_end = gfn_start + tsize_pages;
@@ -447,7 +447,7 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	}
 
 	if (likely(!pfnmap)) {
-		tsize_pages = 1 << (tsize + 10 - PAGE_SHIFT);
+		tsize_pages = 1UL << (tsize + 10 - PAGE_SHIFT);
 		pfn = gfn_to_pfn_memslot(slot, gfn);
 		if (is_error_noslot_pfn(pfn)) {
 			if (printk_ratelimit())
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 2e51289610e4..6fd2405c7f4a 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -559,6 +559,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		else
 			r = num_online_cpus();
 		break;
+	case KVM_CAP_NR_MEMSLOTS:
+		r = KVM_USER_MEM_SLOTS;
+		break;
 	case KVM_CAP_MAX_VCPUS:
 		r = KVM_MAX_VCPUS;
 		break;