Merge branch 'kvm-updates/2.6.34' of git://git.kernel.org/pub/scm/vir…

…t/kvm/kvm

* 'kvm-updates/2.6.34' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (145 commits)
  KVM: x86: Add KVM_CAP_X86_ROBUST_SINGLESTEP
  KVM: VMX: Update instruction length on intercepted BP
  KVM: Fix emulate_sys[call, enter, exit]()'s fault handling
  KVM: Fix segment descriptor loading
  KVM: Fix load_guest_segment_descriptor() to inject page fault
  KVM: x86 emulator: Forbid modifying CS segment register by mov instruction
  KVM: Convert kvm->requests_lock to raw_spinlock_t
  KVM: Convert i8254/i8259 locks to raw_spinlocks
  KVM: x86 emulator: disallow opcode 82 in 64-bit mode
  KVM: x86 emulator: code style cleanup
  KVM: Plan obsolescence of kernel allocated slots, paravirt mmu
  KVM: x86 emulator: Add LOCK prefix validity checking
  KVM: x86 emulator: Check CPL level during privilege instruction emulation
  KVM: x86 emulator: Fix popf emulation
  KVM: x86 emulator: Check IOPL level during io instruction emulation
  KVM: x86 emulator: fix memory access during x86 emulation
  KVM: x86 emulator: Add Virtual-8086 mode of emulation
  KVM: x86 emulator: Add group9 instruction decoding
  KVM: x86 emulator: Add group8 instruction decoding
  KVM: do not store wqh in irqfd
  ...

Trivial conflicts in Documentation/feature-removal-schedule.txt

Documentation/feature-removal-schedule.txt

@@ -556,3 +556,35 @@ Why:	udev fully replaces this special file system that only contains CAPI
 	NCCI TTY device nodes. User space (pppdcapiplugin) works without
 	noticing the difference.
 Who:	Jan Kiszka <[email protected]>
+
+----------------------------
+
+What:	KVM memory aliases support
+When:	July 2010
+Why:	Memory aliasing support is used for speeding up guest vga access
+	through the vga windows.
+
+	Modern userspace no longer uses this feature, so it's just bitrotted
+	code and can be removed with no impact.
+Who:	Avi Kivity <[email protected]>
+
+----------------------------
+
+What:	KVM kernel-allocated memory slots
+When:	July 2010
+Why:	Since 2.6.25, kvm supports user-allocated memory slots, which are
+	much more flexible than kernel-allocated slots.  All current userspace
+	supports the newer interface and this code can be removed with no
+	impact.
+Who:	Avi Kivity <[email protected]>
+
+----------------------------
+
+What:	KVM paravirt mmu host support
+When:	January 2011
+Why:	The paravirt mmu host support is slower than non-paravirt mmu, both
+	on newer and older hardware.  It is already not exposed to the guest,
+	and kept only for live migration purposes.
+Who:	Avi Kivity <[email protected]>
+
+----------------------------

Documentation/kvm/api.txt

@@ -23,12 +23,12 @@ of a virtual machine.  The ioctls belong to three classes
    Only run vcpu ioctls from the same thread that was used to create the
    vcpu.
 
-2. File descritpors
+2. File descriptors
 
 The kvm API is centered around file descriptors.  An initial
 open("/dev/kvm") obtains a handle to the kvm subsystem; this handle
 can be used to issue system ioctls.  A KVM_CREATE_VM ioctl on this
-handle will create a VM file descripror which can be used to issue VM
+handle will create a VM file descriptor which can be used to issue VM
 ioctls.  A KVM_CREATE_VCPU ioctl on a VM fd will create a virtual cpu
 and return a file descriptor pointing to it.  Finally, ioctls on a vcpu
 fd can be used to control the vcpu, including the important task of
@@ -643,7 +643,7 @@ Type: vm ioctl
 Parameters: struct kvm_clock_data (in)
 Returns: 0 on success, -1 on error
 
-Sets the current timestamp of kvmclock to the valued specific in its parameter.
+Sets the current timestamp of kvmclock to the value specified in its parameter.
 In conjunction with KVM_GET_CLOCK, it is used to ensure monotonicity on scenarios
 such as migration.
 
@@ -795,11 +795,11 @@ Unused.
 			__u64 data_offset; /* relative to kvm_run start */
 		} io;
 
-If exit_reason is KVM_EXIT_IO_IN or KVM_EXIT_IO_OUT, then the vcpu has
+If exit_reason is KVM_EXIT_IO, then the vcpu has
 executed a port I/O instruction which could not be satisfied by kvm.
 data_offset describes where the data is located (KVM_EXIT_IO_OUT) or
 where kvm expects application code to place the data for the next
-KVM_RUN invocation (KVM_EXIT_IO_IN).  Data format is a patcked array.
+KVM_RUN invocation (KVM_EXIT_IO_IN).  Data format is a packed array.
 
 		struct {
 			struct kvm_debug_exit_arch arch;
@@ -815,7 +815,7 @@ Unused.
 			__u8  is_write;
 		} mmio;
 
-If exit_reason is KVM_EXIT_MMIO or KVM_EXIT_IO_OUT, then the vcpu has
+If exit_reason is KVM_EXIT_MMIO, then the vcpu has
 executed a memory-mapped I/O instruction which could not be satisfied
 by kvm.  The 'data' member contains the written data if 'is_write' is
 true, and should be filled by application code otherwise.

MAINTAINERS

@@ -3173,7 +3173,7 @@ F:	arch/x86/include/asm/svm.h
 F:	arch/x86/kvm/svm.c
 
 KERNEL VIRTUAL MACHINE (KVM) FOR POWERPC
-M:	Hollis Blanchard <[email protected]>
+M:	Alexander Graf <[email protected]>
 L:	[email protected]
 W:	http://kvm.qumranet.com
 S:	Supported

arch/ia64/kvm/Kconfig

@@ -26,6 +26,7 @@ config KVM
 	select ANON_INODES
 	select HAVE_KVM_IRQCHIP
 	select KVM_APIC_ARCHITECTURE
+	select KVM_MMIO
 	---help---
 	  Support hosting fully virtualized guest machines using hardware
 	  virtualization extensions.  You will need a fairly recent

arch/ia64/kvm/kvm-ia64.c

@@ -241,10 +241,10 @@ static int handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	return 0;
 mmio:
 	if (p->dir)
-		r = kvm_io_bus_read(&vcpu->kvm->mmio_bus, p->addr,
+		r = kvm_io_bus_read(vcpu->kvm, KVM_MMIO_BUS, p->addr,
 				    p->size, &p->data);
 	else
-		r = kvm_io_bus_write(&vcpu->kvm->mmio_bus, p->addr,
+		r = kvm_io_bus_write(vcpu->kvm, KVM_MMIO_BUS, p->addr,
 				     p->size, &p->data);
 	if (r)
 		printk(KERN_ERR"kvm: No iodevice found! addr:%lx\n", p->addr);
@@ -636,12 +636,9 @@ static void kvm_vcpu_post_transition(struct kvm_vcpu *vcpu)
 static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	union context *host_ctx, *guest_ctx;
-	int r;
+	int r, idx;
 
-	/*
-	 * down_read() may sleep and return with interrupts enabled
-	 */
-	down_read(&vcpu->kvm->slots_lock);
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
 
 again:
 	if (signal_pending(current)) {
@@ -663,7 +660,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	if (r < 0)
 		goto vcpu_run_fail;
 
-	up_read(&vcpu->kvm->slots_lock);
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 	kvm_guest_enter();
 
 	/*
@@ -687,7 +684,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	kvm_guest_exit();
 	preempt_enable();
 
-	down_read(&vcpu->kvm->slots_lock);
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
 
 	r = kvm_handle_exit(kvm_run, vcpu);
 
@@ -697,10 +694,10 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	}
 
 out:
-	up_read(&vcpu->kvm->slots_lock);
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 	if (r > 0) {
 		kvm_resched(vcpu);
-		down_read(&vcpu->kvm->slots_lock);
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
 		goto again;
 	}
 
@@ -971,7 +968,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 			goto out;
 		r = kvm_setup_default_irq_routing(kvm);
 		if (r) {
-			kfree(kvm->arch.vioapic);
+			kvm_ioapic_destroy(kvm);
 			goto out;
 		}
 		break;
@@ -1377,12 +1374,14 @@ static void free_kvm(struct kvm *kvm)
 
 static void kvm_release_vm_pages(struct kvm *kvm)
 {
+	struct kvm_memslots *slots;
 	struct kvm_memory_slot *memslot;
 	int i, j;
 	unsigned long base_gfn;
 
-	for (i = 0; i < kvm->nmemslots; i++) {
-		memslot = &kvm->memslots[i];
+	slots = rcu_dereference(kvm->memslots);
+	for (i = 0; i < slots->nmemslots; i++) {
+		memslot = &slots->memslots[i];
 		base_gfn = memslot->base_gfn;
 
 		for (j = 0; j < memslot->npages; j++) {
@@ -1405,6 +1404,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kfree(kvm->arch.vioapic);
 	kvm_release_vm_pages(kvm);
 	kvm_free_physmem(kvm);
+	cleanup_srcu_struct(&kvm->srcu);
 	free_kvm(kvm);
 }
 
@@ -1576,15 +1576,15 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	return r;
 }
 
-int kvm_arch_set_memory_region(struct kvm *kvm,
-		struct kvm_userspace_memory_region *mem,
+int kvm_arch_prepare_memory_region(struct kvm *kvm,
+		struct kvm_memory_slot *memslot,
 		struct kvm_memory_slot old,
+		struct kvm_userspace_memory_region *mem,
 		int user_alloc)
 {
 	unsigned long i;
 	unsigned long pfn;
-	int npages = mem->memory_size >> PAGE_SHIFT;
-	struct kvm_memory_slot *memslot = &kvm->memslots[mem->slot];
+	int npages = memslot->npages;
 	unsigned long base_gfn = memslot->base_gfn;
 
 	if (base_gfn + npages > (KVM_MAX_MEM_SIZE >> PAGE_SHIFT))
@@ -1608,6 +1608,14 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 	return 0;
 }
 
+void kvm_arch_commit_memory_region(struct kvm *kvm,
+		struct kvm_userspace_memory_region *mem,
+		struct kvm_memory_slot old,
+		int user_alloc)
+{
+	return;
+}
+
 void kvm_arch_flush_shadow(struct kvm *kvm)
 {
 	kvm_flush_remote_tlbs(kvm);
@@ -1802,7 +1810,7 @@ static int kvm_ia64_sync_dirty_log(struct kvm *kvm,
 	if (log->slot >= KVM_MEMORY_SLOTS)
 		goto out;
 
-	memslot = &kvm->memslots[log->slot];
+	memslot = &kvm->memslots->memslots[log->slot];
 	r = -ENOENT;
 	if (!memslot->dirty_bitmap)
 		goto out;
@@ -1827,6 +1835,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 	struct kvm_memory_slot *memslot;
 	int is_dirty = 0;
 
+	mutex_lock(&kvm->slots_lock);
 	spin_lock(&kvm->arch.dirty_log_lock);
 
 	r = kvm_ia64_sync_dirty_log(kvm, log);
@@ -1840,12 +1849,13 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 	/* If nothing is dirty, don't bother messing with page tables. */
 	if (is_dirty) {
 		kvm_flush_remote_tlbs(kvm);
-		memslot = &kvm->memslots[log->slot];
+		memslot = &kvm->memslots->memslots[log->slot];
 		n = ALIGN(memslot->npages, BITS_PER_LONG) / 8;
 		memset(memslot->dirty_bitmap, 0, n);
 	}
 	r = 0;
 out:
+	mutex_unlock(&kvm->slots_lock);
 	spin_unlock(&kvm->arch.dirty_log_lock);
 	return r;
 }

arch/ia64/kvm/kvm_fw.c

@@ -75,7 +75,7 @@ static void set_pal_result(struct kvm_vcpu *vcpu,
 	struct exit_ctl_data *p;
 
 	p = kvm_get_exit_data(vcpu);
-	if (p && p->exit_reason == EXIT_REASON_PAL_CALL) {
+	if (p->exit_reason == EXIT_REASON_PAL_CALL) {
 		p->u.pal_data.ret = result;
 		return ;
 	}
@@ -87,7 +87,7 @@ static void set_sal_result(struct kvm_vcpu *vcpu,
 	struct exit_ctl_data *p;
 
 	p = kvm_get_exit_data(vcpu);
-	if (p && p->exit_reason == EXIT_REASON_SAL_CALL) {
+	if (p->exit_reason == EXIT_REASON_SAL_CALL) {
 		p->u.sal_data.ret = result;
 		return ;
 	}
@@ -322,7 +322,7 @@ static  u64 kvm_get_pal_call_index(struct kvm_vcpu *vcpu)
 	struct exit_ctl_data *p;
 
 	p = kvm_get_exit_data(vcpu);
-	if (p && (p->exit_reason == EXIT_REASON_PAL_CALL))
+	if (p->exit_reason == EXIT_REASON_PAL_CALL)
 		index = p->u.pal_data.gr28;
 
 	return index;
@@ -646,18 +646,16 @@ static void kvm_get_sal_call_data(struct kvm_vcpu *vcpu, u64 *in0, u64 *in1,
 
 	p = kvm_get_exit_data(vcpu);
 
-	if (p) {
-		if (p->exit_reason == EXIT_REASON_SAL_CALL) {
-			*in0 = p->u.sal_data.in0;
-			*in1 = p->u.sal_data.in1;
-			*in2 = p->u.sal_data.in2;
-			*in3 = p->u.sal_data.in3;
-			*in4 = p->u.sal_data.in4;
-			*in5 = p->u.sal_data.in5;
-			*in6 = p->u.sal_data.in6;
-			*in7 = p->u.sal_data.in7;
-			return ;
-		}
+	if (p->exit_reason == EXIT_REASON_SAL_CALL) {
+		*in0 = p->u.sal_data.in0;
+		*in1 = p->u.sal_data.in1;
+		*in2 = p->u.sal_data.in2;
+		*in3 = p->u.sal_data.in3;
+		*in4 = p->u.sal_data.in4;
+		*in5 = p->u.sal_data.in5;
+		*in6 = p->u.sal_data.in6;
+		*in7 = p->u.sal_data.in7;
+		return ;
 	}
 	*in0 = 0;
 }

arch/ia64/kvm/mmio.c

@@ -316,8 +316,8 @@ void emulate_io_inst(struct kvm_vcpu *vcpu, u64 padr, u64 ma)
 		return;
 	} else {
 		inst_type = -1;
-		panic_vm(vcpu, "Unsupported MMIO access instruction! \
-				Bunld[0]=0x%lx, Bundle[1]=0x%lx\n",
+		panic_vm(vcpu, "Unsupported MMIO access instruction! "
+				"Bunld[0]=0x%lx, Bundle[1]=0x%lx\n",
 				bundle.i64[0], bundle.i64[1]);
 	}
 

arch/ia64/kvm/vcpu.c

@@ -1639,8 +1639,8 @@ void vcpu_set_psr(struct kvm_vcpu *vcpu, unsigned long val)
 	 * Otherwise panic
 	 */
 	if (val & (IA64_PSR_PK | IA64_PSR_IS | IA64_PSR_VM))
-		panic_vm(vcpu, "Only support guests with vpsr.pk =0 \
-				& vpsr.is=0\n");
+		panic_vm(vcpu, "Only support guests with vpsr.pk =0 "
+				"& vpsr.is=0\n");
 
 	/*
 	 * For those IA64_PSR bits: id/da/dd/ss/ed/ia

arch/powerpc/include/asm/kvm_asm.h

@@ -97,4 +97,10 @@
 #define RESUME_HOST             RESUME_FLAG_HOST
 #define RESUME_HOST_NV          (RESUME_FLAG_HOST|RESUME_FLAG_NV)
 
+#define KVM_GUEST_MODE_NONE	0
+#define KVM_GUEST_MODE_GUEST	1
+#define KVM_GUEST_MODE_SKIP	2
+
+#define KVM_INST_FETCH_FAILED	-1
+
 #endif /* __POWERPC_KVM_ASM_H__ */

arch/powerpc/include/asm/kvm_book3s.h

@@ -22,7 +22,7 @@
 
 #include <linux/types.h>
 #include <linux/kvm_host.h>
-#include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s_64_asm.h>
 
 struct kvmppc_slb {
 	u64 esid;
@@ -33,7 +33,8 @@ struct kvmppc_slb {
 	bool Ks;
 	bool Kp;
 	bool nx;
-	bool large;
+	bool large;	/* PTEs are 16MB */
+	bool tb;	/* 1TB segment */
 	bool class;
 };
 
@@ -69,6 +70,7 @@ struct kvmppc_sid_map {
 
 struct kvmppc_vcpu_book3s {
 	struct kvm_vcpu vcpu;
+	struct kvmppc_book3s_shadow_vcpu shadow_vcpu;
 	struct kvmppc_sid_map sid_map[SID_MAP_NUM];
 	struct kvmppc_slb slb[64];
 	struct {
@@ -89,6 +91,7 @@ struct kvmppc_vcpu_book3s {
 	u64 vsid_next;
 	u64 vsid_max;
 	int context_id;
+	ulong prog_flags; /* flags to inject when giving a 700 trap */
 };
 
 #define CONTEXT_HOST		0
@@ -119,6 +122,10 @@ extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat,
 
 extern u32 kvmppc_trampoline_lowmem;
 extern u32 kvmppc_trampoline_enter;
+extern void kvmppc_rmcall(ulong srr0, ulong srr1);
+extern void kvmppc_load_up_fpu(void);
+extern void kvmppc_load_up_altivec(void);
+extern void kvmppc_load_up_vsx(void);
 
 static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu)
 {