Merge branch 'for_paulus' of master.kernel.org:/pub/scm/linux/kernel/git/galak/powerpc into for-2.6.21

7 files changed, 151 insertions, 95 deletions

diff --git a/drivers/kvm/kvm.h b/drivers/kvm/kvm.h
index 91e0c75aca8..2db1ca4c680 100644
--- a/drivers/kvm/kvm.h
+++ b/drivers/kvm/kvm.h
@@ -242,6 +242,7 @@ struct kvm_vcpu {
 	u64 pdptrs[4]; /* pae */
 	u64 shadow_efer;
 	u64 apic_base;
+	u64 ia32_misc_enable_msr;
 	int nmsrs;
 	struct vmx_msr_entry *guest_msrs;
 	struct vmx_msr_entry *host_msrs;
diff --git a/drivers/kvm/kvm_main.c b/drivers/kvm/kvm_main.c
index 67c1154960f..b10972ed0c9 100644
--- a/drivers/kvm/kvm_main.c
+++ b/drivers/kvm/kvm_main.c
@@ -272,7 +272,9 @@ static void kvm_free_physmem(struct kvm *kvm)
 
 static void kvm_free_vcpu(struct kvm_vcpu *vcpu)
 {
+	vcpu_load(vcpu->kvm, vcpu_slot(vcpu));
 	kvm_mmu_destroy(vcpu);
+	vcpu_put(vcpu);
 	kvm_arch_ops->vcpu_free(vcpu);
 }
 
@@ -1224,6 +1226,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case MSR_IA32_APICBASE:
 		data = vcpu->apic_base;
 		break;
+	case MSR_IA32_MISC_ENABLE:
+		data = vcpu->ia32_misc_enable_msr;
+		break;
 #ifdef CONFIG_X86_64
 	case MSR_EFER:
 		data = vcpu->shadow_efer;
@@ -1295,6 +1300,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 	case MSR_IA32_APICBASE:
 		vcpu->apic_base = data;
 		break;
+	case MSR_IA32_MISC_ENABLE:
+		vcpu->ia32_misc_enable_msr = data;
+		break;
 	default:
 		printk(KERN_ERR "kvm: unhandled wrmsr: 0x%x\n", msr);
 		return 1;
@@ -1598,6 +1606,10 @@ static u32 msrs_to_save[] = {
 
 static unsigned num_msrs_to_save;
 
+static u32 emulated_msrs[] = {
+	MSR_IA32_MISC_ENABLE,
+};
+
 static __init void kvm_init_msr_list(void)
 {
 	u32 dummy[2];
@@ -1923,7 +1935,7 @@ static long kvm_dev_ioctl(struct file *filp,
 		if (copy_from_user(&msr_list, user_msr_list, sizeof msr_list))
 			goto out;
 		n = msr_list.nmsrs;
-		msr_list.nmsrs = num_msrs_to_save;
+		msr_list.nmsrs = num_msrs_to_save + ARRAY_SIZE(emulated_msrs);
 		if (copy_to_user(user_msr_list, &msr_list, sizeof msr_list))
 			goto out;
 		r = -E2BIG;
@@ -1933,6 +1945,11 @@ static long kvm_dev_ioctl(struct file *filp,
 		if (copy_to_user(user_msr_list->indices, &msrs_to_save,
 				 num_msrs_to_save * sizeof(u32)))
 			goto out;
+		if (copy_to_user(user_msr_list->indices
+				 + num_msrs_to_save * sizeof(u32),
+				 &emulated_msrs,
+				 ARRAY_SIZE(emulated_msrs) * sizeof(u32)))
+			goto out;
 		r = 0;
 		break;
 	}
diff --git a/drivers/kvm/mmu.c b/drivers/kvm/mmu.c
index c6f972914f0..22c426cd8cb 100644
--- a/drivers/kvm/mmu.c
+++ b/drivers/kvm/mmu.c
@@ -143,6 +143,7 @@ static int dbg = 1;
 #define PFERR_PRESENT_MASK (1U << 0)
 #define PFERR_WRITE_MASK (1U << 1)
 #define PFERR_USER_MASK (1U << 2)
+#define PFERR_FETCH_MASK (1U << 4)
 
 #define PT64_ROOT_LEVEL 4
 #define PT32_ROOT_LEVEL 2
@@ -168,6 +169,11 @@ static int is_cpuid_PSE36(void)
 	return 1;
 }
 
+static int is_nx(struct kvm_vcpu *vcpu)
+{
+	return vcpu->shadow_efer & EFER_NX;
+}
+
 static int is_present_pte(unsigned long pte)
 {
 	return pte & PT_PRESENT_MASK;
@@ -992,16 +998,6 @@ static inline int fix_read_pf(u64 *shadow_ent)
 	return 0;
 }
 
-static int may_access(u64 pte, int write, int user)
-{
-
-	if (user && !(pte & PT_USER_MASK))
-		return 0;
-	if (write && !(pte & PT_WRITABLE_MASK))
-		return 0;
-	return 1;
-}
-
 static void paging_free(struct kvm_vcpu *vcpu)
 {
 	nonpaging_free(vcpu);
diff --git a/drivers/kvm/paging_tmpl.h b/drivers/kvm/paging_tmpl.h
index 2dbf4307ed9..149fa45fd9a 100644
--- a/drivers/kvm/paging_tmpl.h
+++ b/drivers/kvm/paging_tmpl.h
@@ -63,13 +63,15 @@ struct guest_walker {
 	pt_element_t *ptep;
 	pt_element_t inherited_ar;
 	gfn_t gfn;
+	u32 error_code;
 };
 
 /*
  * Fetch a guest pte for a guest virtual address
  */
-static void FNAME(walk_addr)(struct guest_walker *walker,
-			     struct kvm_vcpu *vcpu, gva_t addr)
+static int FNAME(walk_addr)(struct guest_walker *walker,
+			    struct kvm_vcpu *vcpu, gva_t addr,
+			    int write_fault, int user_fault, int fetch_fault)
 {
 	hpa_t hpa;
 	struct kvm_memory_slot *slot;
@@ -86,7 +88,7 @@ static void FNAME(walk_addr)(struct guest_walker *walker,
 		walker->ptep = &vcpu->pdptrs[(addr >> 30) & 3];
 		root = *walker->ptep;
 		if (!(root & PT_PRESENT_MASK))
-			return;
+			goto not_present;
 		--walker->level;
 	}
 #endif
@@ -111,11 +113,23 @@ static void FNAME(walk_addr)(struct guest_walker *walker,
 		ASSERT(((unsigned long)walker->table & PAGE_MASK) ==
 		       ((unsigned long)ptep & PAGE_MASK));
 
-		if (is_present_pte(*ptep) && !(*ptep &  PT_ACCESSED_MASK))
-			*ptep |= PT_ACCESSED_MASK;
-
 		if (!is_present_pte(*ptep))
-			break;
+			goto not_present;
+
+		if (write_fault && !is_writeble_pte(*ptep))
+			if (user_fault || is_write_protection(vcpu))
+				goto access_error;
+
+		if (user_fault && !(*ptep & PT_USER_MASK))
+			goto access_error;
+
+#if PTTYPE == 64
+		if (fetch_fault && is_nx(vcpu) && (*ptep & PT64_NX_MASK))
+			goto access_error;
+#endif
+
+		if (!(*ptep & PT_ACCESSED_MASK))
+			*ptep |= PT_ACCESSED_MASK; 	/* avoid rmw */
 
 		if (walker->level == PT_PAGE_TABLE_LEVEL) {
 			walker->gfn = (*ptep & PT_BASE_ADDR_MASK)
@@ -146,6 +160,23 @@ static void FNAME(walk_addr)(struct guest_walker *walker,
 	}
 	walker->ptep = ptep;
 	pgprintk("%s: pte %llx\n", __FUNCTION__, (u64)*ptep);
+	return 1;
+
+not_present:
+	walker->error_code = 0;
+	goto err;
+
+access_error:
+	walker->error_code = PFERR_PRESENT_MASK;
+
+err:
+	if (write_fault)
+		walker->error_code |= PFERR_WRITE_MASK;
+	if (user_fault)
+		walker->error_code |= PFERR_USER_MASK;
+	if (fetch_fault)
+		walker->error_code |= PFERR_FETCH_MASK;
+	return 0;
 }
 
 static void FNAME(release_walker)(struct guest_walker *walker)
@@ -274,7 +305,7 @@ static int FNAME(fix_write_pf)(struct kvm_vcpu *vcpu,
 	struct kvm_mmu_page *page;
 
 	if (is_writeble_pte(*shadow_ent))
-		return 0;
+		return !user || (*shadow_ent & PT_USER_MASK);
 
 	writable_shadow = *shadow_ent & PT_SHADOW_WRITABLE_MASK;
 	if (user) {
@@ -347,8 +378,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
 			       u32 error_code)
 {
 	int write_fault = error_code & PFERR_WRITE_MASK;
-	int pte_present = error_code & PFERR_PRESENT_MASK;
 	int user_fault = error_code & PFERR_USER_MASK;
+	int fetch_fault = error_code & PFERR_FETCH_MASK;
 	struct guest_walker walker;
 	u64 *shadow_pte;
 	int fixed;
@@ -365,19 +396,20 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
 	/*
 	 * Look up the shadow pte for the faulting address.
 	 */
-	FNAME(walk_addr)(&walker, vcpu, addr);
-	shadow_pte = FNAME(fetch)(vcpu, addr, &walker);
+	r = FNAME(walk_addr)(&walker, vcpu, addr, write_fault, user_fault,
+			     fetch_fault);
 
 	/*
 	 * The page is not mapped by the guest.  Let the guest handle it.
 	 */
-	if (!shadow_pte) {
-		pgprintk("%s: not mapped\n", __FUNCTION__);
-		inject_page_fault(vcpu, addr, error_code);
+	if (!r) {
+		pgprintk("%s: guest page fault\n", __FUNCTION__);
+		inject_page_fault(vcpu, addr, walker.error_code);
 		FNAME(release_walker)(&walker);
 		return 0;
 	}
 
+	shadow_pte = FNAME(fetch)(vcpu, addr, &walker);
 	pgprintk("%s: shadow pte %p %llx\n", __FUNCTION__,
 		 shadow_pte, *shadow_pte);
 
@@ -399,22 +431,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
 	 * mmio: emulate if accessible, otherwise its a guest fault.
 	 */
 	if (is_io_pte(*shadow_pte)) {
-		if (may_access(*shadow_pte, write_fault, user_fault))
-			return 1;
-		pgprintk("%s: io work, no access\n", __FUNCTION__);
-		inject_page_fault(vcpu, addr,
-				  error_code | PFERR_PRESENT_MASK);
-		kvm_mmu_audit(vcpu, "post page fault (io)");
-		return 0;
-	}
-
-	/*
-	 * pte not present, guest page fault.
-	 */
-	if (pte_present && !fixed && !write_pt) {
-		inject_page_fault(vcpu, addr, error_code);
-		kvm_mmu_audit(vcpu, "post page fault (guest)");
-		return 0;
+		return 1;
 	}
 
 	++kvm_stat.pf_fixed;
@@ -429,7 +446,7 @@ static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr)
 	pt_element_t guest_pte;
 	gpa_t gpa;
 
-	FNAME(walk_addr)(&walker, vcpu, vaddr);
+	FNAME(walk_addr)(&walker, vcpu, vaddr, 0, 0, 0);
 	guest_pte = *walker.ptep;
 	FNAME(release_walker)(&walker);
 
diff --git a/drivers/kvm/svm.c b/drivers/kvm/svm.c
index 714f6a7841c..c79df79307e 100644
--- a/drivers/kvm/svm.c
+++ b/drivers/kvm/svm.c
@@ -502,6 +502,7 @@ static void init_vmcb(struct vmcb *vmcb)
 				(1ULL << INTERCEPT_IOIO_PROT) |
 				(1ULL << INTERCEPT_MSR_PROT) |
 				(1ULL << INTERCEPT_TASK_SWITCH) |
+				(1ULL << INTERCEPT_SHUTDOWN) |
 				(1ULL << INTERCEPT_VMRUN) |
 				(1ULL << INTERCEPT_VMMCALL) |
 				(1ULL << INTERCEPT_VMLOAD) |
@@ -680,14 +681,14 @@ static void svm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
 
 static void svm_get_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
 {
-	dt->limit = vcpu->svm->vmcb->save.ldtr.limit;
-	dt->base = vcpu->svm->vmcb->save.ldtr.base;
+	dt->limit = vcpu->svm->vmcb->save.idtr.limit;
+	dt->base = vcpu->svm->vmcb->save.idtr.base;
 }
 
 static void svm_set_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
 {
-	vcpu->svm->vmcb->save.ldtr.limit = dt->limit;
-	vcpu->svm->vmcb->save.ldtr.base = dt->base ;
+	vcpu->svm->vmcb->save.idtr.limit = dt->limit;
+	vcpu->svm->vmcb->save.idtr.base = dt->base ;
 }
 
 static void svm_get_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
@@ -892,6 +893,19 @@ static int pf_interception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	return 0;
 }
 
+static int shutdown_interception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+	/*
+	 * VMCB is undefined after a SHUTDOWN intercept
+	 * so reinitialize it.
+	 */
+	memset(vcpu->svm->vmcb, 0, PAGE_SIZE);
+	init_vmcb(vcpu->svm->vmcb);
+
+	kvm_run->exit_reason = KVM_EXIT_SHUTDOWN;
+	return 0;
+}
+
 static int io_get_override(struct kvm_vcpu *vcpu,
 			  struct vmcb_seg **seg,
 			  int *addr_override)
@@ -1149,7 +1163,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data)
 	case MSR_K6_STAR:
 		vcpu->svm->vmcb->save.star = data;
 		break;
-#ifdef CONFIG_X86_64_
+#ifdef CONFIG_X86_64
 	case MSR_LSTAR:
 		vcpu->svm->vmcb->save.lstar = data;
 		break;
@@ -1249,6 +1263,7 @@ static int (*svm_exit_handlers[])(struct kvm_vcpu *vcpu,
 	[SVM_EXIT_IOIO] 		  	= io_interception,
 	[SVM_EXIT_MSR]				= msr_interception,
 	[SVM_EXIT_TASK_SWITCH]			= task_switch_interception,
+	[SVM_EXIT_SHUTDOWN]			= shutdown_interception,
 	[SVM_EXIT_VMRUN]			= invalid_op_interception,
 	[SVM_EXIT_VMMCALL]			= invalid_op_interception,
 	[SVM_EXIT_VMLOAD]			= invalid_op_interception,
@@ -1407,7 +1422,8 @@ static int svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	int r;
 
 again:
-	do_interrupt_requests(vcpu, kvm_run);
+	if (!vcpu->mmio_read_completed)
+		do_interrupt_requests(vcpu, kvm_run);
 
 	clgi();
 
diff --git a/drivers/kvm/vmx.c b/drivers/kvm/vmx.c
index 0aa2659f6ae..54c35c0b318 100644
--- a/drivers/kvm/vmx.c
+++ b/drivers/kvm/vmx.c
@@ -1116,6 +1116,8 @@ static int vmx_vcpu_setup(struct kvm_vcpu *vcpu)
 
 		if (rdmsr_safe(index, &data_low, &data_high) < 0)
 			continue;
+		if (wrmsr_safe(index, data_low, data_high) < 0)
+			continue;
 		data = data_low | ((u64)data_high << 32);
 		vcpu->host_msrs[j].index = index;
 		vcpu->host_msrs[j].reserved = 0;
@@ -1717,7 +1719,8 @@ again:
 	vmcs_writel(HOST_GS_BASE, segment_base(gs_sel));
 #endif
 
-	do_interrupt_requests(vcpu, kvm_run);
+	if (!vcpu->mmio_read_completed)
+		do_interrupt_requests(vcpu, kvm_run);
 
 	if (vcpu->guest_debug.enabled)
 		kvm_guest_debug_pre(vcpu);
diff --git a/drivers/kvm/x86_emulate.c b/drivers/kvm/x86_emulate.c
index be70795b482..7513cddb929 100644
--- a/drivers/kvm/x86_emulate.c
+++ b/drivers/kvm/x86_emulate.c
@@ -61,6 +61,7 @@
 #define ModRM       (1<<6)
 /* Destination is only written; never read. */
 #define Mov         (1<<7)
+#define BitOp       (1<<8)
 
 static u8 opcode_table[256] = {
 	/* 0x00 - 0x07 */
@@ -148,7 +149,7 @@ static u8 opcode_table[256] = {
 	0, 0, ByteOp | DstMem | SrcNone | ModRM, DstMem | SrcNone | ModRM
 };
 
-static u8 twobyte_table[256] = {
+static u16 twobyte_table[256] = {
 	/* 0x00 - 0x0F */
 	0, SrcMem | ModRM | DstReg, 0, 0, 0, 0, ImplicitOps, 0,
 	0, 0, 0, 0, 0, ImplicitOps | ModRM, 0, 0,
@@ -180,16 +181,16 @@ static u8 twobyte_table[256] = {
 	/* 0x90 - 0x9F */
 	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
 	/* 0xA0 - 0xA7 */
-	0, 0, 0, DstMem | SrcReg | ModRM, 0, 0, 0, 0,
+	0, 0, 0, DstMem | SrcReg | ModRM | BitOp, 0, 0, 0, 0,
 	/* 0xA8 - 0xAF */
-	0, 0, 0, DstMem | SrcReg | ModRM, 0, 0, 0, 0,
+	0, 0, 0, DstMem | SrcReg | ModRM | BitOp, 0, 0, 0, 0,
 	/* 0xB0 - 0xB7 */
 	ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, 0,
-	    DstMem | SrcReg | ModRM,
+	    DstMem | SrcReg | ModRM | BitOp,
 	0, 0, ByteOp | DstReg | SrcMem | ModRM | Mov,
 	    DstReg | SrcMem16 | ModRM | Mov,
 	/* 0xB8 - 0xBF */
-	0, 0, DstMem | SrcImmByte | ModRM, DstMem | SrcReg | ModRM,
+	0, 0, DstMem | SrcImmByte | ModRM, DstMem | SrcReg | ModRM | BitOp,
 	0, 0, ByteOp | DstReg | SrcMem | ModRM | Mov,
 	    DstReg | SrcMem16 | ModRM | Mov,
 	/* 0xC0 - 0xCF */
@@ -469,7 +470,8 @@ static int read_descriptor(struct x86_emulate_ctxt *ctxt,
 int
 x86_emulate_memop(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 {
-	u8 b, d, sib, twobyte = 0, rex_prefix = 0;
+	unsigned d;
+	u8 b, sib, twobyte = 0, rex_prefix = 0;
 	u8 modrm, modrm_mod = 0, modrm_reg = 0, modrm_rm = 0;
 	unsigned long *override_base = NULL;
 	unsigned int op_bytes, ad_bytes, lock_prefix = 0, rep_prefix = 0, i;
@@ -726,46 +728,6 @@ done_prefixes:
 		;
 	}
 
-	/* Decode and fetch the destination operand: register or memory. */
-	switch (d & DstMask) {
-	case ImplicitOps:
-		/* Special instructions do their own operand decoding. */
-		goto special_insn;
-	case DstReg:
-		dst.type = OP_REG;
-		if ((d & ByteOp)
-		    && !(twobyte_table && (b == 0xb6 || b == 0xb7))) {
-			dst.ptr = decode_register(modrm_reg, _regs,
-						  (rex_prefix == 0));
-			dst.val = *(u8 *) dst.ptr;
-			dst.bytes = 1;
-		} else {
-			dst.ptr = decode_register(modrm_reg, _regs, 0);
-			switch ((dst.bytes = op_bytes)) {
-			case 2:
-				dst.val = *(u16 *)dst.ptr;
-				break;
-			case 4:
-				dst.val = *(u32 *)dst.ptr;
-				break;
-			case 8:
-				dst.val = *(u64 *)dst.ptr;
-				break;
-			}
-		}
-		break;
-	case DstMem:
-		dst.type = OP_MEM;
-		dst.ptr = (unsigned long *)cr2;
-		dst.bytes = (d & ByteOp) ? 1 : op_bytes;
-		if (!(d & Mov) && /* optimisation - avoid slow emulated read */
-		    ((rc = ops->read_emulated((unsigned long)dst.ptr,
-					      &dst.val, dst.bytes, ctxt)) != 0))
-			goto done;
-		break;
-	}
-	dst.orig_val = dst.val;
-
 	/*
 	 * Decode and fetch the source operand: register, memory
 	 * or immediate.
@@ -838,6 +800,50 @@ done_prefixes:
 		break;
 	}
 
+	/* Decode and fetch the destination operand: register or memory. */
+	switch (d & DstMask) {
+	case ImplicitOps:
+		/* Special instructions do their own operand decoding. */
+		goto special_insn;
+	case DstReg:
+		dst.type = OP_REG;
+		if ((d & ByteOp)
+		    && !(twobyte_table && (b == 0xb6 || b == 0xb7))) {
+			dst.ptr = decode_register(modrm_reg, _regs,
+						  (rex_prefix == 0));
+			dst.val = *(u8 *) dst.ptr;
+			dst.bytes = 1;
+		} else {
+			dst.ptr = decode_register(modrm_reg, _regs, 0);
+			switch ((dst.bytes = op_bytes)) {
+			case 2:
+				dst.val = *(u16 *)dst.ptr;
+				break;
+			case 4:
+				dst.val = *(u32 *)dst.ptr;
+				break;
+			case 8:
+				dst.val = *(u64 *)dst.ptr;
+				break;
+			}
+		}
+		break;
+	case DstMem:
+		dst.type = OP_MEM;
+		dst.ptr = (unsigned long *)cr2;
+		dst.bytes = (d & ByteOp) ? 1 : op_bytes;
+		if (d & BitOp) {
+			dst.ptr += src.val / BITS_PER_LONG;
+			dst.bytes = sizeof(long);
+		}
+		if (!(d & Mov) && /* optimisation - avoid slow emulated read */
+		    ((rc = ops->read_emulated((unsigned long)dst.ptr,
+					      &dst.val, dst.bytes, ctxt)) != 0))
+			goto done;
+		break;
+	}
+	dst.orig_val = dst.val;
+
 	if (twobyte)
 		goto twobyte_insn;