From d27d4aca184ac0ca6b7e32caf79e1c2b91959be9 Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi@qumranet.com>
Date: Mon, 19 Feb 2007 14:37:46 +0200
Subject: KVM: Cosmetics

Signed-off-by: Avi Kivity <avi@qumranet.com>
---
 drivers/kvm/svm.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'drivers/kvm/svm.c')

diff --git a/drivers/kvm/svm.c b/drivers/kvm/svm.c
index 83da4ea150a3..31836444bc62 100644
--- a/drivers/kvm/svm.c
+++ b/drivers/kvm/svm.c
@@ -1042,22 +1042,22 @@ static int io_interception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 		addr_mask = io_adress(vcpu, _in, &kvm_run->io.address);
 		if (!addr_mask) {
-			printk(KERN_DEBUG "%s: get io address failed\n", __FUNCTION__);
+			printk(KERN_DEBUG "%s: get io address failed\n",
+			       __FUNCTION__);
 			return 1;
 		}
 
 		if (kvm_run->io.rep) {
-			kvm_run->io.count = vcpu->regs[VCPU_REGS_RCX] & addr_mask;
+			kvm_run->io.count
+				= vcpu->regs[VCPU_REGS_RCX] & addr_mask;
 			kvm_run->io.string_down = (vcpu->svm->vmcb->save.rflags
 						   & X86_EFLAGS_DF) != 0;
 		}
-	} else {
+	} else
 		kvm_run->io.value = vcpu->svm->vmcb->save.rax;
-	}
 	return 0;
 }
 
-
 static int nop_on_interception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	return 1;
-- 
cgit v1.2.3


From 9d8f549dc69b1fc65d0b03916c02f12ca49b3ea0 Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <darwish.07@gmail.com>
Date: Mon, 19 Feb 2007 14:37:46 +0200
Subject: KVM: Use ARRAY_SIZE macro instead of manual calculation.

Signed-off-by: Ahmed S. Darwish <darwish.07@gmail.com>
Signed-off-by: Dor Laor <dor.laor@qumranet.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
---
 drivers/kvm/kvm_svm.h | 3 ++-
 drivers/kvm/svm.c     | 5 +++--
 drivers/kvm/vmx.c     | 3 ++-
 3 files changed, 7 insertions(+), 4 deletions(-)

(limited to 'drivers/kvm/svm.c')

diff --git a/drivers/kvm/kvm_svm.h b/drivers/kvm/kvm_svm.h
index 74cc862f4935..624f1ca48657 100644
--- a/drivers/kvm/kvm_svm.h
+++ b/drivers/kvm/kvm_svm.h
@@ -1,6 +1,7 @@
 #ifndef __KVM_SVM_H
 #define __KVM_SVM_H
 
+#include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/list.h>
 #include <asm/msr.h>
@@ -18,7 +19,7 @@ static const u32 host_save_msrs[] = {
 	MSR_IA32_LASTBRANCHTOIP, MSR_IA32_LASTINTFROMIP,MSR_IA32_LASTINTTOIP,*/
 };
 
-#define NR_HOST_SAVE_MSRS (sizeof(host_save_msrs) / sizeof(*host_save_msrs))
+#define NR_HOST_SAVE_MSRS ARRAY_SIZE(host_save_msrs)
 #define NUM_DB_REGS 4
 
 struct vcpu_svm {
diff --git a/drivers/kvm/svm.c b/drivers/kvm/svm.c
index 31836444bc62..72cac0488b31 100644
--- a/drivers/kvm/svm.c
+++ b/drivers/kvm/svm.c
@@ -15,6 +15,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/kernel.h>
 #include <linux/vmalloc.h>
 #include <linux/highmem.h>
 #include <linux/profile.h>
@@ -75,7 +76,7 @@ struct svm_init_data {
 
 static u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000};
 
-#define NUM_MSR_MAPS (sizeof(msrpm_ranges) / sizeof(*msrpm_ranges))
+#define NUM_MSR_MAPS ARRAY_SIZE(msrpm_ranges)
 #define MSRS_RANGE_SIZE 2048
 #define MSRS_IN_RANGE (MSRS_RANGE_SIZE * 8 / 2)
 
@@ -1297,7 +1298,7 @@ static int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		       __FUNCTION__, vcpu->svm->vmcb->control.exit_int_info,
 		       exit_code);
 
-	if (exit_code >= sizeof(svm_exit_handlers) / sizeof(*svm_exit_handlers)
+	if (exit_code >= ARRAY_SIZE(svm_exit_handlers)
 	    || svm_exit_handlers[exit_code] == 0) {
 		kvm_run->exit_reason = KVM_EXIT_UNKNOWN;
 		printk(KERN_ERR "%s: 0x%x @ 0x%llx cr0 0x%lx rflags 0x%llx\n",
diff --git a/drivers/kvm/vmx.c b/drivers/kvm/vmx.c
index e02c59807a7e..d1198e2b2b5d 100644
--- a/drivers/kvm/vmx.c
+++ b/drivers/kvm/vmx.c
@@ -19,6 +19,7 @@
 #include "vmx.h"
 #include "kvm_vmx.h"
 #include <linux/module.h>
+#include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/highmem.h>
 #include <linux/profile.h>
@@ -75,7 +76,7 @@ static const u32 vmx_msr_index[] = {
 #endif
 	MSR_EFER, MSR_K6_STAR,
 };
-#define NR_VMX_MSR (sizeof(vmx_msr_index) / sizeof(*vmx_msr_index))
+#define NR_VMX_MSR ARRAY_SIZE(vmx_msr_index)
 
 static inline int is_page_fault(u32 intr_info)
 {
-- 
cgit v1.2.3


From 102d8325a1d2f266d3d0a03fdde948544e72c12d Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Mon, 19 Feb 2007 14:37:47 +0200
Subject: KVM: add MSR based hypercall API

This adds a special MSR based hypercall API to KVM. This is to be
used by paravirtual kernels and virtual drivers.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Avi Kivity <avi@qumranet.com>
---
 drivers/kvm/kvm.h        |  6 ++++
 drivers/kvm/kvm_main.c   | 73 ++++++++++++++++++++++++++++++++++++++++++++++++
 drivers/kvm/svm.c        | 13 +++++++++
 drivers/kvm/vmx.c        | 13 +++++++++
 include/linux/kvm_para.h | 55 ++++++++++++++++++++++++++++++++++++
 5 files changed, 160 insertions(+)
 create mode 100644 include/linux/kvm_para.h

(limited to 'drivers/kvm/svm.c')

diff --git a/drivers/kvm/kvm.h b/drivers/kvm/kvm.h
index 9a49b2ed2a1e..fd7746a2bc3e 100644
--- a/drivers/kvm/kvm.h
+++ b/drivers/kvm/kvm.h
@@ -14,6 +14,7 @@
 
 #include "vmx.h"
 #include <linux/kvm.h>
+#include <linux/kvm_para.h>
 
 #define CR0_PE_MASK (1ULL << 0)
 #define CR0_TS_MASK (1ULL << 3)
@@ -237,6 +238,9 @@ struct kvm_vcpu {
 	unsigned long cr0;
 	unsigned long cr2;
 	unsigned long cr3;
+	gpa_t para_state_gpa;
+	struct page *para_state_page;
+	gpa_t hypercall_gpa;
 	unsigned long cr4;
 	unsigned long cr8;
 	u64 pdptrs[4]; /* pae */
@@ -382,6 +386,8 @@ struct kvm_arch_ops {
 	int (*run)(struct kvm_vcpu *vcpu, struct kvm_run *run);
 	int (*vcpu_setup)(struct kvm_vcpu *vcpu);
 	void (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
+	void (*patch_hypercall)(struct kvm_vcpu *vcpu,
+				unsigned char *hypercall_addr);
 };
 
 extern struct kvm_stat kvm_stat;
diff --git a/drivers/kvm/kvm_main.c b/drivers/kvm/kvm_main.c
index 122c05f283e1..757a41f1db84 100644
--- a/drivers/kvm/kvm_main.c
+++ b/drivers/kvm/kvm_main.c
@@ -1204,6 +1204,73 @@ void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val,
 	}
 }
 
+/*
+ * Register the para guest with the host:
+ */
+static int vcpu_register_para(struct kvm_vcpu *vcpu, gpa_t para_state_gpa)
+{
+	struct kvm_vcpu_para_state *para_state;
+	hpa_t para_state_hpa, hypercall_hpa;
+	struct page *para_state_page;
+	unsigned char *hypercall;
+	gpa_t hypercall_gpa;
+
+	printk(KERN_DEBUG "kvm: guest trying to enter paravirtual mode\n");
+	printk(KERN_DEBUG ".... para_state_gpa: %08Lx\n", para_state_gpa);
+
+	/*
+	 * Needs to be page aligned:
+	 */
+	if (para_state_gpa != PAGE_ALIGN(para_state_gpa))
+		goto err_gp;
+
+	para_state_hpa = gpa_to_hpa(vcpu, para_state_gpa);
+	printk(KERN_DEBUG ".... para_state_hpa: %08Lx\n", para_state_hpa);
+	if (is_error_hpa(para_state_hpa))
+		goto err_gp;
+
+	para_state_page = pfn_to_page(para_state_hpa >> PAGE_SHIFT);
+	para_state = kmap_atomic(para_state_page, KM_USER0);
+
+	printk(KERN_DEBUG "....  guest version: %d\n", para_state->guest_version);
+	printk(KERN_DEBUG "....           size: %d\n", para_state->size);
+
+	para_state->host_version = KVM_PARA_API_VERSION;
+	/*
+	 * We cannot support guests that try to register themselves
+	 * with a newer API version than the host supports:
+	 */
+	if (para_state->guest_version > KVM_PARA_API_VERSION) {
+		para_state->ret = -KVM_EINVAL;
+		goto err_kunmap_skip;
+	}
+
+	hypercall_gpa = para_state->hypercall_gpa;
+	hypercall_hpa = gpa_to_hpa(vcpu, hypercall_gpa);
+	printk(KERN_DEBUG ".... hypercall_hpa: %08Lx\n", hypercall_hpa);
+	if (is_error_hpa(hypercall_hpa)) {
+		para_state->ret = -KVM_EINVAL;
+		goto err_kunmap_skip;
+	}
+
+	printk(KERN_DEBUG "kvm: para guest successfully registered.\n");
+	vcpu->para_state_page = para_state_page;
+	vcpu->para_state_gpa = para_state_gpa;
+	vcpu->hypercall_gpa = hypercall_gpa;
+
+	hypercall = kmap_atomic(pfn_to_page(hypercall_hpa >> PAGE_SHIFT),
+				KM_USER1) + (hypercall_hpa & ~PAGE_MASK);
+	kvm_arch_ops->patch_hypercall(vcpu, hypercall);
+	kunmap_atomic(hypercall, KM_USER1);
+
+	para_state->ret = 0;
+err_kunmap_skip:
+	kunmap_atomic(para_state, KM_USER0);
+	return 0;
+err_gp:
+	return 1;
+}
+
 int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 {
 	u64 data;
@@ -1312,6 +1379,12 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 	case MSR_IA32_MISC_ENABLE:
 		vcpu->ia32_misc_enable_msr = data;
 		break;
+	/*
+	 * This is the 'probe whether the host is KVM' logic:
+	 */
+	case MSR_KVM_API_MAGIC:
+		return vcpu_register_para(vcpu, data);
+
 	default:
 		printk(KERN_ERR "kvm: unhandled wrmsr: 0x%x\n", msr);
 		return 1;
diff --git a/drivers/kvm/svm.c b/drivers/kvm/svm.c
index 72cac0488b31..f6e86528f031 100644
--- a/drivers/kvm/svm.c
+++ b/drivers/kvm/svm.c
@@ -1669,6 +1669,18 @@ static int is_disabled(void)
 	return 0;
 }
 
+static void
+svm_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall)
+{
+	/*
+	 * Patch in the VMMCALL instruction:
+	 */
+	hypercall[0] = 0x0f;
+	hypercall[1] = 0x01;
+	hypercall[2] = 0xd9;
+	hypercall[3] = 0xc3;
+}
+
 static struct kvm_arch_ops svm_arch_ops = {
 	.cpu_has_kvm_support = has_svm,
 	.disabled_by_bios = is_disabled,
@@ -1717,6 +1729,7 @@ static struct kvm_arch_ops svm_arch_ops = {
 	.run = svm_vcpu_run,
 	.skip_emulated_instruction = skip_emulated_instruction,
 	.vcpu_setup = svm_vcpu_setup,
+	.patch_hypercall = svm_patch_hypercall,
 };
 
 static int __init svm_init(void)
diff --git a/drivers/kvm/vmx.c b/drivers/kvm/vmx.c
index d1198e2b2b5d..0198d400037f 100644
--- a/drivers/kvm/vmx.c
+++ b/drivers/kvm/vmx.c
@@ -1469,6 +1469,18 @@ static int handle_io(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	return 0;
 }
 
+static void
+vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall)
+{
+	/*
+	 * Patch in the VMCALL instruction:
+	 */
+	hypercall[0] = 0x0f;
+	hypercall[1] = 0x01;
+	hypercall[2] = 0xc1;
+	hypercall[3] = 0xc3;
+}
+
 static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	u64 exit_qualification;
@@ -2064,6 +2076,7 @@ static struct kvm_arch_ops vmx_arch_ops = {
 	.run = vmx_vcpu_run,
 	.skip_emulated_instruction = skip_emulated_instruction,
 	.vcpu_setup = vmx_vcpu_setup,
+	.patch_hypercall = vmx_patch_hypercall,
 };
 
 static int __init vmx_init(void)
diff --git a/include/linux/kvm_para.h b/include/linux/kvm_para.h
new file mode 100644
index 000000000000..74be5c1002ec
--- /dev/null
+++ b/include/linux/kvm_para.h
@@ -0,0 +1,55 @@
+#ifndef __LINUX_KVM_PARA_H
+#define __LINUX_KVM_PARA_H
+
+/*
+ * Guest OS interface for KVM paravirtualization
+ *
+ * Note: this interface is totally experimental, and is certain to change
+ *       as we make progress.
+ */
+
+/*
+ * Per-VCPU descriptor area shared between guest and host. Writable to
+ * both guest and host. Registered with the host by the guest when
+ * a guest acknowledges paravirtual mode.
+ *
+ * NOTE: all addresses are guest-physical addresses (gpa), to make it
+ * easier for the hypervisor to map between the various addresses.
+ */
+struct kvm_vcpu_para_state {
+	/*
+	 * API version information for compatibility. If there's any support
+	 * mismatch (too old host trying to execute too new guest) then
+	 * the host will deny entry into paravirtual mode. Any other
+	 * combination (new host + old guest and new host + new guest)
+	 * is supposed to work - new host versions will support all old
+	 * guest API versions.
+	 */
+	u32 guest_version;
+	u32 host_version;
+	u32 size;
+	u32 ret;
+
+	/*
+	 * The address of the vm exit instruction (VMCALL or VMMCALL),
+	 * which the host will patch according to the CPU model the
+	 * VM runs on:
+	 */
+	u64 hypercall_gpa;
+
+} __attribute__ ((aligned(PAGE_SIZE)));
+
+#define KVM_PARA_API_VERSION 1
+
+/*
+ * This is used for an RDMSR's ECX parameter to probe for a KVM host.
+ * Hopefully no CPU vendor will use up this number. This is placed well
+ * out of way of the typical space occupied by CPU vendors' MSR indices,
+ * and we think (or at least hope) it wont be occupied in the future
+ * either.
+ */
+#define MSR_KVM_API_MAGIC 0x87655678
+
+#define KVM_EINVAL 1
+
+#endif
-- 
cgit v1.2.3


From 02e235bc8eebf8a6fef10d46479b3c18f3e9c4f2 Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi@qumranet.com>
Date: Mon, 19 Feb 2007 14:37:47 +0200
Subject: KVM: Add hypercall host support for svm

Signed-off-by: Avi Kivity <avi@qumranet.com>
---
 drivers/kvm/svm.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

(limited to 'drivers/kvm/svm.c')

diff --git a/drivers/kvm/svm.c b/drivers/kvm/svm.c
index f6e86528f031..aaa6742089e5 100644
--- a/drivers/kvm/svm.c
+++ b/drivers/kvm/svm.c
@@ -1076,6 +1076,20 @@ static int halt_interception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	return 0;
 }
 
+static int vmmcall_interception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+	printk(KERN_DEBUG "got vmmcall at RIP %08llx\n",
+	       vcpu->svm->vmcb->save.rip);
+	printk(KERN_DEBUG "vmmcall params: %08llx, %08lx, %08lx, %08lx\n",
+	       vcpu->svm->vmcb->save.rax,
+	       vcpu->regs[VCPU_REGS_RCX],
+	       vcpu->regs[VCPU_REGS_RDX],
+	       vcpu->regs[VCPU_REGS_RBP]);
+	vcpu->svm->vmcb->save.rax = 0;
+	vcpu->svm->vmcb->save.rip += 3;
+	return 1;
+}
+
 static int invalid_op_interception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	inject_ud(vcpu);
@@ -1276,7 +1290,7 @@ static int (*svm_exit_handlers[])(struct kvm_vcpu *vcpu,
 	[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_VMMCALL]			= vmmcall_interception,
 	[SVM_EXIT_VMLOAD]			= invalid_op_interception,
 	[SVM_EXIT_VMSAVE]			= invalid_op_interception,
 	[SVM_EXIT_STGI]				= invalid_op_interception,
-- 
cgit v1.2.3


From 270fd9b96f5fcb7df15d3ca6166545d4aa0f3ee9 Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi@qumranet.com>
Date: Mon, 19 Feb 2007 14:37:47 +0200
Subject: KVM: Wire up hypercall handlers to a central arch-independent
 location

Signed-off-by: Avi Kivity <avi@qumranet.com>
---
 drivers/kvm/kvm.h      |  2 ++
 drivers/kvm/kvm_main.c | 36 ++++++++++++++++++++++++++++++++++++
 drivers/kvm/svm.c      | 10 +---------
 drivers/kvm/vmx.c      | 10 +---------
 4 files changed, 40 insertions(+), 18 deletions(-)

(limited to 'drivers/kvm/svm.c')

diff --git a/drivers/kvm/kvm.h b/drivers/kvm/kvm.h
index fd7746a2bc3e..41cc27de4d66 100644
--- a/drivers/kvm/kvm.h
+++ b/drivers/kvm/kvm.h
@@ -482,6 +482,8 @@ void kvm_mmu_post_write(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes);
 int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva);
 void kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
 
+int kvm_hypercall(struct kvm_vcpu *vcpu, struct kvm_run *run);
+
 static inline int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
 				     u32 error_code)
 {
diff --git a/drivers/kvm/kvm_main.c b/drivers/kvm/kvm_main.c
index 757a41f1db84..2be9738dfd78 100644
--- a/drivers/kvm/kvm_main.c
+++ b/drivers/kvm/kvm_main.c
@@ -1138,6 +1138,42 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 }
 EXPORT_SYMBOL_GPL(emulate_instruction);
 
+int kvm_hypercall(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	unsigned long nr, a0, a1, a2, a3, a4, a5, ret;
+
+	kvm_arch_ops->decache_regs(vcpu);
+	ret = -KVM_EINVAL;
+#ifdef CONFIG_X86_64
+	if (is_long_mode(vcpu)) {
+		nr = vcpu->regs[VCPU_REGS_RAX];
+		a0 = vcpu->regs[VCPU_REGS_RDI];
+		a1 = vcpu->regs[VCPU_REGS_RSI];
+		a2 = vcpu->regs[VCPU_REGS_RDX];
+		a3 = vcpu->regs[VCPU_REGS_RCX];
+		a4 = vcpu->regs[VCPU_REGS_R8];
+		a5 = vcpu->regs[VCPU_REGS_R9];
+	} else
+#endif
+	{
+		nr = vcpu->regs[VCPU_REGS_RBX] & -1u;
+		a0 = vcpu->regs[VCPU_REGS_RAX] & -1u;
+		a1 = vcpu->regs[VCPU_REGS_RCX] & -1u;
+		a2 = vcpu->regs[VCPU_REGS_RDX] & -1u;
+		a3 = vcpu->regs[VCPU_REGS_RSI] & -1u;
+		a4 = vcpu->regs[VCPU_REGS_RDI] & -1u;
+		a5 = vcpu->regs[VCPU_REGS_RBP] & -1u;
+	}
+	switch (nr) {
+	default:
+		;
+	}
+	vcpu->regs[VCPU_REGS_RAX] = ret;
+	kvm_arch_ops->cache_regs(vcpu);
+	return 1;
+}
+EXPORT_SYMBOL_GPL(kvm_hypercall);
+
 static u64 mk_cr_64(u64 curr_cr, u32 new_val)
 {
 	return (curr_cr & ~((1ULL << 32) - 1)) | new_val;
diff --git a/drivers/kvm/svm.c b/drivers/kvm/svm.c
index aaa6742089e5..711ea42370a8 100644
--- a/drivers/kvm/svm.c
+++ b/drivers/kvm/svm.c
@@ -1078,16 +1078,8 @@ static int halt_interception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 static int vmmcall_interception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
-	printk(KERN_DEBUG "got vmmcall at RIP %08llx\n",
-	       vcpu->svm->vmcb->save.rip);
-	printk(KERN_DEBUG "vmmcall params: %08llx, %08lx, %08lx, %08lx\n",
-	       vcpu->svm->vmcb->save.rax,
-	       vcpu->regs[VCPU_REGS_RCX],
-	       vcpu->regs[VCPU_REGS_RDX],
-	       vcpu->regs[VCPU_REGS_RBP]);
-	vcpu->svm->vmcb->save.rax = 0;
 	vcpu->svm->vmcb->save.rip += 3;
-	return 1;
+	return kvm_hypercall(vcpu, kvm_run);
 }
 
 static int invalid_op_interception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
diff --git a/drivers/kvm/vmx.c b/drivers/kvm/vmx.c
index ca79e594ea6e..ff956a6302ec 100644
--- a/drivers/kvm/vmx.c
+++ b/drivers/kvm/vmx.c
@@ -1659,16 +1659,8 @@ static int handle_halt(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 static int handle_vmcall(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
-	kvm_run->exit_reason = KVM_EXIT_DEBUG;
-	printk(KERN_DEBUG "got vmcall at RIP %08lx\n", vmcs_readl(GUEST_RIP));
-	printk(KERN_DEBUG "vmcall params: %08lx, %08lx, %08lx, %08lx\n",
-		vcpu->regs[VCPU_REGS_RAX],
-		vcpu->regs[VCPU_REGS_RCX],
-		vcpu->regs[VCPU_REGS_RDX],
-		vcpu->regs[VCPU_REGS_RBP]);
-	vcpu->regs[VCPU_REGS_RAX] = 0;
 	vmcs_writel(GUEST_RIP, vmcs_readl(GUEST_RIP)+3);
-	return 1;
+	return kvm_hypercall(vcpu, kvm_run);
 }
 
 /*
-- 
cgit v1.2.3


From cd205625e9bf2090d9bd95848ef4b34ad3f1a8b3 Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi@qumranet.com>
Date: Mon, 19 Feb 2007 14:37:47 +0200
Subject: KVM: svm: init cr0 with the wp bit set

Signed-off-by: Avi Kivity <avi@qumranet.com>
---
 drivers/kvm/svm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/kvm/svm.c')

diff --git a/drivers/kvm/svm.c b/drivers/kvm/svm.c
index 711ea42370a8..57aad502e078 100644
--- a/drivers/kvm/svm.c
+++ b/drivers/kvm/svm.c
@@ -554,7 +554,7 @@ static void init_vmcb(struct vmcb *vmcb)
 	 * cr0 val on cpu init should be 0x60000010, we enable cpu
 	 * cache by default. the orderly way is to enable cache in bios.
 	 */
-	save->cr0 = 0x00000010 | CR0_PG_MASK;
+	save->cr0 = 0x00000010 | CR0_PG_MASK | CR0_WP_MASK;
 	save->cr4 = CR4_PAE_MASK;
 	/* rdx = ?? */
 }
-- 
cgit v1.2.3


From 0152527b76b72333121d5a1243f9e091b58d4580 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <joerg.roedel@amd.com>
Date: Mon, 19 Feb 2007 14:37:47 +0200
Subject: KVM: SVM: intercept SMI to handle it at host level

This patch changes the SVM code to intercept SMIs and handle it
outside the guest.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
---
 drivers/kvm/svm.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'drivers/kvm/svm.c')

diff --git a/drivers/kvm/svm.c b/drivers/kvm/svm.c
index 57aad502e078..5a200c0b4b48 100644
--- a/drivers/kvm/svm.c
+++ b/drivers/kvm/svm.c
@@ -486,6 +486,7 @@ static void init_vmcb(struct vmcb *vmcb)
 
 	control->intercept = 	(1ULL << INTERCEPT_INTR) |
 				(1ULL << INTERCEPT_NMI) |
+				(1ULL << INTERCEPT_SMI) |
 		/*
 		 * selective cr0 intercept bug?
 		 *    	0:   0f 22 d8                mov    %eax,%cr3
-- 
cgit v1.2.3


From bccf2150fe62dda5fb09efa2f64d2a234694eb48 Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi@qumranet.com>
Date: Wed, 21 Feb 2007 18:04:26 +0200
Subject: KVM: Per-vcpu inodes

Allocate a distinct inode for every vcpu in a VM.  This has the following
benefits:

 - the filp cachelines are no longer bounced when f_count is incremented on
   every ioctl()
 - the API and internal code are distinctly clearer; for example, on the
   KVM_GET_REGS ioctl, there is no need to copy the vcpu number from
   userspace and then copy the registers back; the vcpu identity is derived
   from the fd used to make the call

Right now the performance benefits are completely theoretical since (a) we
don't support more than one vcpu per VM and (b) virtualization hardware
inefficiencies completely everwhelm any cacheline bouncing effects.  But
both of these will change, and we need to prepare the API today.

Signed-off-by: Avi Kivity <avi@qumranet.com>
---
 drivers/kvm/kvm.h      |   3 +-
 drivers/kvm/kvm_main.c | 263 ++++++++++++++++++++++++++++---------------------
 drivers/kvm/svm.c      |   3 +-
 drivers/kvm/vmx.c      |   3 +-
 include/linux/kvm.h    |  38 ++++---
 5 files changed, 170 insertions(+), 140 deletions(-)

(limited to 'drivers/kvm/svm.c')

diff --git a/drivers/kvm/kvm.h b/drivers/kvm/kvm.h
index 41cc27de4d66..0d122bf889db 100644
--- a/drivers/kvm/kvm.h
+++ b/drivers/kvm/kvm.h
@@ -309,6 +309,7 @@ struct kvm {
 	int busy;
 	unsigned long rmap_overflow;
 	struct list_head vm_list;
+	struct file *filp;
 };
 
 struct kvm_stat {
@@ -343,7 +344,7 @@ struct kvm_arch_ops {
 	int (*vcpu_create)(struct kvm_vcpu *vcpu);
 	void (*vcpu_free)(struct kvm_vcpu *vcpu);
 
-	struct kvm_vcpu *(*vcpu_load)(struct kvm_vcpu *vcpu);
+	void (*vcpu_load)(struct kvm_vcpu *vcpu);
 	void (*vcpu_put)(struct kvm_vcpu *vcpu);
 	void (*vcpu_decache)(struct kvm_vcpu *vcpu);
 
diff --git a/drivers/kvm/kvm_main.c b/drivers/kvm/kvm_main.c
index 6fb36c80e3e8..a593d092d85b 100644
--- a/drivers/kvm/kvm_main.c
+++ b/drivers/kvm/kvm_main.c
@@ -96,6 +96,9 @@ struct segment_descriptor_64 {
 
 #endif
 
+static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
+			   unsigned long arg);
+
 static struct inode *kvmfs_inode(struct file_operations *fops)
 {
 	int error = -ENOMEM;
@@ -246,24 +249,30 @@ int kvm_write_guest(struct kvm_vcpu *vcpu, gva_t addr, unsigned long size,
 }
 EXPORT_SYMBOL_GPL(kvm_write_guest);
 
-static int vcpu_slot(struct kvm_vcpu *vcpu)
+/*
+ * Switches to specified vcpu, until a matching vcpu_put()
+ */
+static void vcpu_load(struct kvm_vcpu *vcpu)
 {
-	return vcpu - vcpu->kvm->vcpus;
+	mutex_lock(&vcpu->mutex);
+	kvm_arch_ops->vcpu_load(vcpu);
 }
 
 /*
- * Switches to specified vcpu, until a matching vcpu_put()
+ * Switches to specified vcpu, until a matching vcpu_put(). Will return NULL
+ * if the slot is not populated.
  */
-static struct kvm_vcpu *vcpu_load(struct kvm *kvm, int vcpu_slot)
+static struct kvm_vcpu *vcpu_load_slot(struct kvm *kvm, int slot)
 {
-	struct kvm_vcpu *vcpu = &kvm->vcpus[vcpu_slot];
+	struct kvm_vcpu *vcpu = &kvm->vcpus[slot];
 
 	mutex_lock(&vcpu->mutex);
-	if (unlikely(!vcpu->vmcs)) {
+	if (!vcpu->vmcs) {
 		mutex_unlock(&vcpu->mutex);
 		return NULL;
 	}
-	return kvm_arch_ops->vcpu_load(vcpu);
+	kvm_arch_ops->vcpu_load(vcpu);
+	return vcpu;
 }
 
 static void vcpu_put(struct kvm_vcpu *vcpu)
@@ -336,9 +345,10 @@ static void kvm_free_physmem(struct kvm *kvm)
 
 static void kvm_free_vcpu(struct kvm_vcpu *vcpu)
 {
-	if (!vcpu_load(vcpu->kvm, vcpu_slot(vcpu)))
+	if (!vcpu->vmcs)
 		return;
 
+	vcpu_load(vcpu);
 	kvm_mmu_destroy(vcpu);
 	vcpu_put(vcpu);
 	kvm_arch_ops->vcpu_free(vcpu);
@@ -725,7 +735,7 @@ raced:
 	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
 		struct kvm_vcpu *vcpu;
 
-		vcpu = vcpu_load(kvm, i);
+		vcpu = vcpu_load_slot(kvm, i);
 		if (!vcpu)
 			continue;
 		kvm_mmu_reset_context(vcpu);
@@ -791,8 +801,9 @@ static int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 	if (any) {
 		cleared = 0;
 		for (i = 0; i < KVM_MAX_VCPUS; ++i) {
-			struct kvm_vcpu *vcpu = vcpu_load(kvm, i);
+			struct kvm_vcpu *vcpu;
 
+			vcpu = vcpu_load_slot(kvm, i);
 			if (!vcpu)
 				continue;
 			if (!cleared) {
@@ -1461,8 +1472,7 @@ void kvm_resched(struct kvm_vcpu *vcpu)
 {
 	vcpu_put(vcpu);
 	cond_resched();
-	/* Cannot fail -  no vcpu unplug yet. */
-	vcpu_load(vcpu->kvm, vcpu_slot(vcpu));
+	vcpu_load(vcpu);
 }
 EXPORT_SYMBOL_GPL(kvm_resched);
 
@@ -1484,17 +1494,11 @@ void save_msrs(struct vmx_msr_entry *e, int n)
 }
 EXPORT_SYMBOL_GPL(save_msrs);
 
-static int kvm_vm_ioctl_run(struct kvm *kvm, struct kvm_run *kvm_run)
+static int kvm_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
-	struct kvm_vcpu *vcpu;
 	int r;
 
-	if (!valid_vcpu(kvm_run->vcpu))
-		return -EINVAL;
-
-	vcpu = vcpu_load(kvm, kvm_run->vcpu);
-	if (!vcpu)
-		return -ENOENT;
+	vcpu_load(vcpu);
 
 	/* re-sync apic's tpr */
 	vcpu->cr8 = kvm_run->cr8;
@@ -1517,16 +1521,10 @@ static int kvm_vm_ioctl_run(struct kvm *kvm, struct kvm_run *kvm_run)
 	return r;
 }
 
-static int kvm_vm_ioctl_get_regs(struct kvm *kvm, struct kvm_regs *regs)
+static int kvm_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu,
+				   struct kvm_regs *regs)
 {
-	struct kvm_vcpu *vcpu;
-
-	if (!valid_vcpu(regs->vcpu))
-		return -EINVAL;
-
-	vcpu = vcpu_load(kvm, regs->vcpu);
-	if (!vcpu)
-		return -ENOENT;
+	vcpu_load(vcpu);
 
 	kvm_arch_ops->cache_regs(vcpu);
 
@@ -1563,16 +1561,10 @@ static int kvm_vm_ioctl_get_regs(struct kvm *kvm, struct kvm_regs *regs)
 	return 0;
 }
 
-static int kvm_vm_ioctl_set_regs(struct kvm *kvm, struct kvm_regs *regs)
+static int kvm_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu,
+				   struct kvm_regs *regs)
 {
-	struct kvm_vcpu *vcpu;
-
-	if (!valid_vcpu(regs->vcpu))
-		return -EINVAL;
-
-	vcpu = vcpu_load(kvm, regs->vcpu);
-	if (!vcpu)
-		return -ENOENT;
+	vcpu_load(vcpu);
 
 	vcpu->regs[VCPU_REGS_RAX] = regs->rax;
 	vcpu->regs[VCPU_REGS_RBX] = regs->rbx;
@@ -1609,16 +1601,12 @@ static void get_segment(struct kvm_vcpu *vcpu,
 	return kvm_arch_ops->get_segment(vcpu, var, seg);
 }
 
-static int kvm_vm_ioctl_get_sregs(struct kvm *kvm, struct kvm_sregs *sregs)
+static int kvm_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
+				    struct kvm_sregs *sregs)
 {
-	struct kvm_vcpu *vcpu;
 	struct descriptor_table dt;
 
-	if (!valid_vcpu(sregs->vcpu))
-		return -EINVAL;
-	vcpu = vcpu_load(kvm, sregs->vcpu);
-	if (!vcpu)
-		return -ENOENT;
+	vcpu_load(vcpu);
 
 	get_segment(vcpu, &sregs->cs, VCPU_SREG_CS);
 	get_segment(vcpu, &sregs->ds, VCPU_SREG_DS);
@@ -1660,18 +1648,14 @@ static void set_segment(struct kvm_vcpu *vcpu,
 	return kvm_arch_ops->set_segment(vcpu, var, seg);
 }
 
-static int kvm_vm_ioctl_set_sregs(struct kvm *kvm, struct kvm_sregs *sregs)
+static int kvm_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
+				    struct kvm_sregs *sregs)
 {
-	struct kvm_vcpu *vcpu;
 	int mmu_reset_needed = 0;
 	int i;
 	struct descriptor_table dt;
 
-	if (!valid_vcpu(sregs->vcpu))
-		return -EINVAL;
-	vcpu = vcpu_load(kvm, sregs->vcpu);
-	if (!vcpu)
-		return -ENOENT;
+	vcpu_load(vcpu);
 
 	set_segment(vcpu, &sregs->cs, VCPU_SREG_CS);
 	set_segment(vcpu, &sregs->ds, VCPU_SREG_DS);
@@ -1777,20 +1761,14 @@ static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
  *
  * @return number of msrs set successfully.
  */
-static int __msr_io(struct kvm *kvm, struct kvm_msrs *msrs,
+static int __msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs,
 		    struct kvm_msr_entry *entries,
 		    int (*do_msr)(struct kvm_vcpu *vcpu,
 				  unsigned index, u64 *data))
 {
-	struct kvm_vcpu *vcpu;
 	int i;
 
-	if (!valid_vcpu(msrs->vcpu))
-		return -EINVAL;
-
-	vcpu = vcpu_load(kvm, msrs->vcpu);
-	if (!vcpu)
-		return -ENOENT;
+	vcpu_load(vcpu);
 
 	for (i = 0; i < msrs->nmsrs; ++i)
 		if (do_msr(vcpu, entries[i].index, &entries[i].data))
@@ -1806,7 +1784,7 @@ static int __msr_io(struct kvm *kvm, struct kvm_msrs *msrs,
  *
  * @return number of msrs set successfully.
  */
-static int msr_io(struct kvm *kvm, struct kvm_msrs __user *user_msrs,
+static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs,
 		  int (*do_msr)(struct kvm_vcpu *vcpu,
 				unsigned index, u64 *data),
 		  int writeback)
@@ -1834,7 +1812,7 @@ static int msr_io(struct kvm *kvm, struct kvm_msrs __user *user_msrs,
 	if (copy_from_user(entries, user_msrs->entries, size))
 		goto out_free;
 
-	r = n = __msr_io(kvm, &msrs, entries, do_msr);
+	r = n = __msr_io(vcpu, &msrs, entries, do_msr);
 	if (r < 0)
 		goto out_free;
 
@@ -1853,38 +1831,31 @@ out:
 /*
  * Translate a guest virtual address to a guest physical address.
  */
-static int kvm_vm_ioctl_translate(struct kvm *kvm, struct kvm_translation *tr)
+static int kvm_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
+				    struct kvm_translation *tr)
 {
 	unsigned long vaddr = tr->linear_address;
-	struct kvm_vcpu *vcpu;
 	gpa_t gpa;
 
-	vcpu = vcpu_load(kvm, tr->vcpu);
-	if (!vcpu)
-		return -ENOENT;
-	spin_lock(&kvm->lock);
+	vcpu_load(vcpu);
+	spin_lock(&vcpu->kvm->lock);
 	gpa = vcpu->mmu.gva_to_gpa(vcpu, vaddr);
 	tr->physical_address = gpa;
 	tr->valid = gpa != UNMAPPED_GVA;
 	tr->writeable = 1;
 	tr->usermode = 0;
-	spin_unlock(&kvm->lock);
+	spin_unlock(&vcpu->kvm->lock);
 	vcpu_put(vcpu);
 
 	return 0;
 }
 
-static int kvm_vm_ioctl_interrupt(struct kvm *kvm, struct kvm_interrupt *irq)
+static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
+				    struct kvm_interrupt *irq)
 {
-	struct kvm_vcpu *vcpu;
-
-	if (!valid_vcpu(irq->vcpu))
-		return -EINVAL;
 	if (irq->irq < 0 || irq->irq >= 256)
 		return -EINVAL;
-	vcpu = vcpu_load(kvm, irq->vcpu);
-	if (!vcpu)
-		return -ENOENT;
+	vcpu_load(vcpu);
 
 	set_bit(irq->irq, vcpu->irq_pending);
 	set_bit(irq->irq / BITS_PER_LONG, &vcpu->irq_summary);
@@ -1894,17 +1865,12 @@ static int kvm_vm_ioctl_interrupt(struct kvm *kvm, struct kvm_interrupt *irq)
 	return 0;
 }
 
-static int kvm_vm_ioctl_debug_guest(struct kvm *kvm,
-				     struct kvm_debug_guest *dbg)
+static int kvm_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
+				      struct kvm_debug_guest *dbg)
 {
-	struct kvm_vcpu *vcpu;
 	int r;
 
-	if (!valid_vcpu(dbg->vcpu))
-		return -EINVAL;
-	vcpu = vcpu_load(kvm, dbg->vcpu);
-	if (!vcpu)
-		return -ENOENT;
+	vcpu_load(vcpu);
 
 	r = kvm_arch_ops->set_guest_debug(vcpu, dbg);
 
@@ -1913,6 +1879,59 @@ static int kvm_vm_ioctl_debug_guest(struct kvm *kvm,
 	return r;
 }
 
+static int kvm_vcpu_release(struct inode *inode, struct file *filp)
+{
+	struct kvm_vcpu *vcpu = filp->private_data;
+
+	fput(vcpu->kvm->filp);
+	return 0;
+}
+
+static struct file_operations kvm_vcpu_fops = {
+	.release        = kvm_vcpu_release,
+	.unlocked_ioctl = kvm_vcpu_ioctl,
+	.compat_ioctl   = kvm_vcpu_ioctl,
+};
+
+/*
+ * Allocates an inode for the vcpu.
+ */
+static int create_vcpu_fd(struct kvm_vcpu *vcpu)
+{
+	int fd, r;
+	struct inode *inode;
+	struct file *file;
+
+	atomic_inc(&vcpu->kvm->filp->f_count);
+	inode = kvmfs_inode(&kvm_vcpu_fops);
+	if (IS_ERR(inode)) {
+		r = PTR_ERR(inode);
+		goto out1;
+	}
+
+	file = kvmfs_file(inode, vcpu);
+	if (IS_ERR(file)) {
+		r = PTR_ERR(file);
+		goto out2;
+	}
+
+	r = get_unused_fd();
+	if (r < 0)
+		goto out3;
+	fd = r;
+	fd_install(fd, file);
+
+	return fd;
+
+out3:
+	fput(file);
+out2:
+	iput(inode);
+out1:
+	fput(vcpu->kvm->filp);
+	return r;
+}
+
 /*
  * Creates some virtual cpus.  Good luck creating more than one.
  */
@@ -1955,7 +1974,11 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, int n)
 	if (r < 0)
 		goto out_free_vcpus;
 
-	return 0;
+	r = create_vcpu_fd(vcpu);
+	if (r < 0)
+		goto out_free_vcpus;
+
+	return r;
 
 out_free_vcpus:
 	kvm_free_vcpu(vcpu);
@@ -1964,26 +1987,21 @@ out:
 	return r;
 }
 
-static long kvm_vm_ioctl(struct file *filp,
-			 unsigned int ioctl, unsigned long arg)
+static long kvm_vcpu_ioctl(struct file *filp,
+			   unsigned int ioctl, unsigned long arg)
 {
-	struct kvm *kvm = filp->private_data;
+	struct kvm_vcpu *vcpu = filp->private_data;
 	void __user *argp = (void __user *)arg;
 	int r = -EINVAL;
 
 	switch (ioctl) {
-	case KVM_CREATE_VCPU:
-		r = kvm_vm_ioctl_create_vcpu(kvm, arg);
-		if (r)
-			goto out;
-		break;
 	case KVM_RUN: {
 		struct kvm_run kvm_run;
 
 		r = -EFAULT;
 		if (copy_from_user(&kvm_run, argp, sizeof kvm_run))
 			goto out;
-		r = kvm_vm_ioctl_run(kvm, &kvm_run);
+		r = kvm_vcpu_ioctl_run(vcpu, &kvm_run);
 		if (r < 0 &&  r != -EINTR)
 			goto out;
 		if (copy_to_user(argp, &kvm_run, sizeof kvm_run)) {
@@ -1995,10 +2013,8 @@ static long kvm_vm_ioctl(struct file *filp,
 	case KVM_GET_REGS: {
 		struct kvm_regs kvm_regs;
 
-		r = -EFAULT;
-		if (copy_from_user(&kvm_regs, argp, sizeof kvm_regs))
-			goto out;
-		r = kvm_vm_ioctl_get_regs(kvm, &kvm_regs);
+		memset(&kvm_regs, 0, sizeof kvm_regs);
+		r = kvm_vcpu_ioctl_get_regs(vcpu, &kvm_regs);
 		if (r)
 			goto out;
 		r = -EFAULT;
@@ -2013,7 +2029,7 @@ static long kvm_vm_ioctl(struct file *filp,
 		r = -EFAULT;
 		if (copy_from_user(&kvm_regs, argp, sizeof kvm_regs))
 			goto out;
-		r = kvm_vm_ioctl_set_regs(kvm, &kvm_regs);
+		r = kvm_vcpu_ioctl_set_regs(vcpu, &kvm_regs);
 		if (r)
 			goto out;
 		r = 0;
@@ -2022,10 +2038,8 @@ static long kvm_vm_ioctl(struct file *filp,
 	case KVM_GET_SREGS: {
 		struct kvm_sregs kvm_sregs;
 
-		r = -EFAULT;
-		if (copy_from_user(&kvm_sregs, argp, sizeof kvm_sregs))
-			goto out;
-		r = kvm_vm_ioctl_get_sregs(kvm, &kvm_sregs);
+		memset(&kvm_sregs, 0, sizeof kvm_sregs);
+		r = kvm_vcpu_ioctl_get_sregs(vcpu, &kvm_sregs);
 		if (r)
 			goto out;
 		r = -EFAULT;
@@ -2040,7 +2054,7 @@ static long kvm_vm_ioctl(struct file *filp,
 		r = -EFAULT;
 		if (copy_from_user(&kvm_sregs, argp, sizeof kvm_sregs))
 			goto out;
-		r = kvm_vm_ioctl_set_sregs(kvm, &kvm_sregs);
+		r = kvm_vcpu_ioctl_set_sregs(vcpu, &kvm_sregs);
 		if (r)
 			goto out;
 		r = 0;
@@ -2052,7 +2066,7 @@ static long kvm_vm_ioctl(struct file *filp,
 		r = -EFAULT;
 		if (copy_from_user(&tr, argp, sizeof tr))
 			goto out;
-		r = kvm_vm_ioctl_translate(kvm, &tr);
+		r = kvm_vcpu_ioctl_translate(vcpu, &tr);
 		if (r)
 			goto out;
 		r = -EFAULT;
@@ -2067,7 +2081,7 @@ static long kvm_vm_ioctl(struct file *filp,
 		r = -EFAULT;
 		if (copy_from_user(&irq, argp, sizeof irq))
 			goto out;
-		r = kvm_vm_ioctl_interrupt(kvm, &irq);
+		r = kvm_vcpu_ioctl_interrupt(vcpu, &irq);
 		if (r)
 			goto out;
 		r = 0;
@@ -2079,12 +2093,38 @@ static long kvm_vm_ioctl(struct file *filp,
 		r = -EFAULT;
 		if (copy_from_user(&dbg, argp, sizeof dbg))
 			goto out;
-		r = kvm_vm_ioctl_debug_guest(kvm, &dbg);
+		r = kvm_vcpu_ioctl_debug_guest(vcpu, &dbg);
 		if (r)
 			goto out;
 		r = 0;
 		break;
 	}
+	case KVM_GET_MSRS:
+		r = msr_io(vcpu, argp, get_msr, 1);
+		break;
+	case KVM_SET_MSRS:
+		r = msr_io(vcpu, argp, do_set_msr, 0);
+		break;
+	default:
+		;
+	}
+out:
+	return r;
+}
+
+static long kvm_vm_ioctl(struct file *filp,
+			   unsigned int ioctl, unsigned long arg)
+{
+	struct kvm *kvm = filp->private_data;
+	void __user *argp = (void __user *)arg;
+	int r = -EINVAL;
+
+	switch (ioctl) {
+	case KVM_CREATE_VCPU:
+		r = kvm_vm_ioctl_create_vcpu(kvm, arg);
+		if (r < 0)
+			goto out;
+		break;
 	case KVM_SET_MEMORY_REGION: {
 		struct kvm_memory_region kvm_mem;
 
@@ -2107,12 +2147,6 @@ static long kvm_vm_ioctl(struct file *filp,
 			goto out;
 		break;
 	}
-	case KVM_GET_MSRS:
-		r = msr_io(kvm, argp, get_msr, 1);
-		break;
-	case KVM_SET_MSRS:
-		r = msr_io(kvm, argp, do_set_msr, 0);
-		break;
 	default:
 		;
 	}
@@ -2182,6 +2216,7 @@ static int kvm_dev_ioctl_create_vm(void)
 		r = PTR_ERR(file);
 		goto out3;
 	}
+	kvm->filp = file;
 
 	r = get_unused_fd();
 	if (r < 0)
diff --git a/drivers/kvm/svm.c b/drivers/kvm/svm.c
index 5a200c0b4b48..3d8ea7ac2ecc 100644
--- a/drivers/kvm/svm.c
+++ b/drivers/kvm/svm.c
@@ -600,10 +600,9 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu)
 	kfree(vcpu->svm);
 }
 
-static struct kvm_vcpu *svm_vcpu_load(struct kvm_vcpu *vcpu)
+static void svm_vcpu_load(struct kvm_vcpu *vcpu)
 {
 	get_cpu();
-	return vcpu;
 }
 
 static void svm_vcpu_put(struct kvm_vcpu *vcpu)
diff --git a/drivers/kvm/vmx.c b/drivers/kvm/vmx.c
index ff956a6302ec..c07178e61122 100644
--- a/drivers/kvm/vmx.c
+++ b/drivers/kvm/vmx.c
@@ -204,7 +204,7 @@ static void vmcs_write64(unsigned long field, u64 value)
  * Switches to specified vcpu, until a matching vcpu_put(), but assumes
  * vcpu mutex is already taken.
  */
-static struct kvm_vcpu *vmx_vcpu_load(struct kvm_vcpu *vcpu)
+static void vmx_vcpu_load(struct kvm_vcpu *vcpu)
 {
 	u64 phys_addr = __pa(vcpu->vmcs);
 	int cpu;
@@ -242,7 +242,6 @@ static struct kvm_vcpu *vmx_vcpu_load(struct kvm_vcpu *vcpu)
 		rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp);
 		vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */
 	}
-	return vcpu;
 }
 
 static void vmx_vcpu_put(struct kvm_vcpu *vcpu)
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index d6e6635dbec1..7c9a4004af44 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -52,11 +52,10 @@ enum kvm_exit_reason {
 /* for KVM_RUN */
 struct kvm_run {
 	/* in */
-	__u32 vcpu;
 	__u32 emulated;  /* skip current instruction */
 	__u32 mmio_completed; /* mmio request completed */
 	__u8 request_interrupt_window;
-	__u8 padding1[3];
+	__u8 padding1[7];
 
 	/* out */
 	__u32 exit_type;
@@ -111,10 +110,6 @@ struct kvm_run {
 
 /* for KVM_GET_REGS and KVM_SET_REGS */
 struct kvm_regs {
-	/* in */
-	__u32 vcpu;
-	__u32 padding;
-
 	/* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
 	__u64 rax, rbx, rcx, rdx;
 	__u64 rsi, rdi, rsp, rbp;
@@ -141,10 +136,6 @@ struct kvm_dtable {
 
 /* for KVM_GET_SREGS and KVM_SET_SREGS */
 struct kvm_sregs {
-	/* in */
-	__u32 vcpu;
-	__u32 padding;
-
 	/* out (KVM_GET_SREGS) / in (KVM_SET_SREGS) */
 	struct kvm_segment cs, ds, es, fs, gs, ss;
 	struct kvm_segment tr, ldt;
@@ -163,8 +154,8 @@ struct kvm_msr_entry {
 
 /* for KVM_GET_MSRS and KVM_SET_MSRS */
 struct kvm_msrs {
-	__u32 vcpu;
 	__u32 nmsrs; /* number of msrs in entries */
+	__u32 pad;
 
 	struct kvm_msr_entry entries[0];
 };
@@ -179,8 +170,6 @@ struct kvm_msr_list {
 struct kvm_translation {
 	/* in */
 	__u64 linear_address;
-	__u32 vcpu;
-	__u32 padding;
 
 	/* out */
 	__u64 physical_address;
@@ -193,7 +182,6 @@ struct kvm_translation {
 /* for KVM_INTERRUPT */
 struct kvm_interrupt {
 	/* in */
-	__u32 vcpu;
 	__u32 irq;
 };
 
@@ -206,8 +194,8 @@ struct kvm_breakpoint {
 /* for KVM_DEBUG_GUEST */
 struct kvm_debug_guest {
 	/* int */
-	__u32 vcpu;
 	__u32 enabled;
+	__u32 pad;
 	struct kvm_breakpoint breakpoints[4];
 	__u32 singlestep;
 };
@@ -234,18 +222,26 @@ struct kvm_dirty_log {
 /*
  * ioctls for VM fds
  */
+#define KVM_SET_MEMORY_REGION     _IOW(KVMIO, 10, struct kvm_memory_region)
+/*
+ * KVM_CREATE_VCPU receives as a parameter the vcpu slot, and returns
+ * a vcpu fd.
+ */
+#define KVM_CREATE_VCPU           _IOW(KVMIO, 11, int)
+#define KVM_GET_DIRTY_LOG         _IOW(KVMIO, 12, struct kvm_dirty_log)
+
+/*
+ * ioctls for vcpu fds
+ */
 #define KVM_RUN                   _IOWR(KVMIO, 2, struct kvm_run)
-#define KVM_GET_REGS              _IOWR(KVMIO, 3, struct kvm_regs)
+#define KVM_GET_REGS              _IOR(KVMIO, 3, struct kvm_regs)
 #define KVM_SET_REGS              _IOW(KVMIO, 4, struct kvm_regs)
-#define KVM_GET_SREGS             _IOWR(KVMIO, 5, struct kvm_sregs)
+#define KVM_GET_SREGS             _IOR(KVMIO, 5, struct kvm_sregs)
 #define KVM_SET_SREGS             _IOW(KVMIO, 6, struct kvm_sregs)
 #define KVM_TRANSLATE             _IOWR(KVMIO, 7, struct kvm_translation)
 #define KVM_INTERRUPT             _IOW(KVMIO, 8, struct kvm_interrupt)
 #define KVM_DEBUG_GUEST           _IOW(KVMIO, 9, struct kvm_debug_guest)
-#define KVM_SET_MEMORY_REGION     _IOW(KVMIO, 10, struct kvm_memory_region)
-#define KVM_CREATE_VCPU           _IOW(KVMIO, 11, int /* vcpu_slot */)
-#define KVM_GET_DIRTY_LOG         _IOW(KVMIO, 12, struct kvm_dirty_log)
 #define KVM_GET_MSRS              _IOWR(KVMIO, 13, struct kvm_msrs)
-#define KVM_SET_MSRS              _IOWR(KVMIO, 14, struct kvm_msrs)
+#define KVM_SET_MSRS              _IOW(KVMIO, 14, struct kvm_msrs)
 
 #endif
-- 
cgit v1.2.3