[PATCH 00/12] x86: disable virt on kdump and emergency_restart (v4)

[PATCH 00/12] x86: disable virt on kdump and emergency_restart (v4)

[Eduardo Habkost]

Hi, Ingo,

This is yet another spin of the series to disable vmx on kdump and on
emergency_restart, after some feedback from Avi.

The only change from v3 is that vmx.h and svm.h were moved from
arch/x86/kvm to arch/x86/include/asm, instead of moving code
from those headers to asm/virtext.h.

I haven't tested the SVM changes on AMD CPUs. The changes are really
simple, but some testing is welcome.

This series is against tip.git#master, that already contains the
nmi_shootdown_cpus() changes I've submitted previously.


For reference, this is the history of the patchset:

v1: Implemented the changes using a function pointer registering interface
    where KVM could hook the virt-disable functions
v2: Style fixes
v3: Implemented the changes by moving the virt-disable code from KVM
    to inline functions on asm/virtext.h
v4: Move KVM svm.h and vmx.h to include/asm, instead of moving
    pieces of their contents to asm/virtext.h

-- 
Eduardo

[PATCH 01/12] kvm: vmx: move vmx.h to include/asm

[Eduardo Habkost]

vmx.h will be used by core code that is independent of KVM, so I am
moving it outside the arch/x86/kvm directory.

Signed-off-by: Eduardo Habkost <ehabkost-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
---
 arch/x86/include/asm/vmx.h |  359 ++++++++++++++++++++++++++++++++++++++++++++
 arch/x86/kvm/mmu.c         |    2 +-
 arch/x86/kvm/vmx.c         |    2 +-
 arch/x86/kvm/vmx.h         |  359 --------------------------------------------
 4 files changed, 361 insertions(+), 361 deletions(-)
 create mode 100644 arch/x86/include/asm/vmx.h
 delete mode 100644 arch/x86/kvm/vmx.h

diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
new file mode 100644
index 0000000..ec5edc3
--- /dev/null
+++ b/arch/x86/include/asm/vmx.h
@@ -0,0 +1,359 @@
+#ifndef VMX_H
+#define VMX_H
+
+/*
+ * vmx.h: VMX Architecture related definitions
+ * Copyright (c) 2004, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * A few random additions are:
+ * Copyright (C) 2006 Qumranet
+ *    Avi Kivity <avi-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
+ *    Yaniv Kamay <yaniv-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
+ *
+ */
+
+/*
+ * Definitions of Primary Processor-Based VM-Execution Controls.
+ */
+#define CPU_BASED_VIRTUAL_INTR_PENDING          0x00000004
+#define CPU_BASED_USE_TSC_OFFSETING             0x00000008
+#define CPU_BASED_HLT_EXITING                   0x00000080
+#define CPU_BASED_INVLPG_EXITING                0x00000200
+#define CPU_BASED_MWAIT_EXITING                 0x00000400
+#define CPU_BASED_RDPMC_EXITING                 0x00000800
+#define CPU_BASED_RDTSC_EXITING                 0x00001000
+#define CPU_BASED_CR3_LOAD_EXITING		0x00008000
+#define CPU_BASED_CR3_STORE_EXITING		0x00010000
+#define CPU_BASED_CR8_LOAD_EXITING              0x00080000
+#define CPU_BASED_CR8_STORE_EXITING             0x00100000
+#define CPU_BASED_TPR_SHADOW                    0x00200000
+#define CPU_BASED_VIRTUAL_NMI_PENDING		0x00400000
+#define CPU_BASED_MOV_DR_EXITING                0x00800000
+#define CPU_BASED_UNCOND_IO_EXITING             0x01000000
+#define CPU_BASED_USE_IO_BITMAPS                0x02000000
+#define CPU_BASED_USE_MSR_BITMAPS               0x10000000
+#define CPU_BASED_MONITOR_EXITING               0x20000000
+#define CPU_BASED_PAUSE_EXITING                 0x40000000
+#define CPU_BASED_ACTIVATE_SECONDARY_CONTROLS   0x80000000
+/*
+ * Definitions of Secondary Processor-Based VM-Execution Controls.
+ */
+#define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001
+#define SECONDARY_EXEC_ENABLE_EPT               0x00000002
+#define SECONDARY_EXEC_ENABLE_VPID              0x00000020
+#define SECONDARY_EXEC_WBINVD_EXITING		0x00000040
+
+
+#define PIN_BASED_EXT_INTR_MASK                 0x00000001
+#define PIN_BASED_NMI_EXITING                   0x00000008
+#define PIN_BASED_VIRTUAL_NMIS                  0x00000020
+
+#define VM_EXIT_HOST_ADDR_SPACE_SIZE            0x00000200
+#define VM_EXIT_ACK_INTR_ON_EXIT                0x00008000
+
+#define VM_ENTRY_IA32E_MODE                     0x00000200
+#define VM_ENTRY_SMM                            0x00000400
+#define VM_ENTRY_DEACT_DUAL_MONITOR             0x00000800
+
+/* VMCS Encodings */
+enum vmcs_field {
+	VIRTUAL_PROCESSOR_ID            = 0x00000000,
+	GUEST_ES_SELECTOR               = 0x00000800,
+	GUEST_CS_SELECTOR               = 0x00000802,
+	GUEST_SS_SELECTOR               = 0x00000804,
+	GUEST_DS_SELECTOR               = 0x00000806,
+	GUEST_FS_SELECTOR               = 0x00000808,
+	GUEST_GS_SELECTOR               = 0x0000080a,
+	GUEST_LDTR_SELECTOR             = 0x0000080c,
+	GUEST_TR_SELECTOR               = 0x0000080e,
+	HOST_ES_SELECTOR                = 0x00000c00,
+	HOST_CS_SELECTOR                = 0x00000c02,
+	HOST_SS_SELECTOR                = 0x00000c04,
+	HOST_DS_SELECTOR                = 0x00000c06,
+	HOST_FS_SELECTOR                = 0x00000c08,
+	HOST_GS_SELECTOR                = 0x00000c0a,
+	HOST_TR_SELECTOR                = 0x00000c0c,
+	IO_BITMAP_A                     = 0x00002000,
+	IO_BITMAP_A_HIGH                = 0x00002001,
+	IO_BITMAP_B                     = 0x00002002,
+	IO_BITMAP_B_HIGH                = 0x00002003,
+	MSR_BITMAP                      = 0x00002004,
+	MSR_BITMAP_HIGH                 = 0x00002005,
+	VM_EXIT_MSR_STORE_ADDR          = 0x00002006,
+	VM_EXIT_MSR_STORE_ADDR_HIGH     = 0x00002007,
+	VM_EXIT_MSR_LOAD_ADDR           = 0x00002008,
+	VM_EXIT_MSR_LOAD_ADDR_HIGH      = 0x00002009,
+	VM_ENTRY_MSR_LOAD_ADDR          = 0x0000200a,
+	VM_ENTRY_MSR_LOAD_ADDR_HIGH     = 0x0000200b,
+	TSC_OFFSET                      = 0x00002010,
+	TSC_OFFSET_HIGH                 = 0x00002011,
+	VIRTUAL_APIC_PAGE_ADDR          = 0x00002012,
+	VIRTUAL_APIC_PAGE_ADDR_HIGH     = 0x00002013,
+	APIC_ACCESS_ADDR		= 0x00002014,
+	APIC_ACCESS_ADDR_HIGH		= 0x00002015,
+	EPT_POINTER                     = 0x0000201a,
+	EPT_POINTER_HIGH                = 0x0000201b,
+	GUEST_PHYSICAL_ADDRESS          = 0x00002400,
+	GUEST_PHYSICAL_ADDRESS_HIGH     = 0x00002401,
+	VMCS_LINK_POINTER               = 0x00002800,
+	VMCS_LINK_POINTER_HIGH          = 0x00002801,
+	GUEST_IA32_DEBUGCTL             = 0x00002802,
+	GUEST_IA32_DEBUGCTL_HIGH        = 0x00002803,
+	GUEST_PDPTR0                    = 0x0000280a,
+	GUEST_PDPTR0_HIGH               = 0x0000280b,
+	GUEST_PDPTR1                    = 0x0000280c,
+	GUEST_PDPTR1_HIGH               = 0x0000280d,
+	GUEST_PDPTR2                    = 0x0000280e,
+	GUEST_PDPTR2_HIGH               = 0x0000280f,
+	GUEST_PDPTR3                    = 0x00002810,
+	GUEST_PDPTR3_HIGH               = 0x00002811,
+	PIN_BASED_VM_EXEC_CONTROL       = 0x00004000,
+	CPU_BASED_VM_EXEC_CONTROL       = 0x00004002,
+	EXCEPTION_BITMAP                = 0x00004004,
+	PAGE_FAULT_ERROR_CODE_MASK      = 0x00004006,
+	PAGE_FAULT_ERROR_CODE_MATCH     = 0x00004008,
+	CR3_TARGET_COUNT                = 0x0000400a,
+	VM_EXIT_CONTROLS                = 0x0000400c,
+	VM_EXIT_MSR_STORE_COUNT         = 0x0000400e,
+	VM_EXIT_MSR_LOAD_COUNT          = 0x00004010,
+	VM_ENTRY_CONTROLS               = 0x00004012,
+	VM_ENTRY_MSR_LOAD_COUNT         = 0x00004014,
+	VM_ENTRY_INTR_INFO_FIELD        = 0x00004016,
+	VM_ENTRY_EXCEPTION_ERROR_CODE   = 0x00004018,
+	VM_ENTRY_INSTRUCTION_LEN        = 0x0000401a,
+	TPR_THRESHOLD                   = 0x0000401c,
+	SECONDARY_VM_EXEC_CONTROL       = 0x0000401e,
+	VM_INSTRUCTION_ERROR            = 0x00004400,
+	VM_EXIT_REASON                  = 0x00004402,
+	VM_EXIT_INTR_INFO               = 0x00004404,
+	VM_EXIT_INTR_ERROR_CODE         = 0x00004406,
+	IDT_VECTORING_INFO_FIELD        = 0x00004408,
+	IDT_VECTORING_ERROR_CODE        = 0x0000440a,
+	VM_EXIT_INSTRUCTION_LEN         = 0x0000440c,
+	VMX_INSTRUCTION_INFO            = 0x0000440e,
+	GUEST_ES_LIMIT                  = 0x00004800,
+	GUEST_CS_LIMIT                  = 0x00004802,
+	GUEST_SS_LIMIT                  = 0x00004804,
+	GUEST_DS_LIMIT                  = 0x00004806,
+	GUEST_FS_LIMIT                  = 0x00004808,
+	GUEST_GS_LIMIT                  = 0x0000480a,
+	GUEST_LDTR_LIMIT                = 0x0000480c,
+	GUEST_TR_LIMIT                  = 0x0000480e,
+	GUEST_GDTR_LIMIT                = 0x00004810,
+	GUEST_IDTR_LIMIT                = 0x00004812,
+	GUEST_ES_AR_BYTES               = 0x00004814,
+	GUEST_CS_AR_BYTES               = 0x00004816,
+	GUEST_SS_AR_BYTES               = 0x00004818,
+	GUEST_DS_AR_BYTES               = 0x0000481a,
+	GUEST_FS_AR_BYTES               = 0x0000481c,
+	GUEST_GS_AR_BYTES               = 0x0000481e,
+	GUEST_LDTR_AR_BYTES             = 0x00004820,
+	GUEST_TR_AR_BYTES               = 0x00004822,
+	GUEST_INTERRUPTIBILITY_INFO     = 0x00004824,
+	GUEST_ACTIVITY_STATE            = 0X00004826,
+	GUEST_SYSENTER_CS               = 0x0000482A,
+	HOST_IA32_SYSENTER_CS           = 0x00004c00,
+	CR0_GUEST_HOST_MASK             = 0x00006000,
+	CR4_GUEST_HOST_MASK             = 0x00006002,
+	CR0_READ_SHADOW                 = 0x00006004,
+	CR4_READ_SHADOW                 = 0x00006006,
+	CR3_TARGET_VALUE0               = 0x00006008,
+	CR3_TARGET_VALUE1               = 0x0000600a,
+	CR3_TARGET_VALUE2               = 0x0000600c,
+	CR3_TARGET_VALUE3               = 0x0000600e,
+	EXIT_QUALIFICATION              = 0x00006400,
+	GUEST_LINEAR_ADDRESS            = 0x0000640a,
+	GUEST_CR0                       = 0x00006800,
+	GUEST_CR3                       = 0x00006802,
+	GUEST_CR4                       = 0x00006804,
+	GUEST_ES_BASE                   = 0x00006806,
+	GUEST_CS_BASE                   = 0x00006808,
+	GUEST_SS_BASE                   = 0x0000680a,
+	GUEST_DS_BASE                   = 0x0000680c,
+	GUEST_FS_BASE                   = 0x0000680e,
+	GUEST_GS_BASE                   = 0x00006810,
+	GUEST_LDTR_BASE                 = 0x00006812,
+	GUEST_TR_BASE                   = 0x00006814,
+	GUEST_GDTR_BASE                 = 0x00006816,
+	GUEST_IDTR_BASE                 = 0x00006818,
+	GUEST_DR7                       = 0x0000681a,
+	GUEST_RSP                       = 0x0000681c,
+	GUEST_RIP                       = 0x0000681e,
+	GUEST_RFLAGS                    = 0x00006820,
+	GUEST_PENDING_DBG_EXCEPTIONS    = 0x00006822,
+	GUEST_SYSENTER_ESP              = 0x00006824,
+	GUEST_SYSENTER_EIP              = 0x00006826,
+	HOST_CR0                        = 0x00006c00,
+	HOST_CR3                        = 0x00006c02,
+	HOST_CR4                        = 0x00006c04,
+	HOST_FS_BASE                    = 0x00006c06,
+	HOST_GS_BASE                    = 0x00006c08,
+	HOST_TR_BASE                    = 0x00006c0a,
+	HOST_GDTR_BASE                  = 0x00006c0c,
+	HOST_IDTR_BASE                  = 0x00006c0e,
+	HOST_IA32_SYSENTER_ESP          = 0x00006c10,
+	HOST_IA32_SYSENTER_EIP          = 0x00006c12,
+	HOST_RSP                        = 0x00006c14,
+	HOST_RIP                        = 0x00006c16,
+};
+
+#define VMX_EXIT_REASONS_FAILED_VMENTRY         0x80000000
+
+#define EXIT_REASON_EXCEPTION_NMI       0
+#define EXIT_REASON_EXTERNAL_INTERRUPT  1
+#define EXIT_REASON_TRIPLE_FAULT        2
+
+#define EXIT_REASON_PENDING_INTERRUPT   7
+#define EXIT_REASON_NMI_WINDOW		8
+#define EXIT_REASON_TASK_SWITCH         9
+#define EXIT_REASON_CPUID               10
+#define EXIT_REASON_HLT                 12
+#define EXIT_REASON_INVLPG              14
+#define EXIT_REASON_RDPMC               15
+#define EXIT_REASON_RDTSC               16
+#define EXIT_REASON_VMCALL              18
+#define EXIT_REASON_VMCLEAR             19
+#define EXIT_REASON_VMLAUNCH            20
+#define EXIT_REASON_VMPTRLD             21
+#define EXIT_REASON_VMPTRST             22
+#define EXIT_REASON_VMREAD              23
+#define EXIT_REASON_VMRESUME            24
+#define EXIT_REASON_VMWRITE             25
+#define EXIT_REASON_VMOFF               26
+#define EXIT_REASON_VMON                27
+#define EXIT_REASON_CR_ACCESS           28
+#define EXIT_REASON_DR_ACCESS           29
+#define EXIT_REASON_IO_INSTRUCTION      30
+#define EXIT_REASON_MSR_READ            31
+#define EXIT_REASON_MSR_WRITE           32
+#define EXIT_REASON_MWAIT_INSTRUCTION   36
+#define EXIT_REASON_TPR_BELOW_THRESHOLD 43
+#define EXIT_REASON_APIC_ACCESS         44
+#define EXIT_REASON_EPT_VIOLATION       48
+#define EXIT_REASON_EPT_MISCONFIG       49
+#define EXIT_REASON_WBINVD		54
+
+/*
+ * Interruption-information format
+ */
+#define INTR_INFO_VECTOR_MASK           0xff            /* 7:0 */
+#define INTR_INFO_INTR_TYPE_MASK        0x700           /* 10:8 */
+#define INTR_INFO_DELIVER_CODE_MASK     0x800           /* 11 */
+#define INTR_INFO_UNBLOCK_NMI		0x1000		/* 12 */
+#define INTR_INFO_VALID_MASK            0x80000000      /* 31 */
+#define INTR_INFO_RESVD_BITS_MASK       0x7ffff000
+
+#define VECTORING_INFO_VECTOR_MASK           	INTR_INFO_VECTOR_MASK
+#define VECTORING_INFO_TYPE_MASK        	INTR_INFO_INTR_TYPE_MASK
+#define VECTORING_INFO_DELIVER_CODE_MASK    	INTR_INFO_DELIVER_CODE_MASK
+#define VECTORING_INFO_VALID_MASK       	INTR_INFO_VALID_MASK
+
+#define INTR_TYPE_EXT_INTR              (0 << 8) /* external interrupt */
+#define INTR_TYPE_NMI_INTR		(2 << 8) /* NMI */
+#define INTR_TYPE_EXCEPTION             (3 << 8) /* processor exception */
+#define INTR_TYPE_SOFT_INTR             (4 << 8) /* software interrupt */
+
+/* GUEST_INTERRUPTIBILITY_INFO flags. */
+#define GUEST_INTR_STATE_STI		0x00000001
+#define GUEST_INTR_STATE_MOV_SS		0x00000002
+#define GUEST_INTR_STATE_SMI		0x00000004
+#define GUEST_INTR_STATE_NMI		0x00000008
+
+/*
+ * Exit Qualifications for MOV for Control Register Access
+ */
+#define CONTROL_REG_ACCESS_NUM          0x7     /* 2:0, number of control reg.*/
+#define CONTROL_REG_ACCESS_TYPE         0x30    /* 5:4, access type */
+#define CONTROL_REG_ACCESS_REG          0xf00   /* 10:8, general purpose reg. */
+#define LMSW_SOURCE_DATA_SHIFT 16
+#define LMSW_SOURCE_DATA  (0xFFFF << LMSW_SOURCE_DATA_SHIFT) /* 16:31 lmsw source */
+#define REG_EAX                         (0 << 8)
+#define REG_ECX                         (1 << 8)
+#define REG_EDX                         (2 << 8)
+#define REG_EBX                         (3 << 8)
+#define REG_ESP                         (4 << 8)
+#define REG_EBP                         (5 << 8)
+#define REG_ESI                         (6 << 8)
+#define REG_EDI                         (7 << 8)
+#define REG_R8                         (8 << 8)
+#define REG_R9                         (9 << 8)
+#define REG_R10                        (10 << 8)
+#define REG_R11                        (11 << 8)
+#define REG_R12                        (12 << 8)
+#define REG_R13                        (13 << 8)
+#define REG_R14                        (14 << 8)
+#define REG_R15                        (15 << 8)
+
+/*
+ * Exit Qualifications for MOV for Debug Register Access
+ */
+#define DEBUG_REG_ACCESS_NUM            0x7     /* 2:0, number of debug reg. */
+#define DEBUG_REG_ACCESS_TYPE           0x10    /* 4, direction of access */
+#define TYPE_MOV_TO_DR                  (0 << 4)
+#define TYPE_MOV_FROM_DR                (1 << 4)
+#define DEBUG_REG_ACCESS_REG            0xf00   /* 11:8, general purpose reg. */
+
+
+/* segment AR */
+#define SEGMENT_AR_L_MASK (1 << 13)
+
+#define AR_TYPE_ACCESSES_MASK 1
+#define AR_TYPE_READABLE_MASK (1 << 1)
+#define AR_TYPE_WRITEABLE_MASK (1 << 2)
+#define AR_TYPE_CODE_MASK (1 << 3)
+#define AR_TYPE_MASK 0x0f
+#define AR_TYPE_BUSY_64_TSS 11
+#define AR_TYPE_BUSY_32_TSS 11
+#define AR_TYPE_BUSY_16_TSS 3
+#define AR_TYPE_LDT 2
+
+#define AR_UNUSABLE_MASK (1 << 16)
+#define AR_S_MASK (1 << 4)
+#define AR_P_MASK (1 << 7)
+#define AR_L_MASK (1 << 13)
+#define AR_DB_MASK (1 << 14)
+#define AR_G_MASK (1 << 15)
+#define AR_DPL_SHIFT 5
+#define AR_DPL(ar) (((ar) >> AR_DPL_SHIFT) & 3)
+
+#define AR_RESERVD_MASK 0xfffe0f00
+
+#define APIC_ACCESS_PAGE_PRIVATE_MEMSLOT	9
+#define IDENTITY_PAGETABLE_PRIVATE_MEMSLOT	10
+
+#define VMX_NR_VPIDS				(1 << 16)
+#define VMX_VPID_EXTENT_SINGLE_CONTEXT		1
+#define VMX_VPID_EXTENT_ALL_CONTEXT		2
+
+#define VMX_EPT_EXTENT_INDIVIDUAL_ADDR		0
+#define VMX_EPT_EXTENT_CONTEXT			1
+#define VMX_EPT_EXTENT_GLOBAL			2
+#define VMX_EPT_EXTENT_INDIVIDUAL_BIT		(1ull << 24)
+#define VMX_EPT_EXTENT_CONTEXT_BIT		(1ull << 25)
+#define VMX_EPT_EXTENT_GLOBAL_BIT		(1ull << 26)
+#define VMX_EPT_DEFAULT_GAW			3
+#define VMX_EPT_MAX_GAW				0x4
+#define VMX_EPT_MT_EPTE_SHIFT			3
+#define VMX_EPT_GAW_EPTP_SHIFT			3
+#define VMX_EPT_DEFAULT_MT			0x6ull
+#define VMX_EPT_READABLE_MASK			0x1ull
+#define VMX_EPT_WRITABLE_MASK			0x2ull
+#define VMX_EPT_EXECUTABLE_MASK			0x4ull
+#define VMX_EPT_IGMT_BIT    			(1ull << 6)
+
+#define VMX_EPT_IDENTITY_PAGETABLE_ADDR		0xfffbc000ul
+
+#endif
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index f1983d9..042b89a 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -17,7 +17,6 @@
  *
  */
 
-#include "vmx.h"
 #include "mmu.h"
 
 #include <linux/kvm_host.h>
@@ -33,6 +32,7 @@
 #include <asm/page.h>
 #include <asm/cmpxchg.h>
 #include <asm/io.h>
+#include <asm/vmx.h>
 
 /*
  * When setting this variable to true it enables Two-Dimensional-Paging
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index d06b4dc..e97ef1a 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -16,7 +16,6 @@
  */
 
 #include "irq.h"
-#include "vmx.h"
 #include "mmu.h"
 
 #include <linux/kvm_host.h>
@@ -31,6 +30,7 @@
 
 #include <asm/io.h>
 #include <asm/desc.h>
+#include <asm/vmx.h>
 
 #define __ex(x) __kvm_handle_fault_on_reboot(x)
 
diff --git a/arch/x86/kvm/vmx.h b/arch/x86/kvm/vmx.h
deleted file mode 100644
index ec5edc3..0000000
--- a/arch/x86/kvm/vmx.h
+++ /dev/null
@@ -1,359 +0,0 @@
-#ifndef VMX_H
-#define VMX_H
-
-/*
- * vmx.h: VMX Architecture related definitions
- * Copyright (c) 2004, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
- * Place - Suite 330, Boston, MA 02111-1307 USA.
- *
- * A few random additions are:
- * Copyright (C) 2006 Qumranet
- *    Avi Kivity <avi-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
- *    Yaniv Kamay <yaniv-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
- *
- */
-
-/*
- * Definitions of Primary Processor-Based VM-Execution Controls.
- */
-#define CPU_BASED_VIRTUAL_INTR_PENDING          0x00000004
-#define CPU_BASED_USE_TSC_OFFSETING             0x00000008
-#define CPU_BASED_HLT_EXITING                   0x00000080
-#define CPU_BASED_INVLPG_EXITING                0x00000200
-#define CPU_BASED_MWAIT_EXITING                 0x00000400
-#define CPU_BASED_RDPMC_EXITING                 0x00000800
-#define CPU_BASED_RDTSC_EXITING                 0x00001000
-#define CPU_BASED_CR3_LOAD_EXITING		0x00008000
-#define CPU_BASED_CR3_STORE_EXITING		0x00010000
-#define CPU_BASED_CR8_LOAD_EXITING              0x00080000
-#define CPU_BASED_CR8_STORE_EXITING             0x00100000
-#define CPU_BASED_TPR_SHADOW                    0x00200000
-#define CPU_BASED_VIRTUAL_NMI_PENDING		0x00400000
-#define CPU_BASED_MOV_DR_EXITING                0x00800000
-#define CPU_BASED_UNCOND_IO_EXITING             0x01000000
-#define CPU_BASED_USE_IO_BITMAPS                0x02000000
-#define CPU_BASED_USE_MSR_BITMAPS               0x10000000
-#define CPU_BASED_MONITOR_EXITING               0x20000000
-#define CPU_BASED_PAUSE_EXITING                 0x40000000
-#define CPU_BASED_ACTIVATE_SECONDARY_CONTROLS   0x80000000
-/*
- * Definitions of Secondary Processor-Based VM-Execution Controls.
- */
-#define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001
-#define SECONDARY_EXEC_ENABLE_EPT               0x00000002
-#define SECONDARY_EXEC_ENABLE_VPID              0x00000020
-#define SECONDARY_EXEC_WBINVD_EXITING		0x00000040
-
-
-#define PIN_BASED_EXT_INTR_MASK                 0x00000001
-#define PIN_BASED_NMI_EXITING                   0x00000008
-#define PIN_BASED_VIRTUAL_NMIS                  0x00000020
-
-#define VM_EXIT_HOST_ADDR_SPACE_SIZE            0x00000200
-#define VM_EXIT_ACK_INTR_ON_EXIT                0x00008000
-
-#define VM_ENTRY_IA32E_MODE                     0x00000200
-#define VM_ENTRY_SMM                            0x00000400
-#define VM_ENTRY_DEACT_DUAL_MONITOR             0x00000800
-
-/* VMCS Encodings */
-enum vmcs_field {
-	VIRTUAL_PROCESSOR_ID            = 0x00000000,
-	GUEST_ES_SELECTOR               = 0x00000800,
-	GUEST_CS_SELECTOR               = 0x00000802,
-	GUEST_SS_SELECTOR               = 0x00000804,
-	GUEST_DS_SELECTOR               = 0x00000806,
-	GUEST_FS_SELECTOR               = 0x00000808,
-	GUEST_GS_SELECTOR               = 0x0000080a,
-	GUEST_LDTR_SELECTOR             = 0x0000080c,
-	GUEST_TR_SELECTOR               = 0x0000080e,
-	HOST_ES_SELECTOR                = 0x00000c00,
-	HOST_CS_SELECTOR                = 0x00000c02,
-	HOST_SS_SELECTOR                = 0x00000c04,
-	HOST_DS_SELECTOR                = 0x00000c06,
-	HOST_FS_SELECTOR                = 0x00000c08,
-	HOST_GS_SELECTOR                = 0x00000c0a,
-	HOST_TR_SELECTOR                = 0x00000c0c,
-	IO_BITMAP_A                     = 0x00002000,
-	IO_BITMAP_A_HIGH                = 0x00002001,
-	IO_BITMAP_B                     = 0x00002002,
-	IO_BITMAP_B_HIGH                = 0x00002003,
-	MSR_BITMAP                      = 0x00002004,
-	MSR_BITMAP_HIGH                 = 0x00002005,
-	VM_EXIT_MSR_STORE_ADDR          = 0x00002006,
-	VM_EXIT_MSR_STORE_ADDR_HIGH     = 0x00002007,
-	VM_EXIT_MSR_LOAD_ADDR           = 0x00002008,
-	VM_EXIT_MSR_LOAD_ADDR_HIGH      = 0x00002009,
-	VM_ENTRY_MSR_LOAD_ADDR          = 0x0000200a,
-	VM_ENTRY_MSR_LOAD_ADDR_HIGH     = 0x0000200b,
-	TSC_OFFSET                      = 0x00002010,
-	TSC_OFFSET_HIGH                 = 0x00002011,
-	VIRTUAL_APIC_PAGE_ADDR          = 0x00002012,
-	VIRTUAL_APIC_PAGE_ADDR_HIGH     = 0x00002013,
-	APIC_ACCESS_ADDR		= 0x00002014,
-	APIC_ACCESS_ADDR_HIGH		= 0x00002015,
-	EPT_POINTER                     = 0x0000201a,
-	EPT_POINTER_HIGH                = 0x0000201b,
-	GUEST_PHYSICAL_ADDRESS          = 0x00002400,
-	GUEST_PHYSICAL_ADDRESS_HIGH     = 0x00002401,
-	VMCS_LINK_POINTER               = 0x00002800,
-	VMCS_LINK_POINTER_HIGH          = 0x00002801,
-	GUEST_IA32_DEBUGCTL             = 0x00002802,
-	GUEST_IA32_DEBUGCTL_HIGH        = 0x00002803,
-	GUEST_PDPTR0                    = 0x0000280a,
-	GUEST_PDPTR0_HIGH               = 0x0000280b,
-	GUEST_PDPTR1                    = 0x0000280c,
-	GUEST_PDPTR1_HIGH               = 0x0000280d,
-	GUEST_PDPTR2                    = 0x0000280e,
-	GUEST_PDPTR2_HIGH               = 0x0000280f,
-	GUEST_PDPTR3                    = 0x00002810,
-	GUEST_PDPTR3_HIGH               = 0x00002811,
-	PIN_BASED_VM_EXEC_CONTROL       = 0x00004000,
-	CPU_BASED_VM_EXEC_CONTROL       = 0x00004002,
-	EXCEPTION_BITMAP                = 0x00004004,
-	PAGE_FAULT_ERROR_CODE_MASK      = 0x00004006,
-	PAGE_FAULT_ERROR_CODE_MATCH     = 0x00004008,
-	CR3_TARGET_COUNT                = 0x0000400a,
-	VM_EXIT_CONTROLS                = 0x0000400c,
-	VM_EXIT_MSR_STORE_COUNT         = 0x0000400e,
-	VM_EXIT_MSR_LOAD_COUNT          = 0x00004010,
-	VM_ENTRY_CONTROLS               = 0x00004012,
-	VM_ENTRY_MSR_LOAD_COUNT         = 0x00004014,
-	VM_ENTRY_INTR_INFO_FIELD        = 0x00004016,
-	VM_ENTRY_EXCEPTION_ERROR_CODE   = 0x00004018,
-	VM_ENTRY_INSTRUCTION_LEN        = 0x0000401a,
-	TPR_THRESHOLD                   = 0x0000401c,
-	SECONDARY_VM_EXEC_CONTROL       = 0x0000401e,
-	VM_INSTRUCTION_ERROR            = 0x00004400,
-	VM_EXIT_REASON                  = 0x00004402,
-	VM_EXIT_INTR_INFO               = 0x00004404,
-	VM_EXIT_INTR_ERROR_CODE         = 0x00004406,
-	IDT_VECTORING_INFO_FIELD        = 0x00004408,
-	IDT_VECTORING_ERROR_CODE        = 0x0000440a,
-	VM_EXIT_INSTRUCTION_LEN         = 0x0000440c,
-	VMX_INSTRUCTION_INFO            = 0x0000440e,
-	GUEST_ES_LIMIT                  = 0x00004800,
-	GUEST_CS_LIMIT                  = 0x00004802,
-	GUEST_SS_LIMIT                  = 0x00004804,
-	GUEST_DS_LIMIT                  = 0x00004806,
-	GUEST_FS_LIMIT                  = 0x00004808,
-	GUEST_GS_LIMIT                  = 0x0000480a,
-	GUEST_LDTR_LIMIT                = 0x0000480c,
-	GUEST_TR_LIMIT                  = 0x0000480e,
-	GUEST_GDTR_LIMIT                = 0x00004810,
-	GUEST_IDTR_LIMIT                = 0x00004812,
-	GUEST_ES_AR_BYTES               = 0x00004814,
-	GUEST_CS_AR_BYTES               = 0x00004816,
-	GUEST_SS_AR_BYTES               = 0x00004818,
-	GUEST_DS_AR_BYTES               = 0x0000481a,
-	GUEST_FS_AR_BYTES               = 0x0000481c,
-	GUEST_GS_AR_BYTES               = 0x0000481e,
-	GUEST_LDTR_AR_BYTES             = 0x00004820,
-	GUEST_TR_AR_BYTES               = 0x00004822,
-	GUEST_INTERRUPTIBILITY_INFO     = 0x00004824,
-	GUEST_ACTIVITY_STATE            = 0X00004826,
-	GUEST_SYSENTER_CS               = 0x0000482A,
-	HOST_IA32_SYSENTER_CS           = 0x00004c00,
-	CR0_GUEST_HOST_MASK             = 0x00006000,
-	CR4_GUEST_HOST_MASK             = 0x00006002,
-	CR0_READ_SHADOW                 = 0x00006004,
-	CR4_READ_SHADOW                 = 0x00006006,
-	CR3_TARGET_VALUE0               = 0x00006008,
-	CR3_TARGET_VALUE1               = 0x0000600a,
-	CR3_TARGET_VALUE2               = 0x0000600c,
-	CR3_TARGET_VALUE3               = 0x0000600e,
-	EXIT_QUALIFICATION              = 0x00006400,
-	GUEST_LINEAR_ADDRESS            = 0x0000640a,
-	GUEST_CR0                       = 0x00006800,
-	GUEST_CR3                       = 0x00006802,
-	GUEST_CR4                       = 0x00006804,
-	GUEST_ES_BASE                   = 0x00006806,
-	GUEST_CS_BASE                   = 0x00006808,
-	GUEST_SS_BASE                   = 0x0000680a,
-	GUEST_DS_BASE                   = 0x0000680c,
-	GUEST_FS_BASE                   = 0x0000680e,
-	GUEST_GS_BASE                   = 0x00006810,
-	GUEST_LDTR_BASE                 = 0x00006812,
-	GUEST_TR_BASE                   = 0x00006814,
-	GUEST_GDTR_BASE                 = 0x00006816,
-	GUEST_IDTR_BASE                 = 0x00006818,
-	GUEST_DR7                       = 0x0000681a,
-	GUEST_RSP                       = 0x0000681c,
-	GUEST_RIP                       = 0x0000681e,
-	GUEST_RFLAGS                    = 0x00006820,
-	GUEST_PENDING_DBG_EXCEPTIONS    = 0x00006822,
-	GUEST_SYSENTER_ESP              = 0x00006824,
-	GUEST_SYSENTER_EIP              = 0x00006826,
-	HOST_CR0                        = 0x00006c00,
-	HOST_CR3                        = 0x00006c02,
-	HOST_CR4                        = 0x00006c04,
-	HOST_FS_BASE                    = 0x00006c06,
-	HOST_GS_BASE                    = 0x00006c08,
-	HOST_TR_BASE                    = 0x00006c0a,
-	HOST_GDTR_BASE                  = 0x00006c0c,
-	HOST_IDTR_BASE                  = 0x00006c0e,
-	HOST_IA32_SYSENTER_ESP          = 0x00006c10,
-	HOST_IA32_SYSENTER_EIP          = 0x00006c12,
-	HOST_RSP                        = 0x00006c14,
-	HOST_RIP                        = 0x00006c16,
-};
-
-#define VMX_EXIT_REASONS_FAILED_VMENTRY         0x80000000
-
-#define EXIT_REASON_EXCEPTION_NMI       0
-#define EXIT_REASON_EXTERNAL_INTERRUPT  1
-#define EXIT_REASON_TRIPLE_FAULT        2
-
-#define EXIT_REASON_PENDING_INTERRUPT   7
-#define EXIT_REASON_NMI_WINDOW		8
-#define EXIT_REASON_TASK_SWITCH         9
-#define EXIT_REASON_CPUID               10
-#define EXIT_REASON_HLT                 12
-#define EXIT_REASON_INVLPG              14
-#define EXIT_REASON_RDPMC               15
-#define EXIT_REASON_RDTSC               16
-#define EXIT_REASON_VMCALL              18
-#define EXIT_REASON_VMCLEAR             19
-#define EXIT_REASON_VMLAUNCH            20
-#define EXIT_REASON_VMPTRLD             21
-#define EXIT_REASON_VMPTRST             22
-#define EXIT_REASON_VMREAD              23
-#define EXIT_REASON_VMRESUME            24
-#define EXIT_REASON_VMWRITE             25
-#define EXIT_REASON_VMOFF               26
-#define EXIT_REASON_VMON                27
-#define EXIT_REASON_CR_ACCESS           28
-#define EXIT_REASON_DR_ACCESS           29
-#define EXIT_REASON_IO_INSTRUCTION      30
-#define EXIT_REASON_MSR_READ            31
-#define EXIT_REASON_MSR_WRITE           32
-#define EXIT_REASON_MWAIT_INSTRUCTION   36
-#define EXIT_REASON_TPR_BELOW_THRESHOLD 43
-#define EXIT_REASON_APIC_ACCESS         44
-#define EXIT_REASON_EPT_VIOLATION       48
-#define EXIT_REASON_EPT_MISCONFIG       49
-#define EXIT_REASON_WBINVD		54
-
-/*
- * Interruption-information format
- */
-#define INTR_INFO_VECTOR_MASK           0xff            /* 7:0 */
-#define INTR_INFO_INTR_TYPE_MASK        0x700           /* 10:8 */
-#define INTR_INFO_DELIVER_CODE_MASK     0x800           /* 11 */
-#define INTR_INFO_UNBLOCK_NMI		0x1000		/* 12 */
-#define INTR_INFO_VALID_MASK            0x80000000      /* 31 */
-#define INTR_INFO_RESVD_BITS_MASK       0x7ffff000
-
-#define VECTORING_INFO_VECTOR_MASK           	INTR_INFO_VECTOR_MASK
-#define VECTORING_INFO_TYPE_MASK        	INTR_INFO_INTR_TYPE_MASK
-#define VECTORING_INFO_DELIVER_CODE_MASK    	INTR_INFO_DELIVER_CODE_MASK
-#define VECTORING_INFO_VALID_MASK       	INTR_INFO_VALID_MASK
-
-#define INTR_TYPE_EXT_INTR              (0 << 8) /* external interrupt */
-#define INTR_TYPE_NMI_INTR		(2 << 8) /* NMI */
-#define INTR_TYPE_EXCEPTION             (3 << 8) /* processor exception */
-#define INTR_TYPE_SOFT_INTR             (4 << 8) /* software interrupt */
-
-/* GUEST_INTERRUPTIBILITY_INFO flags. */
-#define GUEST_INTR_STATE_STI		0x00000001
-#define GUEST_INTR_STATE_MOV_SS		0x00000002
-#define GUEST_INTR_STATE_SMI		0x00000004
-#define GUEST_INTR_STATE_NMI		0x00000008
-
-/*
- * Exit Qualifications for MOV for Control Register Access
- */
-#define CONTROL_REG_ACCESS_NUM          0x7     /* 2:0, number of control reg.*/
-#define CONTROL_REG_ACCESS_TYPE         0x30    /* 5:4, access type */
-#define CONTROL_REG_ACCESS_REG          0xf00   /* 10:8, general purpose reg. */
-#define LMSW_SOURCE_DATA_SHIFT 16
-#define LMSW_SOURCE_DATA  (0xFFFF << LMSW_SOURCE_DATA_SHIFT) /* 16:31 lmsw source */
-#define REG_EAX                         (0 << 8)
-#define REG_ECX                         (1 << 8)
-#define REG_EDX                         (2 << 8)
-#define REG_EBX                         (3 << 8)
-#define REG_ESP                         (4 << 8)
-#define REG_EBP                         (5 << 8)
-#define REG_ESI                         (6 << 8)
-#define REG_EDI                         (7 << 8)
-#define REG_R8                         (8 << 8)
-#define REG_R9                         (9 << 8)
-#define REG_R10                        (10 << 8)
-#define REG_R11                        (11 << 8)
-#define REG_R12                        (12 << 8)
-#define REG_R13                        (13 << 8)
-#define REG_R14                        (14 << 8)
-#define REG_R15                        (15 << 8)
-
-/*
- * Exit Qualifications for MOV for Debug Register Access
- */
-#define DEBUG_REG_ACCESS_NUM            0x7     /* 2:0, number of debug reg. */
-#define DEBUG_REG_ACCESS_TYPE           0x10    /* 4, direction of access */
-#define TYPE_MOV_TO_DR                  (0 << 4)
-#define TYPE_MOV_FROM_DR                (1 << 4)
-#define DEBUG_REG_ACCESS_REG            0xf00   /* 11:8, general purpose reg. */
-
-
-/* segment AR */
-#define SEGMENT_AR_L_MASK (1 << 13)
-
-#define AR_TYPE_ACCESSES_MASK 1
-#define AR_TYPE_READABLE_MASK (1 << 1)
-#define AR_TYPE_WRITEABLE_MASK (1 << 2)
-#define AR_TYPE_CODE_MASK (1 << 3)
-#define AR_TYPE_MASK 0x0f
-#define AR_TYPE_BUSY_64_TSS 11
-#define AR_TYPE_BUSY_32_TSS 11
-#define AR_TYPE_BUSY_16_TSS 3
-#define AR_TYPE_LDT 2
-
-#define AR_UNUSABLE_MASK (1 << 16)
-#define AR_S_MASK (1 << 4)
-#define AR_P_MASK (1 << 7)
-#define AR_L_MASK (1 << 13)
-#define AR_DB_MASK (1 << 14)
-#define AR_G_MASK (1 << 15)
-#define AR_DPL_SHIFT 5
-#define AR_DPL(ar) (((ar) >> AR_DPL_SHIFT) & 3)
-
-#define AR_RESERVD_MASK 0xfffe0f00
-
-#define APIC_ACCESS_PAGE_PRIVATE_MEMSLOT	9
-#define IDENTITY_PAGETABLE_PRIVATE_MEMSLOT	10
-
-#define VMX_NR_VPIDS				(1 << 16)
-#define VMX_VPID_EXTENT_SINGLE_CONTEXT		1
-#define VMX_VPID_EXTENT_ALL_CONTEXT		2
-
-#define VMX_EPT_EXTENT_INDIVIDUAL_ADDR		0
-#define VMX_EPT_EXTENT_CONTEXT			1
-#define VMX_EPT_EXTENT_GLOBAL			2
-#define VMX_EPT_EXTENT_INDIVIDUAL_BIT		(1ull << 24)
-#define VMX_EPT_EXTENT_CONTEXT_BIT		(1ull << 25)
-#define VMX_EPT_EXTENT_GLOBAL_BIT		(1ull << 26)
-#define VMX_EPT_DEFAULT_GAW			3
-#define VMX_EPT_MAX_GAW				0x4
-#define VMX_EPT_MT_EPTE_SHIFT			3
-#define VMX_EPT_GAW_EPTP_SHIFT			3
-#define VMX_EPT_DEFAULT_MT			0x6ull
-#define VMX_EPT_READABLE_MASK			0x1ull
-#define VMX_EPT_WRITABLE_MASK			0x2ull
-#define VMX_EPT_EXECUTABLE_MASK			0x4ull
-#define VMX_EPT_IGMT_BIT    			(1ull << 6)
-
-#define VMX_EPT_IDENTITY_PAGETABLE_ADDR		0xfffbc000ul
-
-#endif
-- 
1.5.5.GIT

[PATCH 02/12] kvm: svm: move svm.h to include/asm

[Eduardo Habkost]

svm.h will be used by core code that is independent of KVM, so I am
moving it outside the arch/x86/kvm directory.

Signed-off-by: Eduardo Habkost <ehabkost-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
---
 arch/x86/include/asm/svm.h |  328 ++++++++++++++++++++++++++++++++++++++++++++
 arch/x86/kvm/kvm_svm.h     |    2 +-
 arch/x86/kvm/svm.h         |  328 --------------------------------------------
 3 files changed, 329 insertions(+), 329 deletions(-)
 create mode 100644 arch/x86/include/asm/svm.h
 delete mode 100644 arch/x86/kvm/svm.h

diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
new file mode 100644
index 0000000..1b8afa7
--- /dev/null
+++ b/arch/x86/include/asm/svm.h
@@ -0,0 +1,328 @@
+#ifndef __SVM_H
+#define __SVM_H
+
+enum {
+	INTERCEPT_INTR,
+	INTERCEPT_NMI,
+	INTERCEPT_SMI,
+	INTERCEPT_INIT,
+	INTERCEPT_VINTR,
+	INTERCEPT_SELECTIVE_CR0,
+	INTERCEPT_STORE_IDTR,
+	INTERCEPT_STORE_GDTR,
+	INTERCEPT_STORE_LDTR,
+	INTERCEPT_STORE_TR,
+	INTERCEPT_LOAD_IDTR,
+	INTERCEPT_LOAD_GDTR,
+	INTERCEPT_LOAD_LDTR,
+	INTERCEPT_LOAD_TR,
+	INTERCEPT_RDTSC,
+	INTERCEPT_RDPMC,
+	INTERCEPT_PUSHF,
+	INTERCEPT_POPF,
+	INTERCEPT_CPUID,
+	INTERCEPT_RSM,
+	INTERCEPT_IRET,
+	INTERCEPT_INTn,
+	INTERCEPT_INVD,
+	INTERCEPT_PAUSE,
+	INTERCEPT_HLT,
+	INTERCEPT_INVLPG,
+	INTERCEPT_INVLPGA,
+	INTERCEPT_IOIO_PROT,
+	INTERCEPT_MSR_PROT,
+	INTERCEPT_TASK_SWITCH,
+	INTERCEPT_FERR_FREEZE,
+	INTERCEPT_SHUTDOWN,
+	INTERCEPT_VMRUN,
+	INTERCEPT_VMMCALL,
+	INTERCEPT_VMLOAD,
+	INTERCEPT_VMSAVE,
+	INTERCEPT_STGI,
+	INTERCEPT_CLGI,
+	INTERCEPT_SKINIT,
+	INTERCEPT_RDTSCP,
+	INTERCEPT_ICEBP,
+	INTERCEPT_WBINVD,
+	INTERCEPT_MONITOR,
+	INTERCEPT_MWAIT,
+	INTERCEPT_MWAIT_COND,
+};
+
+
+struct __attribute__ ((__packed__)) vmcb_control_area {
+	u16 intercept_cr_read;
+	u16 intercept_cr_write;
+	u16 intercept_dr_read;
+	u16 intercept_dr_write;
+	u32 intercept_exceptions;
+	u64 intercept;
+	u8 reserved_1[44];
+	u64 iopm_base_pa;
+	u64 msrpm_base_pa;
+	u64 tsc_offset;
+	u32 asid;
+	u8 tlb_ctl;
+	u8 reserved_2[3];
+	u32 int_ctl;
+	u32 int_vector;
+	u32 int_state;
+	u8 reserved_3[4];
+	u32 exit_code;
+	u32 exit_code_hi;
+	u64 exit_info_1;
+	u64 exit_info_2;
+	u32 exit_int_info;
+	u32 exit_int_info_err;
+	u64 nested_ctl;
+	u8 reserved_4[16];
+	u32 event_inj;
+	u32 event_inj_err;
+	u64 nested_cr3;
+	u64 lbr_ctl;
+	u8 reserved_5[832];
+};
+
+
+#define TLB_CONTROL_DO_NOTHING 0
+#define TLB_CONTROL_FLUSH_ALL_ASID 1
+
+#define V_TPR_MASK 0x0f
+
+#define V_IRQ_SHIFT 8
+#define V_IRQ_MASK (1 << V_IRQ_SHIFT)
+
+#define V_INTR_PRIO_SHIFT 16
+#define V_INTR_PRIO_MASK (0x0f << V_INTR_PRIO_SHIFT)
+
+#define V_IGN_TPR_SHIFT 20
+#define V_IGN_TPR_MASK (1 << V_IGN_TPR_SHIFT)
+
+#define V_INTR_MASKING_SHIFT 24
+#define V_INTR_MASKING_MASK (1 << V_INTR_MASKING_SHIFT)
+
+#define SVM_INTERRUPT_SHADOW_MASK 1
+
+#define SVM_IOIO_STR_SHIFT 2
+#define SVM_IOIO_REP_SHIFT 3
+#define SVM_IOIO_SIZE_SHIFT 4
+#define SVM_IOIO_ASIZE_SHIFT 7
+
+#define SVM_IOIO_TYPE_MASK 1
+#define SVM_IOIO_STR_MASK (1 << SVM_IOIO_STR_SHIFT)
+#define SVM_IOIO_REP_MASK (1 << SVM_IOIO_REP_SHIFT)
+#define SVM_IOIO_SIZE_MASK (7 << SVM_IOIO_SIZE_SHIFT)
+#define SVM_IOIO_ASIZE_MASK (7 << SVM_IOIO_ASIZE_SHIFT)
+
+struct __attribute__ ((__packed__)) vmcb_seg {
+	u16 selector;
+	u16 attrib;
+	u32 limit;
+	u64 base;
+};
+
+struct __attribute__ ((__packed__)) vmcb_save_area {
+	struct vmcb_seg es;
+	struct vmcb_seg cs;
+	struct vmcb_seg ss;
+	struct vmcb_seg ds;
+	struct vmcb_seg fs;
+	struct vmcb_seg gs;
+	struct vmcb_seg gdtr;
+	struct vmcb_seg ldtr;
+	struct vmcb_seg idtr;
+	struct vmcb_seg tr;
+	u8 reserved_1[43];
+	u8 cpl;
+	u8 reserved_2[4];
+	u64 efer;
+	u8 reserved_3[112];
+	u64 cr4;
+	u64 cr3;
+	u64 cr0;
+	u64 dr7;
+	u64 dr6;
+	u64 rflags;
+	u64 rip;
+	u8 reserved_4[88];
+	u64 rsp;
+	u8 reserved_5[24];
+	u64 rax;
+	u64 star;
+	u64 lstar;
+	u64 cstar;
+	u64 sfmask;
+	u64 kernel_gs_base;
+	u64 sysenter_cs;
+	u64 sysenter_esp;
+	u64 sysenter_eip;
+	u64 cr2;
+	u8 reserved_6[32];
+	u64 g_pat;
+	u64 dbgctl;
+	u64 br_from;
+	u64 br_to;
+	u64 last_excp_from;
+	u64 last_excp_to;
+};
+
+struct __attribute__ ((__packed__)) vmcb {
+	struct vmcb_control_area control;
+	struct vmcb_save_area save;
+};
+
+#define SVM_CPUID_FEATURE_SHIFT 2
+#define SVM_CPUID_FUNC 0x8000000a
+
+#define MSR_EFER_SVME_MASK (1ULL << 12)
+#define MSR_VM_CR       0xc0010114
+#define MSR_VM_HSAVE_PA 0xc0010117ULL
+
+#define SVM_VM_CR_SVM_DISABLE 4
+
+#define SVM_SELECTOR_S_SHIFT 4
+#define SVM_SELECTOR_DPL_SHIFT 5
+#define SVM_SELECTOR_P_SHIFT 7
+#define SVM_SELECTOR_AVL_SHIFT 8
+#define SVM_SELECTOR_L_SHIFT 9
+#define SVM_SELECTOR_DB_SHIFT 10
+#define SVM_SELECTOR_G_SHIFT 11
+
+#define SVM_SELECTOR_TYPE_MASK (0xf)
+#define SVM_SELECTOR_S_MASK (1 << SVM_SELECTOR_S_SHIFT)
+#define SVM_SELECTOR_DPL_MASK (3 << SVM_SELECTOR_DPL_SHIFT)
+#define SVM_SELECTOR_P_MASK (1 << SVM_SELECTOR_P_SHIFT)
+#define SVM_SELECTOR_AVL_MASK (1 << SVM_SELECTOR_AVL_SHIFT)
+#define SVM_SELECTOR_L_MASK (1 << SVM_SELECTOR_L_SHIFT)
+#define SVM_SELECTOR_DB_MASK (1 << SVM_SELECTOR_DB_SHIFT)
+#define SVM_SELECTOR_G_MASK (1 << SVM_SELECTOR_G_SHIFT)
+
+#define SVM_SELECTOR_WRITE_MASK (1 << 1)
+#define SVM_SELECTOR_READ_MASK SVM_SELECTOR_WRITE_MASK
+#define SVM_SELECTOR_CODE_MASK (1 << 3)
+
+#define INTERCEPT_CR0_MASK 1
+#define INTERCEPT_CR3_MASK (1 << 3)
+#define INTERCEPT_CR4_MASK (1 << 4)
+#define INTERCEPT_CR8_MASK (1 << 8)
+
+#define INTERCEPT_DR0_MASK 1
+#define INTERCEPT_DR1_MASK (1 << 1)
+#define INTERCEPT_DR2_MASK (1 << 2)
+#define INTERCEPT_DR3_MASK (1 << 3)
+#define INTERCEPT_DR4_MASK (1 << 4)
+#define INTERCEPT_DR5_MASK (1 << 5)
+#define INTERCEPT_DR6_MASK (1 << 6)
+#define INTERCEPT_DR7_MASK (1 << 7)
+
+#define SVM_EVTINJ_VEC_MASK 0xff
+
+#define SVM_EVTINJ_TYPE_SHIFT 8
+#define SVM_EVTINJ_TYPE_MASK (7 << SVM_EVTINJ_TYPE_SHIFT)
+
+#define SVM_EVTINJ_TYPE_INTR (0 << SVM_EVTINJ_TYPE_SHIFT)
+#define SVM_EVTINJ_TYPE_NMI (2 << SVM_EVTINJ_TYPE_SHIFT)
+#define SVM_EVTINJ_TYPE_EXEPT (3 << SVM_EVTINJ_TYPE_SHIFT)
+#define SVM_EVTINJ_TYPE_SOFT (4 << SVM_EVTINJ_TYPE_SHIFT)
+
+#define SVM_EVTINJ_VALID (1 << 31)
+#define SVM_EVTINJ_VALID_ERR (1 << 11)
+
+#define SVM_EXITINTINFO_VEC_MASK SVM_EVTINJ_VEC_MASK
+
+#define	SVM_EXITINTINFO_TYPE_INTR SVM_EVTINJ_TYPE_INTR
+#define	SVM_EXITINTINFO_TYPE_NMI SVM_EVTINJ_TYPE_NMI
+#define	SVM_EXITINTINFO_TYPE_EXEPT SVM_EVTINJ_TYPE_EXEPT
+#define	SVM_EXITINTINFO_TYPE_SOFT SVM_EVTINJ_TYPE_SOFT
+
+#define SVM_EXITINTINFO_VALID SVM_EVTINJ_VALID
+#define SVM_EXITINTINFO_VALID_ERR SVM_EVTINJ_VALID_ERR
+
+#define SVM_EXITINFOSHIFT_TS_REASON_IRET 36
+#define SVM_EXITINFOSHIFT_TS_REASON_JMP 38
+
+#define	SVM_EXIT_READ_CR0 	0x000
+#define	SVM_EXIT_READ_CR3 	0x003
+#define	SVM_EXIT_READ_CR4 	0x004
+#define	SVM_EXIT_READ_CR8 	0x008
+#define	SVM_EXIT_WRITE_CR0 	0x010
+#define	SVM_EXIT_WRITE_CR3 	0x013
+#define	SVM_EXIT_WRITE_CR4 	0x014
+#define	SVM_EXIT_WRITE_CR8 	0x018
+#define	SVM_EXIT_READ_DR0 	0x020
+#define	SVM_EXIT_READ_DR1 	0x021
+#define	SVM_EXIT_READ_DR2 	0x022
+#define	SVM_EXIT_READ_DR3 	0x023
+#define	SVM_EXIT_READ_DR4 	0x024
+#define	SVM_EXIT_READ_DR5 	0x025
+#define	SVM_EXIT_READ_DR6 	0x026
+#define	SVM_EXIT_READ_DR7 	0x027
+#define	SVM_EXIT_WRITE_DR0 	0x030
+#define	SVM_EXIT_WRITE_DR1 	0x031
+#define	SVM_EXIT_WRITE_DR2 	0x032
+#define	SVM_EXIT_WRITE_DR3 	0x033
+#define	SVM_EXIT_WRITE_DR4 	0x034
+#define	SVM_EXIT_WRITE_DR5 	0x035
+#define	SVM_EXIT_WRITE_DR6 	0x036
+#define	SVM_EXIT_WRITE_DR7 	0x037
+#define SVM_EXIT_EXCP_BASE      0x040
+#define SVM_EXIT_INTR		0x060
+#define SVM_EXIT_NMI		0x061
+#define SVM_EXIT_SMI		0x062
+#define SVM_EXIT_INIT		0x063
+#define SVM_EXIT_VINTR		0x064
+#define SVM_EXIT_CR0_SEL_WRITE	0x065
+#define SVM_EXIT_IDTR_READ	0x066
+#define SVM_EXIT_GDTR_READ	0x067
+#define SVM_EXIT_LDTR_READ	0x068
+#define SVM_EXIT_TR_READ	0x069
+#define SVM_EXIT_IDTR_WRITE	0x06a
+#define SVM_EXIT_GDTR_WRITE	0x06b
+#define SVM_EXIT_LDTR_WRITE	0x06c
+#define SVM_EXIT_TR_WRITE	0x06d
+#define SVM_EXIT_RDTSC		0x06e
+#define SVM_EXIT_RDPMC		0x06f
+#define SVM_EXIT_PUSHF		0x070
+#define SVM_EXIT_POPF		0x071
+#define SVM_EXIT_CPUID		0x072
+#define SVM_EXIT_RSM		0x073
+#define SVM_EXIT_IRET		0x074
+#define SVM_EXIT_SWINT		0x075
+#define SVM_EXIT_INVD		0x076
+#define SVM_EXIT_PAUSE		0x077
+#define SVM_EXIT_HLT		0x078
+#define SVM_EXIT_INVLPG		0x079
+#define SVM_EXIT_INVLPGA	0x07a
+#define SVM_EXIT_IOIO		0x07b
+#define SVM_EXIT_MSR		0x07c
+#define SVM_EXIT_TASK_SWITCH	0x07d
+#define SVM_EXIT_FERR_FREEZE	0x07e
+#define SVM_EXIT_SHUTDOWN	0x07f
+#define SVM_EXIT_VMRUN		0x080
+#define SVM_EXIT_VMMCALL	0x081
+#define SVM_EXIT_VMLOAD		0x082
+#define SVM_EXIT_VMSAVE		0x083
+#define SVM_EXIT_STGI		0x084
+#define SVM_EXIT_CLGI		0x085
+#define SVM_EXIT_SKINIT		0x086
+#define SVM_EXIT_RDTSCP		0x087
+#define SVM_EXIT_ICEBP		0x088
+#define SVM_EXIT_WBINVD		0x089
+#define SVM_EXIT_MONITOR	0x08a
+#define SVM_EXIT_MWAIT		0x08b
+#define SVM_EXIT_MWAIT_COND	0x08c
+#define SVM_EXIT_NPF  		0x400
+
+#define SVM_EXIT_ERR		-1
+
+#define SVM_CR0_SELECTIVE_MASK (1 << 3 | 1) /* TS and MP */
+
+#define SVM_VMLOAD ".byte 0x0f, 0x01, 0xda"
+#define SVM_VMRUN  ".byte 0x0f, 0x01, 0xd8"
+#define SVM_VMSAVE ".byte 0x0f, 0x01, 0xdb"
+#define SVM_CLGI   ".byte 0x0f, 0x01, 0xdd"
+#define SVM_STGI   ".byte 0x0f, 0x01, 0xdc"
+#define SVM_INVLPGA ".byte 0x0f, 0x01, 0xdf"
+
+#endif
+
diff --git a/arch/x86/kvm/kvm_svm.h b/arch/x86/kvm/kvm_svm.h
index 65ef0fc..8e5ee99 100644
--- a/arch/x86/kvm/kvm_svm.h
+++ b/arch/x86/kvm/kvm_svm.h
@@ -7,7 +7,7 @@
 #include <linux/kvm_host.h>
 #include <asm/msr.h>
 
-#include "svm.h"
+#include <asm/svm.h>
 
 static const u32 host_save_user_msrs[] = {
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/kvm/svm.h b/arch/x86/kvm/svm.h
deleted file mode 100644
index 1b8afa7..0000000
--- a/arch/x86/kvm/svm.h
+++ /dev/null
@@ -1,328 +0,0 @@
-#ifndef __SVM_H
-#define __SVM_H
-
-enum {
-	INTERCEPT_INTR,
-	INTERCEPT_NMI,
-	INTERCEPT_SMI,
-	INTERCEPT_INIT,
-	INTERCEPT_VINTR,
-	INTERCEPT_SELECTIVE_CR0,
-	INTERCEPT_STORE_IDTR,
-	INTERCEPT_STORE_GDTR,
-	INTERCEPT_STORE_LDTR,
-	INTERCEPT_STORE_TR,
-	INTERCEPT_LOAD_IDTR,
-	INTERCEPT_LOAD_GDTR,
-	INTERCEPT_LOAD_LDTR,
-	INTERCEPT_LOAD_TR,
-	INTERCEPT_RDTSC,
-	INTERCEPT_RDPMC,
-	INTERCEPT_PUSHF,
-	INTERCEPT_POPF,
-	INTERCEPT_CPUID,
-	INTERCEPT_RSM,
-	INTERCEPT_IRET,
-	INTERCEPT_INTn,
-	INTERCEPT_INVD,
-	INTERCEPT_PAUSE,
-	INTERCEPT_HLT,
-	INTERCEPT_INVLPG,
-	INTERCEPT_INVLPGA,
-	INTERCEPT_IOIO_PROT,
-	INTERCEPT_MSR_PROT,
-	INTERCEPT_TASK_SWITCH,
-	INTERCEPT_FERR_FREEZE,
-	INTERCEPT_SHUTDOWN,
-	INTERCEPT_VMRUN,
-	INTERCEPT_VMMCALL,
-	INTERCEPT_VMLOAD,
-	INTERCEPT_VMSAVE,
-	INTERCEPT_STGI,
-	INTERCEPT_CLGI,
-	INTERCEPT_SKINIT,
-	INTERCEPT_RDTSCP,
-	INTERCEPT_ICEBP,
-	INTERCEPT_WBINVD,
-	INTERCEPT_MONITOR,
-	INTERCEPT_MWAIT,
-	INTERCEPT_MWAIT_COND,
-};
-
-
-struct __attribute__ ((__packed__)) vmcb_control_area {
-	u16 intercept_cr_read;
-	u16 intercept_cr_write;
-	u16 intercept_dr_read;
-	u16 intercept_dr_write;
-	u32 intercept_exceptions;
-	u64 intercept;
-	u8 reserved_1[44];
-	u64 iopm_base_pa;
-	u64 msrpm_base_pa;
-	u64 tsc_offset;
-	u32 asid;
-	u8 tlb_ctl;
-	u8 reserved_2[3];
-	u32 int_ctl;
-	u32 int_vector;
-	u32 int_state;
-	u8 reserved_3[4];
-	u32 exit_code;
-	u32 exit_code_hi;
-	u64 exit_info_1;
-	u64 exit_info_2;
-	u32 exit_int_info;
-	u32 exit_int_info_err;
-	u64 nested_ctl;
-	u8 reserved_4[16];
-	u32 event_inj;
-	u32 event_inj_err;
-	u64 nested_cr3;
-	u64 lbr_ctl;
-	u8 reserved_5[832];
-};
-
-
-#define TLB_CONTROL_DO_NOTHING 0
-#define TLB_CONTROL_FLUSH_ALL_ASID 1
-
-#define V_TPR_MASK 0x0f
-
-#define V_IRQ_SHIFT 8
-#define V_IRQ_MASK (1 << V_IRQ_SHIFT)
-
-#define V_INTR_PRIO_SHIFT 16
-#define V_INTR_PRIO_MASK (0x0f << V_INTR_PRIO_SHIFT)
-
-#define V_IGN_TPR_SHIFT 20
-#define V_IGN_TPR_MASK (1 << V_IGN_TPR_SHIFT)
-
-#define V_INTR_MASKING_SHIFT 24
-#define V_INTR_MASKING_MASK (1 << V_INTR_MASKING_SHIFT)
-
-#define SVM_INTERRUPT_SHADOW_MASK 1
-
-#define SVM_IOIO_STR_SHIFT 2
-#define SVM_IOIO_REP_SHIFT 3
-#define SVM_IOIO_SIZE_SHIFT 4
-#define SVM_IOIO_ASIZE_SHIFT 7
-
-#define SVM_IOIO_TYPE_MASK 1
-#define SVM_IOIO_STR_MASK (1 << SVM_IOIO_STR_SHIFT)
-#define SVM_IOIO_REP_MASK (1 << SVM_IOIO_REP_SHIFT)
-#define SVM_IOIO_SIZE_MASK (7 << SVM_IOIO_SIZE_SHIFT)
-#define SVM_IOIO_ASIZE_MASK (7 << SVM_IOIO_ASIZE_SHIFT)
-
-struct __attribute__ ((__packed__)) vmcb_seg {
-	u16 selector;
-	u16 attrib;
-	u32 limit;
-	u64 base;
-};
-
-struct __attribute__ ((__packed__)) vmcb_save_area {
-	struct vmcb_seg es;
-	struct vmcb_seg cs;
-	struct vmcb_seg ss;
-	struct vmcb_seg ds;
-	struct vmcb_seg fs;
-	struct vmcb_seg gs;
-	struct vmcb_seg gdtr;
-	struct vmcb_seg ldtr;
-	struct vmcb_seg idtr;
-	struct vmcb_seg tr;
-	u8 reserved_1[43];
-	u8 cpl;
-	u8 reserved_2[4];
-	u64 efer;
-	u8 reserved_3[112];
-	u64 cr4;
-	u64 cr3;
-	u64 cr0;
-	u64 dr7;
-	u64 dr6;
-	u64 rflags;
-	u64 rip;
-	u8 reserved_4[88];
-	u64 rsp;
-	u8 reserved_5[24];
-	u64 rax;
-	u64 star;
-	u64 lstar;
-	u64 cstar;
-	u64 sfmask;
-	u64 kernel_gs_base;
-	u64 sysenter_cs;
-	u64 sysenter_esp;
-	u64 sysenter_eip;
-	u64 cr2;
-	u8 reserved_6[32];
-	u64 g_pat;
-	u64 dbgctl;
-	u64 br_from;
-	u64 br_to;
-	u64 last_excp_from;
-	u64 last_excp_to;
-};
-
-struct __attribute__ ((__packed__)) vmcb {
-	struct vmcb_control_area control;
-	struct vmcb_save_area save;
-};
-
-#define SVM_CPUID_FEATURE_SHIFT 2
-#define SVM_CPUID_FUNC 0x8000000a
-
-#define MSR_EFER_SVME_MASK (1ULL << 12)
-#define MSR_VM_CR       0xc0010114
-#define MSR_VM_HSAVE_PA 0xc0010117ULL
-
-#define SVM_VM_CR_SVM_DISABLE 4
-
-#define SVM_SELECTOR_S_SHIFT 4
-#define SVM_SELECTOR_DPL_SHIFT 5
-#define SVM_SELECTOR_P_SHIFT 7
-#define SVM_SELECTOR_AVL_SHIFT 8
-#define SVM_SELECTOR_L_SHIFT 9
-#define SVM_SELECTOR_DB_SHIFT 10
-#define SVM_SELECTOR_G_SHIFT 11
-
-#define SVM_SELECTOR_TYPE_MASK (0xf)
-#define SVM_SELECTOR_S_MASK (1 << SVM_SELECTOR_S_SHIFT)
-#define SVM_SELECTOR_DPL_MASK (3 << SVM_SELECTOR_DPL_SHIFT)
-#define SVM_SELECTOR_P_MASK (1 << SVM_SELECTOR_P_SHIFT)
-#define SVM_SELECTOR_AVL_MASK (1 << SVM_SELECTOR_AVL_SHIFT)
-#define SVM_SELECTOR_L_MASK (1 << SVM_SELECTOR_L_SHIFT)
-#define SVM_SELECTOR_DB_MASK (1 << SVM_SELECTOR_DB_SHIFT)
-#define SVM_SELECTOR_G_MASK (1 << SVM_SELECTOR_G_SHIFT)
-
-#define SVM_SELECTOR_WRITE_MASK (1 << 1)
-#define SVM_SELECTOR_READ_MASK SVM_SELECTOR_WRITE_MASK
-#define SVM_SELECTOR_CODE_MASK (1 << 3)
-
-#define INTERCEPT_CR0_MASK 1
-#define INTERCEPT_CR3_MASK (1 << 3)
-#define INTERCEPT_CR4_MASK (1 << 4)
-#define INTERCEPT_CR8_MASK (1 << 8)
-
-#define INTERCEPT_DR0_MASK 1
-#define INTERCEPT_DR1_MASK (1 << 1)
-#define INTERCEPT_DR2_MASK (1 << 2)
-#define INTERCEPT_DR3_MASK (1 << 3)
-#define INTERCEPT_DR4_MASK (1 << 4)
-#define INTERCEPT_DR5_MASK (1 << 5)
-#define INTERCEPT_DR6_MASK (1 << 6)
-#define INTERCEPT_DR7_MASK (1 << 7)
-
-#define SVM_EVTINJ_VEC_MASK 0xff
-
-#define SVM_EVTINJ_TYPE_SHIFT 8
-#define SVM_EVTINJ_TYPE_MASK (7 << SVM_EVTINJ_TYPE_SHIFT)
-
-#define SVM_EVTINJ_TYPE_INTR (0 << SVM_EVTINJ_TYPE_SHIFT)
-#define SVM_EVTINJ_TYPE_NMI (2 << SVM_EVTINJ_TYPE_SHIFT)
-#define SVM_EVTINJ_TYPE_EXEPT (3 << SVM_EVTINJ_TYPE_SHIFT)
-#define SVM_EVTINJ_TYPE_SOFT (4 << SVM_EVTINJ_TYPE_SHIFT)
-
-#define SVM_EVTINJ_VALID (1 << 31)
-#define SVM_EVTINJ_VALID_ERR (1 << 11)
-
-#define SVM_EXITINTINFO_VEC_MASK SVM_EVTINJ_VEC_MASK
-
-#define	SVM_EXITINTINFO_TYPE_INTR SVM_EVTINJ_TYPE_INTR
-#define	SVM_EXITINTINFO_TYPE_NMI SVM_EVTINJ_TYPE_NMI
-#define	SVM_EXITINTINFO_TYPE_EXEPT SVM_EVTINJ_TYPE_EXEPT
-#define	SVM_EXITINTINFO_TYPE_SOFT SVM_EVTINJ_TYPE_SOFT
-
-#define SVM_EXITINTINFO_VALID SVM_EVTINJ_VALID
-#define SVM_EXITINTINFO_VALID_ERR SVM_EVTINJ_VALID_ERR
-
-#define SVM_EXITINFOSHIFT_TS_REASON_IRET 36
-#define SVM_EXITINFOSHIFT_TS_REASON_JMP 38
-
-#define	SVM_EXIT_READ_CR0 	0x000
-#define	SVM_EXIT_READ_CR3 	0x003
-#define	SVM_EXIT_READ_CR4 	0x004
-#define	SVM_EXIT_READ_CR8 	0x008
-#define	SVM_EXIT_WRITE_CR0 	0x010
-#define	SVM_EXIT_WRITE_CR3 	0x013
-#define	SVM_EXIT_WRITE_CR4 	0x014
-#define	SVM_EXIT_WRITE_CR8 	0x018
-#define	SVM_EXIT_READ_DR0 	0x020
-#define	SVM_EXIT_READ_DR1 	0x021
-#define	SVM_EXIT_READ_DR2 	0x022
-#define	SVM_EXIT_READ_DR3 	0x023
-#define	SVM_EXIT_READ_DR4 	0x024
-#define	SVM_EXIT_READ_DR5 	0x025
-#define	SVM_EXIT_READ_DR6 	0x026
-#define	SVM_EXIT_READ_DR7 	0x027
-#define	SVM_EXIT_WRITE_DR0 	0x030
-#define	SVM_EXIT_WRITE_DR1 	0x031
-#define	SVM_EXIT_WRITE_DR2 	0x032
-#define	SVM_EXIT_WRITE_DR3 	0x033
-#define	SVM_EXIT_WRITE_DR4 	0x034
-#define	SVM_EXIT_WRITE_DR5 	0x035
-#define	SVM_EXIT_WRITE_DR6 	0x036
-#define	SVM_EXIT_WRITE_DR7 	0x037
-#define SVM_EXIT_EXCP_BASE      0x040
-#define SVM_EXIT_INTR		0x060
-#define SVM_EXIT_NMI		0x061
-#define SVM_EXIT_SMI		0x062
-#define SVM_EXIT_INIT		0x063
-#define SVM_EXIT_VINTR		0x064
-#define SVM_EXIT_CR0_SEL_WRITE	0x065
-#define SVM_EXIT_IDTR_READ	0x066
-#define SVM_EXIT_GDTR_READ	0x067
-#define SVM_EXIT_LDTR_READ	0x068
-#define SVM_EXIT_TR_READ	0x069
-#define SVM_EXIT_IDTR_WRITE	0x06a
-#define SVM_EXIT_GDTR_WRITE	0x06b
-#define SVM_EXIT_LDTR_WRITE	0x06c
-#define SVM_EXIT_TR_WRITE	0x06d
-#define SVM_EXIT_RDTSC		0x06e
-#define SVM_EXIT_RDPMC		0x06f
-#define SVM_EXIT_PUSHF		0x070
-#define SVM_EXIT_POPF		0x071
-#define SVM_EXIT_CPUID		0x072
-#define SVM_EXIT_RSM		0x073
-#define SVM_EXIT_IRET		0x074
-#define SVM_EXIT_SWINT		0x075
-#define SVM_EXIT_INVD		0x076
-#define SVM_EXIT_PAUSE		0x077
-#define SVM_EXIT_HLT		0x078
-#define SVM_EXIT_INVLPG		0x079
-#define SVM_EXIT_INVLPGA	0x07a
-#define SVM_EXIT_IOIO		0x07b
-#define SVM_EXIT_MSR		0x07c
-#define SVM_EXIT_TASK_SWITCH	0x07d
-#define SVM_EXIT_FERR_FREEZE	0x07e
-#define SVM_EXIT_SHUTDOWN	0x07f
-#define SVM_EXIT_VMRUN		0x080
-#define SVM_EXIT_VMMCALL	0x081
-#define SVM_EXIT_VMLOAD		0x082
-#define SVM_EXIT_VMSAVE		0x083
-#define SVM_EXIT_STGI		0x084
-#define SVM_EXIT_CLGI		0x085
-#define SVM_EXIT_SKINIT		0x086
-#define SVM_EXIT_RDTSCP		0x087
-#define SVM_EXIT_ICEBP		0x088
-#define SVM_EXIT_WBINVD		0x089
-#define SVM_EXIT_MONITOR	0x08a
-#define SVM_EXIT_MWAIT		0x08b
-#define SVM_EXIT_MWAIT_COND	0x08c
-#define SVM_EXIT_NPF  		0x400
-
-#define SVM_EXIT_ERR		-1
-
-#define SVM_CR0_SELECTIVE_MASK (1 << 3 | 1) /* TS and MP */
-
-#define SVM_VMLOAD ".byte 0x0f, 0x01, 0xda"
-#define SVM_VMRUN  ".byte 0x0f, 0x01, 0xd8"
-#define SVM_VMSAVE ".byte 0x0f, 0x01, 0xdb"
-#define SVM_CLGI   ".byte 0x0f, 0x01, 0xdd"
-#define SVM_STGI   ".byte 0x0f, 0x01, 0xdc"
-#define SVM_INVLPGA ".byte 0x0f, 0x01, 0xdf"
-
-#endif
-
-- 
1.5.5.GIT

[PATCH 03/12] kvm: vmx: move ASM_VMX_* definitions from asm/kvm_host.h to asm/vmx.h

[Eduardo Habkost]

Those definitions will be used by code outside KVM, so move it outside
of a KVM-specific source file.

Those definitions are used only on kvm/vmx.c, that already includes
asm/vmx.h, so they can be moved safely.

Signed-off-by: Eduardo Habkost <ehabkost-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
---
 arch/x86/include/asm/kvm_host.h |   12 ------------
 arch/x86/include/asm/vmx.h      |   15 +++++++++++++++
 2 files changed, 15 insertions(+), 12 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 8346be8..caad194 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -702,18 +702,6 @@ static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code)
 	kvm_queue_exception_e(vcpu, GP_VECTOR, error_code);
 }
 
-#define ASM_VMX_VMCLEAR_RAX       ".byte 0x66, 0x0f, 0xc7, 0x30"
-#define ASM_VMX_VMLAUNCH          ".byte 0x0f, 0x01, 0xc2"
-#define ASM_VMX_VMRESUME          ".byte 0x0f, 0x01, 0xc3"
-#define ASM_VMX_VMPTRLD_RAX       ".byte 0x0f, 0xc7, 0x30"
-#define ASM_VMX_VMREAD_RDX_RAX    ".byte 0x0f, 0x78, 0xd0"
-#define ASM_VMX_VMWRITE_RAX_RDX   ".byte 0x0f, 0x79, 0xd0"
-#define ASM_VMX_VMWRITE_RSP_RDX   ".byte 0x0f, 0x79, 0xd4"
-#define ASM_VMX_VMXOFF            ".byte 0x0f, 0x01, 0xc4"
-#define ASM_VMX_VMXON_RAX         ".byte 0xf3, 0x0f, 0xc7, 0x30"
-#define ASM_VMX_INVEPT		  ".byte 0x66, 0x0f, 0x38, 0x80, 0x08"
-#define ASM_VMX_INVVPID		  ".byte 0x66, 0x0f, 0x38, 0x81, 0x08"
-
 #define MSR_IA32_TIME_STAMP_COUNTER		0x010
 
 #define TSS_IOPB_BASE_OFFSET 0x66
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index ec5edc3..e8aa699 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -356,4 +356,19 @@ enum vmcs_field {
 
 #define VMX_EPT_IDENTITY_PAGETABLE_ADDR		0xfffbc000ul
 
+
+#define ASM_VMX_VMCLEAR_RAX       ".byte 0x66, 0x0f, 0xc7, 0x30"
+#define ASM_VMX_VMLAUNCH          ".byte 0x0f, 0x01, 0xc2"
+#define ASM_VMX_VMRESUME          ".byte 0x0f, 0x01, 0xc3"
+#define ASM_VMX_VMPTRLD_RAX       ".byte 0x0f, 0xc7, 0x30"
+#define ASM_VMX_VMREAD_RDX_RAX    ".byte 0x0f, 0x78, 0xd0"
+#define ASM_VMX_VMWRITE_RAX_RDX   ".byte 0x0f, 0x79, 0xd0"
+#define ASM_VMX_VMWRITE_RSP_RDX   ".byte 0x0f, 0x79, 0xd4"
+#define ASM_VMX_VMXOFF            ".byte 0x0f, 0x01, 0xc4"
+#define ASM_VMX_VMXON_RAX         ".byte 0xf3, 0x0f, 0xc7, 0x30"
+#define ASM_VMX_INVEPT		  ".byte 0x66, 0x0f, 0x38, 0x80, 0x08"
+#define ASM_VMX_INVVPID		  ".byte 0x66, 0x0f, 0x38, 0x81, 0x08"
+
+
+
 #endif
-- 
1.5.5.GIT

[PATCH 04/12] kvm: vmx: move cpu_has_kvm_support() to an inline on asm/virtext.h

[Eduardo Habkost]

It will be used by core code on kdump and reboot, to disable
vmx if needed.

Signed-off-by: Eduardo Habkost <ehabkost-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
---
 arch/x86/include/asm/virtext.h |   31 +++++++++++++++++++++++++++++++
 arch/x86/kvm/vmx.c             |    4 ++--
 2 files changed, 33 insertions(+), 2 deletions(-)
 create mode 100644 arch/x86/include/asm/virtext.h

diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
new file mode 100644
index 0000000..298b6a0
--- /dev/null
+++ b/arch/x86/include/asm/virtext.h
@@ -0,0 +1,31 @@
+/* CPU virtualization extensions handling
+ *
+ * This should carry the code for handling CPU virtualization extensions
+ * that needs to live in the kernel core.
+ *
+ * Author: Eduardo Habkost <ehabkost-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
+ *
+ * Copyright (C) 2008, Red Hat Inc.
+ *
+ * Contains code from KVM, Copyright (C) 2006 Qumranet, Inc.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ */
+#ifndef _ASM_X86_VIRTEX_H
+#define _ASM_X86_VIRTEX_H
+
+#include <asm/processor.h>
+#include <asm/system.h>
+
+/*
+ * VMX functions:
+ */
+
+static inline int cpu_has_vmx(void)
+{
+	unsigned long ecx = cpuid_ecx(1);
+	return test_bit(5, &ecx); /* CPUID.1:ECX.VMX[bit 5] -> VT */
+}
+
+#endif /* _ASM_X86_VIRTEX_H */
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index e97ef1a..b07681e 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -31,6 +31,7 @@
 #include <asm/io.h>
 #include <asm/desc.h>
 #include <asm/vmx.h>
+#include <asm/virtext.h>
 
 #define __ex(x) __kvm_handle_fault_on_reboot(x)
 
@@ -1032,8 +1033,7 @@ static int vmx_get_irq(struct kvm_vcpu *vcpu)
 
 static __init int cpu_has_kvm_support(void)
 {
-	unsigned long ecx = cpuid_ecx(1);
-	return test_bit(5, &ecx); /* CPUID.1:ECX.VMX[bit 5] -> VT */
+	return cpu_has_vmx();
 }
 
 static __init int vmx_disabled_by_bios(void)
-- 
1.5.5.GIT

[PATCH 05/12] x86: asm/virtext.h: add cpu_vmxoff() inline function

[Eduardo Habkost]

Unfortunately we can't use exactly the same code from vmx
hardware_disable(), because the KVM function uses the
__kvm_handle_fault_on_reboot() tricks.

Signed-off-by: Eduardo Habkost <ehabkost-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
---
 arch/x86/include/asm/virtext.h |   15 +++++++++++++++
 1 files changed, 15 insertions(+), 0 deletions(-)

diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index 298b6a0..7dee5b5 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -18,6 +18,8 @@
 #include <asm/processor.h>
 #include <asm/system.h>
 
+#include <asm/vmx.h>
+
 /*
  * VMX functions:
  */
@@ -28,4 +30,17 @@ static inline int cpu_has_vmx(void)
 	return test_bit(5, &ecx); /* CPUID.1:ECX.VMX[bit 5] -> VT */
 }
 
+
+/** Disable VMX on the current CPU
+ *
+ * vmxoff causes a undefined-opcode exception if vmxon was not run
+ * on the CPU previously. Only call this function if you know VMX
+ * is enabled.
+ */
+static inline void cpu_vmxoff(void)
+{
+	asm volatile (ASM_VMX_VMXOFF : : : "cc");
+	write_cr4(read_cr4() & ~X86_CR4_VMXE);
+}
+
 #endif /* _ASM_X86_VIRTEX_H */
-- 
1.5.5.GIT

[PATCH 06/12] kvm: vmx: extract kvm_cpu_vmxoff() from hardware_disable()

[Eduardo Habkost]

Along with some comments on why it is different from the core cpu_vmxoff()
function.

Signed-off-by: Eduardo Habkost <ehabkost-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
---
 arch/x86/kvm/vmx.c |   13 +++++++++++--
 1 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index b07681e..02340a9 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1079,13 +1079,22 @@ static void vmclear_local_vcpus(void)
 		__vcpu_clear(vmx);
 }
 
-static void hardware_disable(void *garbage)
+
+/* Just like cpu_vmxoff(), but with the __kvm_handle_fault_on_reboot()
+ * tricks.
+ */
+static void kvm_cpu_vmxoff(void)
 {
-	vmclear_local_vcpus();
 	asm volatile (__ex(ASM_VMX_VMXOFF) : : : "cc");
 	write_cr4(read_cr4() & ~X86_CR4_VMXE);
 }
 
+static void hardware_disable(void *garbage)
+{
+	vmclear_local_vcpus();
+	kvm_cpu_vmxoff();
+}
+
 static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt,
 				      u32 msr, u32 *result)
 {
-- 
1.5.5.GIT

[PATCH 07/12] x86: cpu_emergency_vmxoff() function

[Eduardo Habkost]

Add cpu_emergency_vmxoff() and its friends: cpu_vmx_enabled() and
__cpu_emergency_vmxoff().

Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
---
 arch/x86/include/asm/virtext.h |   23 +++++++++++++++++++++++
 1 files changed, 23 insertions(+), 0 deletions(-)

diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index 7dee5b5..6bcf0ac 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -43,4 +43,27 @@ static inline void cpu_vmxoff(void)
 	write_cr4(read_cr4() & ~X86_CR4_VMXE);
 }
 
+static inline int cpu_vmx_enabled(void)
+{
+	return read_cr4() & X86_CR4_VMXE;
+}
+
+/** Disable VMX if it is enabled on the current CPU
+ *
+ * You shouldn't call this if cpu_has_vmx() returns 0.
+ */
+static inline void __cpu_emergency_vmxoff(void)
+{
+	if (cpu_vmx_enabled())
+		cpu_vmxoff();
+}
+
+/** Disable VMX if it is supported and enabled on the current CPU
+ */
+static inline void cpu_emergency_vmxoff(void)
+{
+	if (cpu_has_vmx())
+		__cpu_emergency_vmxoff();
+}
+
 #endif /* _ASM_X86_VIRTEX_H */
-- 
1.5.5.GIT

[PATCH 08/12] kvm: svm: move has_svm() code to asm/virtext.h

[Eduardo Habkost]

Use a trick to keep the printk()s on has_svm() working as before. gcc
will take care of not generating code for the 'msg' stuff when the
function is called with a NULL msg argument.

Signed-off-by: Eduardo Habkost <ehabkost-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
---
 arch/x86/include/asm/virtext.h |   41 ++++++++++++++++++++++++++++++++++++++++
 arch/x86/kvm/svm.c             |   19 ++++-------------
 2 files changed, 46 insertions(+), 14 deletions(-)

diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index 6bcf0ac..6f0d409 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -19,6 +19,7 @@
 #include <asm/system.h>
 
 #include <asm/vmx.h>
+#include <asm/svm.h>
 
 /*
  * VMX functions:
@@ -66,4 +67,44 @@ static inline void cpu_emergency_vmxoff(void)
 		__cpu_emergency_vmxoff();
 }
 
+
+
+
+/*
+ * SVM functions:
+ */
+
+/** Check if the CPU has SVM support
+ *
+ * You can use the 'msg' arg to get a message describing the problem,
+ * if the function returns zero. Simply pass NULL if you are not interested
+ * on the messages; gcc should take care of not generating code for
+ * the messages on this case.
+ */
+static inline int cpu_has_svm(const char **msg)
+{
+	uint32_t eax, ebx, ecx, edx;
+
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) {
+		if (msg)
+			*msg = "not amd";
+		return 0;
+	}
+
+	cpuid(0x80000000, &eax, &ebx, &ecx, &edx);
+	if (eax < SVM_CPUID_FUNC) {
+		if (msg)
+			*msg = "can't execute cpuid_8000000a";
+		return 0;
+	}
+
+	cpuid(0x80000001, &eax, &ebx, &ecx, &edx);
+	if (!(ecx & (1 << SVM_CPUID_FEATURE_SHIFT))) {
+		if (msg)
+			*msg = "svm not available";
+		return 0;
+	}
+	return 1;
+}
+
 #endif /* _ASM_X86_VIRTEX_H */
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 9c4ce65..64241f5 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -28,6 +28,8 @@
 
 #include <asm/desc.h>
 
+#include <asm/virtext.h>
+
 #define __ex(x) __kvm_handle_fault_on_reboot(x)
 
 MODULE_AUTHOR("Qumranet");
@@ -245,24 +247,13 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
 
 static int has_svm(void)
 {
-	uint32_t eax, ebx, ecx, edx;
-
-	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) {
-		printk(KERN_INFO "has_svm: not amd\n");
-		return 0;
-	}
+	const char *msg;
 
-	cpuid(0x80000000, &eax, &ebx, &ecx, &edx);
-	if (eax < SVM_CPUID_FUNC) {
-		printk(KERN_INFO "has_svm: can't execute cpuid_8000000a\n");
+	if (!cpu_has_svm(&msg)) {
+		printk(KERN_INFO "has_svn: %s\n", msg);
 		return 0;
 	}
 
-	cpuid(0x80000001, &eax, &ebx, &ecx, &edx);
-	if (!(ecx & (1 << SVM_CPUID_FEATURE_SHIFT))) {
-		printk(KERN_DEBUG "has_svm: svm not available\n");
-		return 0;
-	}
 	return 1;
 }
 
-- 
1.5.5.GIT

[PATCH 09/12] kvm: svm: move svm_hardware_disable() code to asm/virtext.h

[Eduardo Habkost]

Create cpu_svm_disable() function.

Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
---
 arch/x86/include/asm/virtext.h |   14 ++++++++++++++
 arch/x86/kvm/svm.c             |    6 +-----
 2 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index 6f0d409..2cfe363 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -107,4 +107,18 @@ static inline int cpu_has_svm(const char **msg)
 	return 1;
 }
 
+
+/** Disable SVM on the current CPU
+ *
+ * You should call this only if cpu_has_svm() returned true.
+ */
+static inline void cpu_svm_disable(void)
+{
+	uint64_t efer;
+
+	wrmsrl(MSR_VM_HSAVE_PA, 0);
+	rdmsrl(MSR_EFER, efer);
+	wrmsrl(MSR_EFER, efer & ~MSR_EFER_SVME_MASK);
+}
+
 #endif /* _ASM_X86_VIRTEX_H */
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 64241f5..7ded2ee 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -259,11 +259,7 @@ static int has_svm(void)
 
 static void svm_hardware_disable(void *garbage)
 {
-	uint64_t efer;
-
-	wrmsrl(MSR_VM_HSAVE_PA, 0);
-	rdmsrl(MSR_EFER, efer);
-	wrmsrl(MSR_EFER, efer & ~MSR_EFER_SVME_MASK);
+	cpu_svm_disable();
 }
 
 static void svm_hardware_enable(void *garbage)
-- 
1.5.5.GIT

[PATCH 10/12] x86: cpu_emergency_svm_disable() function

[Eduardo Habkost]

This function can be used by the reboot or kdump code to forcibly
disable SVM on the CPU.

Signed-off-by: Eduardo Habkost <ehabkost-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
---
 arch/x86/include/asm/virtext.h |    8 ++++++++
 1 files changed, 8 insertions(+), 0 deletions(-)

diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index 2cfe363..5936362 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -121,4 +121,12 @@ static inline void cpu_svm_disable(void)
 	wrmsrl(MSR_EFER, efer & ~MSR_EFER_SVME_MASK);
 }
 
+/** Makes sure SVM is disabled, if it is supported on the CPU
+ */
+static inline void cpu_emergency_svm_disable(void)
+{
+	if (cpu_has_svm(NULL))
+		cpu_svm_disable();
+}
+
 #endif /* _ASM_X86_VIRTEX_H */
-- 
1.5.5.GIT

[PATCH 11/12] kdump: forcibly disable VMX and SVM on machine_crash_shutdown()

[Eduardo Habkost]

We need to disable virtualization extensions on all CPUs before booting
the kdump kernel, otherwise the kdump kernel booting will fail, and
rebooting after the kdump kernel did its task may also fail.

We do it using cpu_emergency_vmxoff() and cpu_emergency_svm_disable(),
that should always work, because those functions check if the CPUs
support SVM or VMX before doing their tasks.

Signed-off-by: Eduardo Habkost <ehabkost-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
---
 arch/x86/kernel/crash.c |   18 ++++++++++++++++++
 1 files changed, 18 insertions(+), 0 deletions(-)

diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index d84a852..c689d19 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -26,6 +26,7 @@
 #include <linux/kdebug.h>
 #include <asm/smp.h>
 #include <asm/reboot.h>
+#include <asm/virtext.h>
 
 #include <mach_ipi.h>
 
@@ -49,6 +50,15 @@ static void kdump_nmi_callback(int cpu, struct die_args *args)
 #endif
 	crash_save_cpu(regs, cpu);
 
+	/* Disable VMX or SVM if needed.
+	 *
+	 * We need to disable virtualization on all CPUs.
+	 * Having VMX or SVM enabled on any CPU may break rebooting
+	 * after the kdump kernel has finished its task.
+	 */
+	cpu_emergency_vmxoff();
+	cpu_emergency_svm_disable();
+
 	disable_local_APIC();
 }
 
@@ -80,6 +90,14 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
 	local_irq_disable();
 
 	kdump_nmi_shootdown_cpus();
+
+	/* Booting kdump kernel with VMX or SVM enabled won't work,
+	 * because (among other limitations) we can't disable paging
+	 * with the virt flags.
+	 */
+	cpu_emergency_vmxoff();
+	cpu_emergency_svm_disable();
+
 	lapic_shutdown();
 #if defined(CONFIG_X86_IO_APIC)
 	disable_IO_APIC();
-- 
1.5.5.GIT

[PATCH 12/12] x86: disable VMX on all CPUs on reboot

[Eduardo Habkost]

On emergency_restart, we may need to use an NMI to disable virtualization
on all CPUs. We do that using nmi_shootdown_cpus() if VMX is enabled.

Note: With this patch, we will run the NMI stuff only when the CPU where
emergency_restart() was called has VMX enabled. This should work on most
cases because KVM enables VMX on all CPUs, but we may miss the small
window where KVM is doing that. Also, I don't know if all code using
VMX out there always enable VMX on all CPUs like KVM does. We have two
other alternatives for that:

a) Have an API that all code that enables VMX on any CPU should use
   to tell the kernel core that it is going to enable VMX on the CPUs.
b) Always call nmi_shootdown_cpus() if the CPU supports VMX. This is
   a bit intrusive and more risky, as it would run nmi_shootdown_cpus()
   on emergency_reboot() even on systems where virtualization is never
   enabled.


Finding a proper point to hook the nmi_shootdown_cpus() call isn't
trivial, as the non-emergency machine_restart() (that doesn't need the
NMI tricks) uses machine_emergency_restart() directly.

The solution to make this work without adding a new function or argument
to machine_ops was setting a 'reboot_emergency' flag that tells if
native_machine_emergency_restart() needs to do the virt cleanup or not.

Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
---
 arch/x86/kernel/reboot.c |   63 ++++++++++++++++++++++++++++++++++++++++++++-
 1 files changed, 61 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 6f05a28..a5f8c09 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -12,6 +12,7 @@
 #include <asm/proto.h>
 #include <asm/reboot_fixups.h>
 #include <asm/reboot.h>
+#include <asm/virtext.h>
 
 #ifdef CONFIG_X86_32
 # include <linux/dmi.h>
@@ -39,6 +40,13 @@ int reboot_force;
 static int reboot_cpu = -1;
 #endif
 
+/* This is set if we need to go through the 'emergency' path.
+ * When machine_emergency_restart() is called, we may be on
+ * an inconsistent state and won't be able to do a clean cleanup
+ */
+static int reboot_emergency;
+
+
 /* This is set by the PCI code if either type 1 or type 2 PCI is detected */
 bool port_cf9_safe = false;
 
@@ -359,6 +367,48 @@ static inline void kb_wait(void)
 	}
 }
 
+static void vmxoff_nmi(int cpu, struct die_args *args)
+{
+	cpu_emergency_vmxoff();
+}
+
+/* Use NMIs as IPIs to tell all CPUs to disable virtualization
+ */
+static void emergency_vmx_disable_all(void)
+{
+	/* Just make sure we won't change CPUs while doing this */
+	local_irq_disable();
+
+	/* We need to disable VMX on all CPUs before rebooting, otherwise
+	 * we risk hanging up the machine, because the CPU ignore INIT
+	 * signals when VMX is enabled.
+	 *
+	 * We can't take any locks and we may be on an inconsistent
+	 * state, so we use NMIs as IPIs to tell the other CPUs to disable
+	 * VMX and halt.
+	 * 
+	 * For safety, we will avoid running the nmi_shootdown_cpus()
+	 * stuff unnecessarily, but we don't have a way to check
+	 * if other CPUs have VMX enabled. So we will call it only if the
+	 * CPU we are running on has VMX enabled.
+	 *
+	 * We will miss cases where VMX is not enabled on all CPUs. This
+	 * shouldn't do much harm because KVM always enable VMX on all
+	 * CPUs anyway. But we can miss it on the small window where KVM
+	 * is still enabling VMX.
+	 */
+	if (cpu_has_vmx() && cpu_vmx_enabled()) {
+		/* Disable VMX on this CPU.
+		 */
+		cpu_vmxoff();
+
+		/* Halt and disable VMX on the other CPUs */
+		nmi_shootdown_cpus(vmxoff_nmi);
+
+	}
+}
+
+
 void __attribute__((weak)) mach_reboot_fixups(void)
 {
 }
@@ -367,6 +417,9 @@ static void native_machine_emergency_restart(void)
 {
 	int i;
 
+	if (reboot_emergency)
+		emergency_vmx_disable_all();
+
 	/* Tell the BIOS if we want cold or warm reboot */
 	*((unsigned short *)__va(0x472)) = reboot_mode;
 
@@ -473,13 +526,19 @@ void native_machine_shutdown(void)
 #endif
 }
 
+static void __machine_emergency_restart(int emergency)
+{
+	reboot_emergency = emergency;
+	machine_ops.emergency_restart();
+}
+
 static void native_machine_restart(char *__unused)
 {
 	printk("machine restart\n");
 
 	if (!reboot_force)
 		machine_shutdown();
-	machine_emergency_restart();
+	__machine_emergency_restart(0);
 }
 
 static void native_machine_halt(void)
@@ -523,7 +582,7 @@ void machine_shutdown(void)
 
 void machine_emergency_restart(void)
 {
-	machine_ops.emergency_restart();
+	__machine_emergency_restart(1);
 }
 
 void machine_restart(char *cmd)
-- 
1.5.5.GIT

Re: [PATCH 00/12] x86: disable virt on kdump and emergency_restart (v4)

[Ingo Molnar]

* Eduardo Habkost <ehabkost-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org> wrote:

> Hi, Ingo,
> 
> This is yet another spin of the series to disable vmx on kdump and 
> on emergency_restart, after some feedback from Avi.

this is going to interact with the KVM tree, wont it?

i think the best way forward would be to keep your changes in the KVM 
tree.

Lets try a Git trick for that. Avi could do that by pulling your other 
x86 changes from the x86 topic tree into the kvm tree. They are 
reviewed, acked and well-tested now, and kept in a separate tree so no 
other x86 change will be pulled in via them.

We can do this if Avi can guarantee that these commits wont ever be 
rebased within KVM - then the two trees will merge up just fine in 
linux-next (and later in v2.6.29 as well), without any awkward merge 
dependencies or merge conflicts.

See the pull request below.

	Ingo

------------>
Please pull the latest x86/crashdump git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git x86/crashdump


out-of-topic modifications in x86/crashdump:
--------------------------------------------
include/linux/kexec.h              # 92be3d6: kexec/i386: allocate page table p

 Thanks,

	Ingo

------------------>
Eduardo Habkost (8):
      x86 kdump: extract kdump-specific code from crash_nmi_callback()
      x86 kdump: move crashing_cpu assignment to nmi_shootdown_cpus()
      x86 kdump: create kdump_nmi_shootdown_cpus()
      x86 kdump: make kdump_nmi_callback() a function ptr on crash_nmi_callback()
      x86 kdump: make nmi_shootdown_cpus() non-static
      x86: move nmi_shootdown_cpus() to reboot.c
      x86: make nmi_shootdown_cpus() available on !SMP and !X86_LOCAL_APIC
      x86: disable IRQs before doing anything on nmi_shootdown_cpus()

Huang Ying (3):
      kexec/i386: remove PAGE_SIZE alignment from relocate_kernel
      kexec/i386: allocate page table pages dynamically
      kexec/i386: setup kexec page table in C


 arch/x86/include/asm/kexec.h         |   31 +++++-----
 arch/x86/include/asm/reboot.h        |    5 ++
 arch/x86/kernel/crash.c              |   70 +++------------------
 arch/x86/kernel/machine_kexec_32.c   |  104 ++++++++++++++++++++++++-------
 arch/x86/kernel/reboot.c             |   95 ++++++++++++++++++++++++++++
 arch/x86/kernel/relocate_kernel_32.S |  115 ----------------------------------
 include/linux/kexec.h                |    4 +
 7 files changed, 210 insertions(+), 214 deletions(-)

diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index a1f2277..c61d8b2 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -5,21 +5,8 @@
 # define PA_CONTROL_PAGE	0
 # define VA_CONTROL_PAGE	1
 # define PA_PGD			2
-# define VA_PGD			3
-# define PA_PTE_0		4
-# define VA_PTE_0		5
-# define PA_PTE_1		6
-# define VA_PTE_1		7
-# define PA_SWAP_PAGE		8
-# ifdef CONFIG_X86_PAE
-#  define PA_PMD_0		9
-#  define VA_PMD_0		10
-#  define PA_PMD_1		11
-#  define VA_PMD_1		12
-#  define PAGES_NR		13
-# else
-#  define PAGES_NR		9
-# endif
+# define PA_SWAP_PAGE		3
+# define PAGES_NR		4
 #else
 # define PA_CONTROL_PAGE	0
 # define VA_CONTROL_PAGE	1
@@ -170,6 +157,20 @@ relocate_kernel(unsigned long indirection_page,
 		unsigned long start_address) ATTRIB_NORET;
 #endif
 
+#ifdef CONFIG_X86_32
+#define ARCH_HAS_KIMAGE_ARCH
+
+struct kimage_arch {
+	pgd_t *pgd;
+#ifdef CONFIG_X86_PAE
+	pmd_t *pmd0;
+	pmd_t *pmd1;
+#endif
+	pte_t *pte0;
+	pte_t *pte1;
+};
+#endif
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_X86_KEXEC_H */
diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h
index df77103..562d4fd 100644
--- a/arch/x86/include/asm/reboot.h
+++ b/arch/x86/include/asm/reboot.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_X86_REBOOT_H
 #define _ASM_X86_REBOOT_H
 
+#include <linux/kdebug.h>
+
 struct pt_regs;
 
 struct machine_ops {
@@ -18,4 +20,7 @@ void native_machine_crash_shutdown(struct pt_regs *regs);
 void native_machine_shutdown(void);
 void machine_real_restart(const unsigned char *code, int length);
 
+typedef void (*nmi_shootdown_cb)(int, struct die_args*);
+void nmi_shootdown_cpus(nmi_shootdown_cb callback);
+
 #endif /* _ASM_X86_REBOOT_H */
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 2685538..d84a852 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -29,34 +29,17 @@
 
 #include <mach_ipi.h>
 
-/* This keeps a track of which one is crashing cpu. */
-static int crashing_cpu;
 
 #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC)
-static atomic_t waiting_for_crash_ipi;
 
-static int crash_nmi_callback(struct notifier_block *self,
-			unsigned long val, void *data)
+static void kdump_nmi_callback(int cpu, struct die_args *args)
 {
 	struct pt_regs *regs;
 #ifdef CONFIG_X86_32
 	struct pt_regs fixed_regs;
 #endif
-	int cpu;
 
-	if (val != DIE_NMI_IPI)
-		return NOTIFY_OK;
-
-	regs = ((struct die_args *)data)->regs;
-	cpu = raw_smp_processor_id();
-
-	/* Don't do anything if this handler is invoked on crashing cpu.
-	 * Otherwise, system will completely hang. Crashing cpu can get
-	 * an NMI if system was initially booted with nmi_watchdog parameter.
-	 */
-	if (cpu == crashing_cpu)
-		return NOTIFY_STOP;
-	local_irq_disable();
+	regs = args->regs;
 
 #ifdef CONFIG_X86_32
 	if (!user_mode_vm(regs)) {
@@ -65,54 +48,19 @@ static int crash_nmi_callback(struct notifier_block *self,
 	}
 #endif
 	crash_save_cpu(regs, cpu);
-	disable_local_APIC();
-	atomic_dec(&waiting_for_crash_ipi);
-	/* Assume hlt works */
-	halt();
-	for (;;)
-		cpu_relax();
-
-	return 1;
-}
 
-static void smp_send_nmi_allbutself(void)
-{
-	cpumask_t mask = cpu_online_map;
-	cpu_clear(safe_smp_processor_id(), mask);
-	if (!cpus_empty(mask))
-		send_IPI_mask(mask, NMI_VECTOR);
+	disable_local_APIC();
 }
 
-static struct notifier_block crash_nmi_nb = {
-	.notifier_call = crash_nmi_callback,
-};
-
-static void nmi_shootdown_cpus(void)
+static void kdump_nmi_shootdown_cpus(void)
 {
-	unsigned long msecs;
-
-	atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
-	/* Would it be better to replace the trap vector here? */
-	if (register_die_notifier(&crash_nmi_nb))
-		return;		/* return what? */
-	/* Ensure the new callback function is set before sending
-	 * out the NMI
-	 */
-	wmb();
+	nmi_shootdown_cpus(kdump_nmi_callback);
 
-	smp_send_nmi_allbutself();
-
-	msecs = 1000; /* Wait at most a second for the other cpus to stop */
-	while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) {
-		mdelay(1);
-		msecs--;
-	}
-
-	/* Leave the nmi callback set */
 	disable_local_APIC();
 }
+
 #else
-static void nmi_shootdown_cpus(void)
+static void kdump_nmi_shootdown_cpus(void)
 {
 	/* There are no cpus to shootdown */
 }
@@ -131,9 +79,7 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
 	/* The kernel is broken so disable interrupts */
 	local_irq_disable();
 
-	/* Make a note of crashing cpu. Will be used in NMI callback.*/
-	crashing_cpu = safe_smp_processor_id();
-	nmi_shootdown_cpus();
+	kdump_nmi_shootdown_cpus();
 	lapic_shutdown();
 #if defined(CONFIG_X86_IO_APIC)
 	disable_IO_APIC();
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 7a38574..37f4200 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -13,6 +13,7 @@
 #include <linux/numa.h>
 #include <linux/ftrace.h>
 #include <linux/suspend.h>
+#include <linux/gfp.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -25,15 +26,6 @@
 #include <asm/system.h>
 #include <asm/cacheflush.h>
 
-#define PAGE_ALIGNED __attribute__ ((__aligned__(PAGE_SIZE)))
-static u32 kexec_pgd[1024] PAGE_ALIGNED;
-#ifdef CONFIG_X86_PAE
-static u32 kexec_pmd0[1024] PAGE_ALIGNED;
-static u32 kexec_pmd1[1024] PAGE_ALIGNED;
-#endif
-static u32 kexec_pte0[1024] PAGE_ALIGNED;
-static u32 kexec_pte1[1024] PAGE_ALIGNED;
-
 static void set_idt(void *newidt, __u16 limit)
 {
 	struct desc_ptr curidt;
@@ -76,6 +68,76 @@ static void load_segments(void)
 #undef __STR
 }
 
+static void machine_kexec_free_page_tables(struct kimage *image)
+{
+	free_page((unsigned long)image->arch.pgd);
+#ifdef CONFIG_X86_PAE
+	free_page((unsigned long)image->arch.pmd0);
+	free_page((unsigned long)image->arch.pmd1);
+#endif
+	free_page((unsigned long)image->arch.pte0);
+	free_page((unsigned long)image->arch.pte1);
+}
+
+static int machine_kexec_alloc_page_tables(struct kimage *image)
+{
+	image->arch.pgd = (pgd_t *)get_zeroed_page(GFP_KERNEL);
+#ifdef CONFIG_X86_PAE
+	image->arch.pmd0 = (pmd_t *)get_zeroed_page(GFP_KERNEL);
+	image->arch.pmd1 = (pmd_t *)get_zeroed_page(GFP_KERNEL);
+#endif
+	image->arch.pte0 = (pte_t *)get_zeroed_page(GFP_KERNEL);
+	image->arch.pte1 = (pte_t *)get_zeroed_page(GFP_KERNEL);
+	if (!image->arch.pgd ||
+#ifdef CONFIG_X86_PAE
+	    !image->arch.pmd0 || !image->arch.pmd1 ||
+#endif
+	    !image->arch.pte0 || !image->arch.pte1) {
+		machine_kexec_free_page_tables(image);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+static void machine_kexec_page_table_set_one(
+	pgd_t *pgd, pmd_t *pmd, pte_t *pte,
+	unsigned long vaddr, unsigned long paddr)
+{
+	pud_t *pud;
+
+	pgd += pgd_index(vaddr);
+#ifdef CONFIG_X86_PAE
+	if (!(pgd_val(*pgd) & _PAGE_PRESENT))
+		set_pgd(pgd, __pgd(__pa(pmd) | _PAGE_PRESENT));
+#endif
+	pud = pud_offset(pgd, vaddr);
+	pmd = pmd_offset(pud, vaddr);
+	if (!(pmd_val(*pmd) & _PAGE_PRESENT))
+		set_pmd(pmd, __pmd(__pa(pte) | _PAGE_TABLE));
+	pte = pte_offset_kernel(pmd, vaddr);
+	set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC));
+}
+
+static void machine_kexec_prepare_page_tables(struct kimage *image)
+{
+	void *control_page;
+	pmd_t *pmd = 0;
+
+	control_page = page_address(image->control_code_page);
+#ifdef CONFIG_X86_PAE
+	pmd = image->arch.pmd0;
+#endif
+	machine_kexec_page_table_set_one(
+		image->arch.pgd, pmd, image->arch.pte0,
+		(unsigned long)control_page, __pa(control_page));
+#ifdef CONFIG_X86_PAE
+	pmd = image->arch.pmd1;
+#endif
+	machine_kexec_page_table_set_one(
+		image->arch.pgd, pmd, image->arch.pte1,
+		__pa(control_page), __pa(control_page));
+}
+
 /*
  * A architecture hook called to validate the
  * proposed image and prepare the control pages
@@ -87,12 +149,20 @@ static void load_segments(void)
  * reboot code buffer to allow us to avoid allocations
  * later.
  *
- * Make control page executable.
+ * - Make control page executable.
+ * - Allocate page tables
+ * - Setup page tables
  */
 int machine_kexec_prepare(struct kimage *image)
 {
+	int error;
+
 	if (nx_enabled)
 		set_pages_x(image->control_code_page, 1);
+	error = machine_kexec_alloc_page_tables(image);
+	if (error)
+		return error;
+	machine_kexec_prepare_page_tables(image);
 	return 0;
 }
 
@@ -104,6 +174,7 @@ void machine_kexec_cleanup(struct kimage *image)
 {
 	if (nx_enabled)
 		set_pages_nx(image->control_code_page, 1);
+	machine_kexec_free_page_tables(image);
 }
 
 /*
@@ -150,18 +221,7 @@ void machine_kexec(struct kimage *image)
 	relocate_kernel_ptr = control_page;
 	page_list[PA_CONTROL_PAGE] = __pa(control_page);
 	page_list[VA_CONTROL_PAGE] = (unsigned long)control_page;
-	page_list[PA_PGD] = __pa(kexec_pgd);
-	page_list[VA_PGD] = (unsigned long)kexec_pgd;
-#ifdef CONFIG_X86_PAE
-	page_list[PA_PMD_0] = __pa(kexec_pmd0);
-	page_list[VA_PMD_0] = (unsigned long)kexec_pmd0;
-	page_list[PA_PMD_1] = __pa(kexec_pmd1);
-	page_list[VA_PMD_1] = (unsigned long)kexec_pmd1;
-#endif
-	page_list[PA_PTE_0] = __pa(kexec_pte0);
-	page_list[VA_PTE_0] = (unsigned long)kexec_pte0;
-	page_list[PA_PTE_1] = __pa(kexec_pte1);
-	page_list[VA_PTE_1] = (unsigned long)kexec_pte1;
+	page_list[PA_PGD] = __pa(image->arch.pgd);
 
 	if (image->type == KEXEC_TYPE_DEFAULT)
 		page_list[PA_SWAP_PAGE] = (page_to_pfn(image->swap_page)
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 724adfc..c3cd512 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -21,6 +21,9 @@
 # include <asm/iommu.h>
 #endif
 
+#include <mach_ipi.h>
+
+
 /*
  * Power off function, if any
  */
@@ -514,3 +517,95 @@ void machine_crash_shutdown(struct pt_regs *regs)
 	machine_ops.crash_shutdown(regs);
 }
 #endif
+
+
+#if defined(CONFIG_SMP)
+
+/* This keeps a track of which one is crashing cpu. */
+static int crashing_cpu;
+static nmi_shootdown_cb shootdown_callback;
+
+static atomic_t waiting_for_crash_ipi;
+
+static int crash_nmi_callback(struct notifier_block *self,
+			unsigned long val, void *data)
+{
+	int cpu;
+
+	if (val != DIE_NMI_IPI)
+		return NOTIFY_OK;
+
+	cpu = raw_smp_processor_id();
+
+	/* Don't do anything if this handler is invoked on crashing cpu.
+	 * Otherwise, system will completely hang. Crashing cpu can get
+	 * an NMI if system was initially booted with nmi_watchdog parameter.
+	 */
+	if (cpu == crashing_cpu)
+		return NOTIFY_STOP;
+	local_irq_disable();
+
+	shootdown_callback(cpu, (struct die_args *)data);
+
+	atomic_dec(&waiting_for_crash_ipi);
+	/* Assume hlt works */
+	halt();
+	for (;;)
+		cpu_relax();
+
+	return 1;
+}
+
+static void smp_send_nmi_allbutself(void)
+{
+	cpumask_t mask = cpu_online_map;
+	cpu_clear(safe_smp_processor_id(), mask);
+	if (!cpus_empty(mask))
+		send_IPI_mask(mask, NMI_VECTOR);
+}
+
+static struct notifier_block crash_nmi_nb = {
+	.notifier_call = crash_nmi_callback,
+};
+
+/* Halt all other CPUs, calling the specified function on each of them
+ *
+ * This function can be used to halt all other CPUs on crash
+ * or emergency reboot time. The function passed as parameter
+ * will be called inside a NMI handler on all CPUs.
+ */
+void nmi_shootdown_cpus(nmi_shootdown_cb callback)
+{
+	unsigned long msecs;
+	local_irq_disable();
+
+	/* Make a note of crashing cpu. Will be used in NMI callback.*/
+	crashing_cpu = safe_smp_processor_id();
+
+	shootdown_callback = callback;
+
+	atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
+	/* Would it be better to replace the trap vector here? */
+	if (register_die_notifier(&crash_nmi_nb))
+		return;		/* return what? */
+	/* Ensure the new callback function is set before sending
+	 * out the NMI
+	 */
+	wmb();
+
+	smp_send_nmi_allbutself();
+
+	msecs = 1000; /* Wait at most a second for the other cpus to stop */
+	while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) {
+		mdelay(1);
+		msecs--;
+	}
+
+	/* Leave the nmi callback set */
+}
+#else /* !CONFIG_SMP */
+void nmi_shootdown_cpus(nmi_shootdown_cb callback)
+{
+	/* No other CPUs to shoot down */
+}
+#endif
diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S
index 6f50664..a160f31 100644
--- a/arch/x86/kernel/relocate_kernel_32.S
+++ b/arch/x86/kernel/relocate_kernel_32.S
@@ -10,15 +10,12 @@
 #include <asm/page.h>
 #include <asm/kexec.h>
 #include <asm/processor-flags.h>
-#include <asm/pgtable.h>
 
 /*
  * Must be relocatable PIC code callable as a C function
  */
 
 #define PTR(x) (x << 2)
-#define PAGE_ATTR (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY)
-#define PAE_PGD_ATTR (_PAGE_PRESENT)
 
 /* control_page + KEXEC_CONTROL_CODE_MAX_SIZE
  * ~ control_page + PAGE_SIZE are used as data storage and stack for
@@ -39,7 +36,6 @@
 #define CP_PA_BACKUP_PAGES_MAP	DATA(0x1c)
 
 	.text
-	.align PAGE_SIZE
 	.globl relocate_kernel
 relocate_kernel:
 	/* Save the CPU context, used for jumping back */
@@ -60,117 +56,6 @@ relocate_kernel:
 	movl	%cr4, %eax
 	movl	%eax, CR4(%edi)
 
-#ifdef CONFIG_X86_PAE
-	/* map the control page at its virtual address */
-
-	movl	PTR(VA_PGD)(%ebp), %edi
-	movl	PTR(VA_CONTROL_PAGE)(%ebp), %eax
-	andl	$0xc0000000, %eax
-	shrl	$27, %eax
-	addl	%edi, %eax
-
-	movl	PTR(PA_PMD_0)(%ebp), %edx
-	orl	$PAE_PGD_ATTR, %edx
-	movl	%edx, (%eax)
-
-	movl	PTR(VA_PMD_0)(%ebp), %edi
-	movl	PTR(VA_CONTROL_PAGE)(%ebp), %eax
-	andl	$0x3fe00000, %eax
-	shrl	$18, %eax
-	addl	%edi, %eax
-
-	movl	PTR(PA_PTE_0)(%ebp), %edx
-	orl	$PAGE_ATTR, %edx
-	movl	%edx, (%eax)
-
-	movl	PTR(VA_PTE_0)(%ebp), %edi
-	movl	PTR(VA_CONTROL_PAGE)(%ebp), %eax
-	andl	$0x001ff000, %eax
-	shrl	$9, %eax
-	addl	%edi, %eax
-
-	movl	PTR(PA_CONTROL_PAGE)(%ebp), %edx
-	orl	$PAGE_ATTR, %edx
-	movl	%edx, (%eax)
-
-	/* identity map the control page at its physical address */
-
-	movl	PTR(VA_PGD)(%ebp), %edi
-	movl	PTR(PA_CONTROL_PAGE)(%ebp), %eax
-	andl	$0xc0000000, %eax
-	shrl	$27, %eax
-	addl	%edi, %eax
-
-	movl	PTR(PA_PMD_1)(%ebp), %edx
-	orl	$PAE_PGD_ATTR, %edx
-	movl	%edx, (%eax)
-
-	movl	PTR(VA_PMD_1)(%ebp), %edi
-	movl	PTR(PA_CONTROL_PAGE)(%ebp), %eax
-	andl	$0x3fe00000, %eax
-	shrl	$18, %eax
-	addl	%edi, %eax
-
-	movl	PTR(PA_PTE_1)(%ebp), %edx
-	orl	$PAGE_ATTR, %edx
-	movl	%edx, (%eax)
-
-	movl	PTR(VA_PTE_1)(%ebp), %edi
-	movl	PTR(PA_CONTROL_PAGE)(%ebp), %eax
-	andl	$0x001ff000, %eax
-	shrl	$9, %eax
-	addl	%edi, %eax
-
-	movl	PTR(PA_CONTROL_PAGE)(%ebp), %edx
-	orl	$PAGE_ATTR, %edx
-	movl	%edx, (%eax)
-#else
-	/* map the control page at its virtual address */
-
-	movl	PTR(VA_PGD)(%ebp), %edi
-	movl	PTR(VA_CONTROL_PAGE)(%ebp), %eax
-	andl	$0xffc00000, %eax
-	shrl	$20, %eax
-	addl	%edi, %eax
-
-	movl	PTR(PA_PTE_0)(%ebp), %edx
-	orl	$PAGE_ATTR, %edx
-	movl	%edx, (%eax)
-
-	movl	PTR(VA_PTE_0)(%ebp), %edi
-	movl	PTR(VA_CONTROL_PAGE)(%ebp), %eax
-	andl	$0x003ff000, %eax
-	shrl	$10, %eax
-	addl	%edi, %eax
-
-	movl	PTR(PA_CONTROL_PAGE)(%ebp), %edx
-	orl	$PAGE_ATTR, %edx
-	movl	%edx, (%eax)
-
-	/* identity map the control page at its physical address */
-
-	movl	PTR(VA_PGD)(%ebp), %edi
-	movl	PTR(PA_CONTROL_PAGE)(%ebp), %eax
-	andl	$0xffc00000, %eax
-	shrl	$20, %eax
-	addl	%edi, %eax
-
-	movl	PTR(PA_PTE_1)(%ebp), %edx
-	orl	$PAGE_ATTR, %edx
-	movl	%edx, (%eax)
-
-	movl	PTR(VA_PTE_1)(%ebp), %edi
-	movl	PTR(PA_CONTROL_PAGE)(%ebp), %eax
-	andl	$0x003ff000, %eax
-	shrl	$10, %eax
-	addl	%edi, %eax
-
-	movl	PTR(PA_CONTROL_PAGE)(%ebp), %edx
-	orl	$PAGE_ATTR, %edx
-	movl	%edx, (%eax)
-#endif
-
-relocate_new_kernel:
 	/* read the arguments and say goodbye to the stack */
 	movl  20+4(%esp), %ebx /* page_list */
 	movl  20+8(%esp), %ebp /* list of pages */
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index 17f76fc..adc34f2 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -100,6 +100,10 @@ struct kimage {
 #define KEXEC_TYPE_DEFAULT 0
 #define KEXEC_TYPE_CRASH   1
 	unsigned int preserve_context : 1;
+
+#ifdef ARCH_HAS_KIMAGE_ARCH
+	struct kimage_arch arch;
+#endif
 };

Re: [PATCH 00/12] x86: disable virt on kdump and emergency_restart (v4)

[Avi Kivity]

Ingo Molnar wrote:
> * Eduardo Habkost <ehabkost-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org> wrote:
>
>   
>> Hi, Ingo,
>>
>> This is yet another spin of the series to disable vmx on kdump and 
>> on emergency_restart, after some feedback from Avi.
>>     
>
> this is going to interact with the KVM tree, wont it?
>
> i think the best way forward would be to keep your changes in the KVM 
> tree.
>
> Lets try a Git trick for that. Avi could do that by pulling your other 
> x86 changes from the x86 topic tree into the kvm tree. They are 
> reviewed, acked and well-tested now, and kept in a separate tree so no 
> other x86 change will be pulled in via them.
>
> We can do this if Avi can guarantee that these commits wont ever be 
> rebased within KVM - then the two trees will merge up just fine in 
> linux-next (and later in v2.6.29 as well), without any awkward merge 
> dependencies or merge conflicts.
>   

I never rebase kvm.git master, so I pulled the x86 changes and applied 
all.  Ingo, this will mean you have to push x86 before kvm.git, but as 
you're generally faster than me there shouldn't be a problem.

Eduardo, please check the merge (there was a small conflict in reboot.c 
which I fixed) once I push it.  Also, when generating patches that move 
files, use the -M switch: this makes it easier to review, and also 
handles files that change better.

-- 
I have a truly marvellous patch that fixes the bug which this
signature is too narrow to contain.

Re: [PATCH 00/12] x86: disable virt on kdump and emergency_restart (v4)

[Ingo Molnar]

* Avi Kivity <avi-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org> wrote:

> Ingo Molnar wrote:
>> * Eduardo Habkost <ehabkost-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org> wrote:
>>
>>   
>>> Hi, Ingo,
>>>
>>> This is yet another spin of the series to disable vmx on kdump and  
>>> on emergency_restart, after some feedback from Avi.
>>>     
>>
>> this is going to interact with the KVM tree, wont it?
>>
>> i think the best way forward would be to keep your changes in the KVM  
>> tree.
>>
>> Lets try a Git trick for that. Avi could do that by pulling your other  
>> x86 changes from the x86 topic tree into the kvm tree. They are  
>> reviewed, acked and well-tested now, and kept in a separate tree so no  
>> other x86 change will be pulled in via them.
>>
>> We can do this if Avi can guarantee that these commits wont ever be  
>> rebased within KVM - then the two trees will merge up just fine in  
>> linux-next (and later in v2.6.29 as well), without any awkward merge  
>> dependencies or merge conflicts.
>>   
>
> I never rebase kvm.git master, so I pulled the x86 changes and 
> applied all.  Ingo, this will mean you have to push x86 before 
> kvm.git, but as you're generally faster than me there shouldn't be a 
> problem.

Great!

Note that the dependencies are even more relaxed that that: you can 
push it too via the KVM tree, independently of the x86 push. Obviously 
you got those x86 changes from us x86 maintainers and they all work 
standalone too.

Pulling from each other means both sides agree on that sub-set of 
changes and trust each other - so there's no forced merge ordering or 
maintenance boundaries - any side can merge it upstream. (If you feel 
uneasy about it on any level, and were you to send a pull request 
first, then you can point it out to Linus in the pull request that you 
got those changes from us.)

	Ingo

Re: [PATCH 00/12] x86: disable virt on kdump and emergency_restart (v4)

[Eduardo Habkost]

On Fri, Nov 21, 2008 at 06:07:36PM +0200, Avi Kivity wrote:
<snip>
>
> Eduardo, please check the merge (there was a small conflict in reboot.c  
> which I fixed) once I push it.  Also, when generating patches that move  
> files, use the -M switch: this makes it easier to review, and also  
> handles files that change better.

The merge looks ok. I didn't know about -M, I will use it next time.

Thanks!

-- 
Eduardo