Merge branch 'kvm-updates/2.6.32' of git://git.kernel.org/pub/scm/virt/kvm/kvm

* 'kvm-updates/2.6.32' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (202 commits)
  MAINTAINERS: update KVM entry
  KVM: correct error-handling code
  KVM: fix compile warnings on s390
  KVM: VMX: Check cpl before emulating debug register access
  KVM: fix misreporting of coalesced interrupts by kvm tracer
  KVM: x86: drop duplicate kvm_flush_remote_tlb calls
  KVM: VMX: call vmx_load_host_state() only if msr is cached
  KVM: VMX: Conditionally reload debug register 6
  KVM: Use thread debug register storage instead of kvm specific data
  KVM guest: do not batch pte updates from interrupt context
  KVM: Fix coalesced interrupt reporting in IOAPIC
  KVM guest: fix bogus wallclock physical address calculation
  KVM: VMX: Fix cr8 exiting control clobbering by EPT
  KVM: Optimize kvm_mmu_unprotect_page_virt() for tdp
  KVM: Document KVM_CAP_IRQCHIP
  KVM: Protect update_cr8_intercept() when running without an apic
  KVM: VMX: Fix EPT with WP bit change during paging
  KVM: Use kvm_{read,write}_guest_virt() to read and write segment descriptors
  KVM: x86 emulator: Add adc and sbb missing decoder flags
  KVM: Add missing #include
  ...

arch/powerpc/include/asm/kvm_host.h

@@ -34,7 +34,8 @@
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 
 /* We don't currently support large pages. */
-#define KVM_PAGES_PER_HPAGE (1UL << 31)
+#define KVM_NR_PAGE_SIZES	1
+#define KVM_PAGES_PER_HPAGE(x)	(1UL<<31)
 
 struct kvm;
 struct kvm_run;
@@ -153,7 +154,6 @@ struct kvm_vcpu_arch {
 	u32 pid;
 	u32 swap_pid;
 
-	u32 pvr;
 	u32 ccr0;
 	u32 ccr1;
 	u32 dbcr0;

arch/powerpc/kvm/44x.c

@@ -138,7 +138,7 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 	kmem_cache_free(kvm_vcpu_cache, vcpu_44x);
 }
 
-static int kvmppc_44x_init(void)
+static int __init kvmppc_44x_init(void)
 {
 	int r;
 
@@ -149,7 +149,7 @@ static int kvmppc_44x_init(void)
 	return kvm_init(NULL, sizeof(struct kvmppc_vcpu_44x), THIS_MODULE);
 }
 
-static void kvmppc_44x_exit(void)
+static void __exit kvmppc_44x_exit(void)
 {
 	kvmppc_booke_exit();
 }

arch/powerpc/kvm/44x_tlb.c

@@ -30,6 +30,7 @@
 #include "timing.h"
 
 #include "44x_tlb.h"
+#include "trace.h"
 
 #ifndef PPC44x_TLBE_SIZE
 #define PPC44x_TLBE_SIZE	PPC44x_TLB_4K
@@ -263,7 +264,7 @@ static void kvmppc_44x_shadow_release(struct kvmppc_vcpu_44x *vcpu_44x,
 
 	/* XXX set tlb_44x_index to stlb_index? */
 
-	KVMTRACE_1D(STLB_INVAL, &vcpu_44x->vcpu, stlb_index, handler);
+	trace_kvm_stlb_inval(stlb_index);
 }
 
 void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
@@ -365,8 +366,8 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gpa_t gpaddr,
 	/* Insert shadow mapping into hardware TLB. */
 	kvmppc_44x_tlbe_set_modified(vcpu_44x, victim);
 	kvmppc_44x_tlbwe(victim, &stlbe);
-	KVMTRACE_5D(STLB_WRITE, vcpu, victim, stlbe.tid, stlbe.word0, stlbe.word1,
-	            stlbe.word2, handler);
+	trace_kvm_stlb_write(victim, stlbe.tid, stlbe.word0, stlbe.word1,
+			     stlbe.word2);
 }
 
 /* For a particular guest TLB entry, invalidate the corresponding host TLB
@@ -485,8 +486,8 @@ int kvmppc_44x_emul_tlbwe(struct kvm_vcpu *vcpu, u8 ra, u8 rs, u8 ws)
 		kvmppc_mmu_map(vcpu, eaddr, gpaddr, gtlb_index);
 	}
 
-	KVMTRACE_5D(GTLB_WRITE, vcpu, gtlb_index, tlbe->tid, tlbe->word0,
-	            tlbe->word1, tlbe->word2, handler);
+	trace_kvm_gtlb_write(gtlb_index, tlbe->tid, tlbe->word0, tlbe->word1,
+			     tlbe->word2);
 
 	kvmppc_set_exit_type(vcpu, EMULATED_TLBWE_EXITS);
 	return EMULATE_DONE;

arch/powerpc/kvm/Kconfig

@@ -2,8 +2,7 @@
 # KVM configuration
 #
 
-config HAVE_KVM_IRQCHIP
-       bool
+source "virt/kvm/Kconfig"
 
 menuconfig VIRTUALIZATION
 	bool "Virtualization"
@@ -59,17 +58,6 @@ config KVM_E500
 
 	  If unsure, say N.
 
-config KVM_TRACE
-	bool "KVM trace support"
-	depends on KVM && MARKERS && SYSFS
-	select RELAY
-	select DEBUG_FS
-	default n
-	---help---
-	  This option allows reading a trace of kvm-related events through
-	  relayfs.  Note the ABI is not considered stable and will be
-	  modified in future updates.
-
 source drivers/virtio/Kconfig
 
 endif # VIRTUALIZATION

arch/powerpc/kvm/Makefile

@@ -8,7 +8,9 @@ EXTRA_CFLAGS += -Ivirt/kvm -Iarch/powerpc/kvm
 
 common-objs-y = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o)
 
-common-objs-$(CONFIG_KVM_TRACE)  += $(addprefix ../../../virt/kvm/, kvm_trace.o)
+CFLAGS_44x_tlb.o  := -I.
+CFLAGS_e500_tlb.o := -I.
+CFLAGS_emulate.o  := -I.
 
 kvm-objs := $(common-objs-y) powerpc.o emulate.o
 obj-$(CONFIG_KVM_EXIT_TIMING) += timing.o

arch/powerpc/kvm/booke.c

@@ -520,7 +520,7 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
 	return kvmppc_core_vcpu_translate(vcpu, tr);
 }
 
-int kvmppc_booke_init(void)
+int __init kvmppc_booke_init(void)
 {
 	unsigned long ivor[16];
 	unsigned long max_ivor = 0;

arch/powerpc/kvm/e500.c

@@ -60,9 +60,6 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
 
 	kvmppc_e500_tlb_setup(vcpu_e500);
 
-	/* Use the same core vertion as host's */
-	vcpu->arch.pvr = mfspr(SPRN_PVR);
-
 	return 0;
 }
 
@@ -132,7 +129,7 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 	kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
 }
 
-static int kvmppc_e500_init(void)
+static int __init kvmppc_e500_init(void)
 {
 	int r, i;
 	unsigned long ivor[3];
@@ -160,7 +157,7 @@ static int kvmppc_e500_init(void)
 	return kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), THIS_MODULE);
 }
 
-static void kvmppc_e500_exit(void)
+static void __init kvmppc_e500_exit(void)
 {
 	kvmppc_booke_exit();
 }

arch/powerpc/kvm/e500_emulate.c

@@ -180,6 +180,9 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 	case SPRN_MMUCSR0:
 		vcpu->arch.gpr[rt] = 0; break;
 
+	case SPRN_MMUCFG:
+		vcpu->arch.gpr[rt] = mfspr(SPRN_MMUCFG); break;
+
 	/* extra exceptions */
 	case SPRN_IVOR32:
 		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL];

arch/powerpc/kvm/e500_tlb.c

@@ -22,6 +22,7 @@
 
 #include "../mm/mmu_decl.h"
 #include "e500_tlb.h"
+#include "trace.h"
 
 #define to_htlb1_esel(esel) (tlb1_entry_num - (esel) - 1)
 
@@ -224,9 +225,8 @@ static void kvmppc_e500_stlbe_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500,
 
 	kvmppc_e500_shadow_release(vcpu_e500, tlbsel, esel);
 	stlbe->mas1 = 0;
-	KVMTRACE_5D(STLB_INVAL, &vcpu_e500->vcpu, index_of(tlbsel, esel),
-			stlbe->mas1, stlbe->mas2, stlbe->mas3, stlbe->mas7,
-			handler);
+	trace_kvm_stlb_inval(index_of(tlbsel, esel), stlbe->mas1, stlbe->mas2,
+			     stlbe->mas3, stlbe->mas7);
 }
 
 static void kvmppc_e500_tlb1_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500,
@@ -269,7 +269,7 @@ static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu,
 	tlbsel = (vcpu_e500->mas4 >> 28) & 0x1;
 	victim = (tlbsel == 0) ? tlb0_get_next_victim(vcpu_e500) : 0;
 	pidsel = (vcpu_e500->mas4 >> 16) & 0xf;
-	tsized = (vcpu_e500->mas4 >> 8) & 0xf;
+	tsized = (vcpu_e500->mas4 >> 7) & 0x1f;
 
 	vcpu_e500->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(victim)
 		| MAS0_NV(vcpu_e500->guest_tlb_nv[tlbsel]);
@@ -309,7 +309,7 @@ static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	vcpu_e500->shadow_pages[tlbsel][esel] = new_page;
 
 	/* Force TS=1 IPROT=0 TSIZE=4KB for all guest mappings. */
-	stlbe->mas1 = MAS1_TSIZE(BOOKE_PAGESZ_4K)
+	stlbe->mas1 = MAS1_TSIZE(BOOK3E_PAGESZ_4K)
 		| MAS1_TID(get_tlb_tid(gtlbe)) | MAS1_TS | MAS1_VALID;
 	stlbe->mas2 = (gvaddr & MAS2_EPN)
 		| e500_shadow_mas2_attrib(gtlbe->mas2,
@@ -319,9 +319,8 @@ static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 				vcpu_e500->vcpu.arch.msr & MSR_PR);
 	stlbe->mas7 = (hpaddr >> 32) & MAS7_RPN;
 
-	KVMTRACE_5D(STLB_WRITE, &vcpu_e500->vcpu, index_of(tlbsel, esel),
-			stlbe->mas1, stlbe->mas2, stlbe->mas3, stlbe->mas7,
-			handler);
+	trace_kvm_stlb_write(index_of(tlbsel, esel), stlbe->mas1, stlbe->mas2,
+			     stlbe->mas3, stlbe->mas7);
 }
 
 /* XXX only map the one-one case, for now use TLB0 */
@@ -535,9 +534,8 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 	gtlbe->mas3 = vcpu_e500->mas3;
 	gtlbe->mas7 = vcpu_e500->mas7;
 
-	KVMTRACE_5D(GTLB_WRITE, vcpu, vcpu_e500->mas0,
-			gtlbe->mas1, gtlbe->mas2, gtlbe->mas3, gtlbe->mas7,
-			handler);
+	trace_kvm_gtlb_write(vcpu_e500->mas0, gtlbe->mas1, gtlbe->mas2,
+			     gtlbe->mas3, gtlbe->mas7);
 
 	/* Invalidate shadow mappings for the about-to-be-clobbered TLBE. */
 	if (tlbe_is_host_safe(vcpu, gtlbe)) {
@@ -545,7 +543,7 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 		case 0:
 			/* TLB0 */
 			gtlbe->mas1 &= ~MAS1_TSIZE(~0);
-			gtlbe->mas1 |= MAS1_TSIZE(BOOKE_PAGESZ_4K);
+			gtlbe->mas1 |= MAS1_TSIZE(BOOK3E_PAGESZ_4K);
 
 			stlbsel = 0;
 			sesel = kvmppc_e500_stlbe_map(vcpu_e500, 0, esel);
@@ -679,14 +677,14 @@ void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *vcpu_e500)
 
 	/* Insert large initial mapping for guest. */
 	tlbe = &vcpu_e500->guest_tlb[1][0];
-	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOKE_PAGESZ_256M);
+	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_256M);
 	tlbe->mas2 = 0;
 	tlbe->mas3 = E500_TLB_SUPER_PERM_MASK;
 	tlbe->mas7 = 0;
 
 	/* 4K map for serial output. Used by kernel wrapper. */
 	tlbe = &vcpu_e500->guest_tlb[1][1];
-	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOKE_PAGESZ_4K);
+	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_4K);
 	tlbe->mas2 = (0xe0004500 & 0xFFFFF000) | MAS2_I | MAS2_G;
 	tlbe->mas3 = (0xe0004500 & 0xFFFFF000) | E500_TLB_SUPER_PERM_MASK;
 	tlbe->mas7 = 0;

arch/powerpc/kvm/e500_tlb.h

@@ -16,7 +16,7 @@
 #define __KVM_E500_TLB_H__
 
 #include <linux/kvm_host.h>
-#include <asm/mmu-fsl-booke.h>
+#include <asm/mmu-book3e.h>
 #include <asm/tlb.h>
 #include <asm/kvm_e500.h>
 
@@ -59,7 +59,7 @@ extern void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *);
 /* TLB helper functions */
 static inline unsigned int get_tlb_size(const struct tlbe *tlbe)
 {
-	return (tlbe->mas1 >> 8) & 0xf;
+	return (tlbe->mas1 >> 7) & 0x1f;
 }
 
 static inline gva_t get_tlb_eaddr(const struct tlbe *tlbe)
@@ -70,7 +70,7 @@ static inline gva_t get_tlb_eaddr(const struct tlbe *tlbe)
 static inline u64 get_tlb_bytes(const struct tlbe *tlbe)
 {
 	unsigned int pgsize = get_tlb_size(tlbe);
-	return 1ULL << 10 << (pgsize << 1);
+	return 1ULL << 10 << pgsize;
 }
 
 static inline gva_t get_tlb_end(const struct tlbe *tlbe)

arch/powerpc/kvm/emulate.c

@@ -29,6 +29,7 @@
 #include <asm/kvm_ppc.h>
 #include <asm/disassemble.h>
 #include "timing.h"
+#include "trace.h"
 
 #define OP_TRAP 3
 
@@ -187,7 +188,9 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			case SPRN_SRR1:
 				vcpu->arch.gpr[rt] = vcpu->arch.srr1; break;
 			case SPRN_PVR:
-				vcpu->arch.gpr[rt] = vcpu->arch.pvr; break;
+				vcpu->arch.gpr[rt] = mfspr(SPRN_PVR); break;
+			case SPRN_PIR:
+				vcpu->arch.gpr[rt] = mfspr(SPRN_PIR); break;
 
 			/* Note: mftb and TBRL/TBWL are user-accessible, so
 			 * the guest can always access the real TB anyways.
@@ -417,7 +420,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		}
 	}
 
-	KVMTRACE_3D(PPC_INSTR, vcpu, inst, (int)vcpu->arch.pc, emulated, entryexit);
+	trace_kvm_ppc_instr(inst, vcpu->arch.pc, emulated);
 
 	if (advance)
 		vcpu->arch.pc += 4; /* Advance past emulated instruction. */

arch/powerpc/kvm/powerpc.c

@@ -31,25 +31,17 @@
 #include "timing.h"
 #include "../mm/mmu_decl.h"
 
+#define CREATE_TRACE_POINTS
+#include "trace.h"
+
 gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
 {
 	return gfn;
 }
 
-int kvm_cpu_has_interrupt(struct kvm_vcpu *v)
-{
-	return !!(v->arch.pending_exceptions);
-}
-
-int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu)
-{
-	/* do real check here */
-	return 1;
-}
-
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 {
-	return !(v->arch.msr & MSR_WE);
+	return !(v->arch.msr & MSR_WE) || !!(v->arch.pending_exceptions);
 }
 
 
@@ -122,13 +114,17 @@ struct kvm *kvm_arch_create_vm(void)
 static void kvmppc_free_vcpus(struct kvm *kvm)
 {
 	unsigned int i;
+	struct kvm_vcpu *vcpu;
 
-	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
-		if (kvm->vcpus[i]) {
-			kvm_arch_vcpu_free(kvm->vcpus[i]);
-			kvm->vcpus[i] = NULL;
-		}
-	}
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		kvm_arch_vcpu_free(vcpu);
+
+	mutex_lock(&kvm->lock);
+	for (i = 0; i < atomic_read(&kvm->online_vcpus); i++)
+		kvm->vcpus[i] = NULL;
+
+	atomic_set(&kvm->online_vcpus, 0);
+	mutex_unlock(&kvm->lock);
 }
 
 void kvm_arch_sync_events(struct kvm *kvm)

arch/powerpc/kvm/trace.h

@@ -0,0 +1,104 @@
+#if !defined(_TRACE_KVM_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_KVM_H
+
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kvm
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace
+
+/*
+ * Tracepoint for guest mode entry.
+ */
+TRACE_EVENT(kvm_ppc_instr,
+	TP_PROTO(unsigned int inst, unsigned long pc, unsigned int emulate),
+	TP_ARGS(inst, pc, emulate),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	inst		)
+		__field(	unsigned long,	pc		)
+		__field(	unsigned int,	emulate		)
+	),
+
+	TP_fast_assign(
+		__entry->inst		= inst;
+		__entry->pc		= pc;
+		__entry->emulate	= emulate;
+	),
+
+	TP_printk("inst %u pc 0x%lx emulate %u\n",
+		  __entry->inst, __entry->pc, __entry->emulate)
+);
+
+TRACE_EVENT(kvm_stlb_inval,
+	TP_PROTO(unsigned int stlb_index),
+	TP_ARGS(stlb_index),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	stlb_index	)
+	),
+
+	TP_fast_assign(
+		__entry->stlb_index	= stlb_index;
+	),
+
+	TP_printk("stlb_index %u", __entry->stlb_index)
+);
+
+TRACE_EVENT(kvm_stlb_write,
+	TP_PROTO(unsigned int victim, unsigned int tid, unsigned int word0,
+		 unsigned int word1, unsigned int word2),
+	TP_ARGS(victim, tid, word0, word1, word2),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	victim		)
+		__field(	unsigned int,	tid		)
+		__field(	unsigned int,	word0		)
+		__field(	unsigned int,	word1		)
+		__field(	unsigned int,	word2		)
+	),
+
+	TP_fast_assign(
+		__entry->victim		= victim;
+		__entry->tid		= tid;
+		__entry->word0		= word0;
+		__entry->word1		= word1;
+		__entry->word2		= word2;
+	),
+
+	TP_printk("victim %u tid %u w0 %u w1 %u w2 %u",
+		__entry->victim, __entry->tid, __entry->word0,
+		__entry->word1, __entry->word2)
+);
+
+TRACE_EVENT(kvm_gtlb_write,
+	TP_PROTO(unsigned int gtlb_index, unsigned int tid, unsigned int word0,
+		 unsigned int word1, unsigned int word2),
+	TP_ARGS(gtlb_index, tid, word0, word1, word2),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	gtlb_index	)
+		__field(	unsigned int,	tid		)
+		__field(	unsigned int,	word0		)
+		__field(	unsigned int,	word1		)
+		__field(	unsigned int,	word2		)
+	),
+
+	TP_fast_assign(
+		__entry->gtlb_index	= gtlb_index;
+		__entry->tid		= tid;
+		__entry->word0		= word0;
+		__entry->word1		= word1;
+		__entry->word2		= word2;
+	),
+
+	TP_printk("gtlb_index %u tid %u w0 %u w1 %u w2 %u",
+		__entry->gtlb_index, __entry->tid, __entry->word0,
+		__entry->word1, __entry->word2)
+);
+
+#endif /* _TRACE_KVM_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>