[PATCH 95/98] HACK: fix include/uapi/xen/privcmd.h compilation in userspace

From: Mikko Rapeli
Date: Sat May 30 2015 - 12:20:40 EST

Next message: Mikko Rapeli: "[PATCH 77/98] include/uapi/linux/errqueue.h: include linux/time.h"
Previous message: Mikko Rapeli: "[PATCH 70/98] include/uapi/linux/netfilter/xt_HMARK.h: include linux/netfilter.h"
In reply to: Mikko Rapeli: "[PATCH 70/98] include/uapi/linux/netfilter/xt_HMARK.h: include linux/netfilter.h"
Next in thread: Andrew Cooper: "Re: [Xen-devel] [PATCH 95/98] HACK: fix include/uapi/xen/privcmd.h compilation in userspace"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

privcmd.h depends on xen/interface/xen.h which is now exported to userspace.
xen/interface/xen.h then depends on asm/xen/interface.h which is now
exported to userspace together with its dependencies asm/xen/interface_32.h,
asm/xen/interface_64.h and asm/pvclock-abi.h on x86 architecture.

Then all of these headers were fixed to use __u8 etc from linux/types.h
instead of custom types.

Then define uint64_t and uint32_t if needed.

After all these changes these header files now compile in userspace too
on x86.

HACK since I have no idea if this is correct way to fix this.

Signed-off-by: Mikko Rapeli <mikko.rapeli@xxxxxx>
---
arch/x86/include/asm/pvclock-abi.h | 41 +-
arch/x86/include/asm/xen/interface.h | 185 +------
arch/x86/include/asm/xen/interface_32.h | 98 +---
arch/x86/include/asm/xen/interface_64.h | 144 +----
arch/x86/include/uapi/asm/Kbuild | 2 +
arch/x86/include/uapi/asm/pvclock-abi.h | 47 ++
arch/x86/include/uapi/asm/xen/Kbuild | 5 +
arch/x86/include/uapi/asm/xen/interface.h | 198 +++++++
arch/x86/include/uapi/asm/xen/interface_32.h | 103 ++++
arch/x86/include/uapi/asm/xen/interface_64.h | 150 ++++++
include/uapi/xen/Kbuild | 1 +
include/uapi/xen/interface/Kbuild | 2 +
include/uapi/xen/interface/xen.h | 759 +++++++++++++++++++++++++++
include/xen/interface/xen.h | 754 +-------------------------
14 files changed, 1272 insertions(+), 1217 deletions(-)
create mode 100644 arch/x86/include/uapi/asm/pvclock-abi.h
create mode 100644 arch/x86/include/uapi/asm/xen/Kbuild
create mode 100644 arch/x86/include/uapi/asm/xen/interface.h
create mode 100644 arch/x86/include/uapi/asm/xen/interface_32.h
create mode 100644 arch/x86/include/uapi/asm/xen/interface_64.h
create mode 100644 include/uapi/xen/interface/Kbuild
create mode 100644 include/uapi/xen/interface/xen.h

diff --git a/arch/x86/include/asm/pvclock-abi.h b/arch/x86/include/asm/pvclock-abi.h
index 6167fd7..20df65d 100644
--- a/arch/x86/include/asm/pvclock-abi.h
+++ b/arch/x86/include/asm/pvclock-abi.h
@@ -1,45 +1,6 @@
#ifndef _ASM_X86_PVCLOCK_ABI_H
#define _ASM_X86_PVCLOCK_ABI_H
-#ifndef __ASSEMBLY__

-/*
- * These structs MUST NOT be changed.
- * They are the ABI between hypervisor and guest OS.
- * Both Xen and KVM are using this.
- *
- * pvclock_vcpu_time_info holds the system time and the tsc timestamp
- * of the last update. So the guest can use the tsc delta to get a
- * more precise system time. There is one per virtual cpu.
- *
- * pvclock_wall_clock references the point in time when the system
- * time was zero (usually boot time), thus the guest calculates the
- * current wall clock by adding the system time.
- *
- * Protocol for the "version" fields is: hypervisor raises it (making
- * it uneven) before it starts updating the fields and raises it again
- * (making it even) when it is done. Thus the guest can make sure the
- * time values it got are consistent by checking the version before
- * and after reading them.
- */
+#include <uapi/asm/pvclock-abi.h>

-struct pvclock_vcpu_time_info {
- u32 version;
- u32 pad0;
- u64 tsc_timestamp;
- u64 system_time;
- u32 tsc_to_system_mul;
- s8 tsc_shift;
- u8 flags;
- u8 pad[2];
-} __attribute__((__packed__)); /* 32 bytes */
-
-struct pvclock_wall_clock {
- u32 version;
- u32 sec;
- u32 nsec;
-} __attribute__((__packed__));
-
-#define PVCLOCK_TSC_STABLE_BIT (1 << 0)
-#define PVCLOCK_GUEST_STOPPED (1 << 1)
-#endif /* __ASSEMBLY__ */
#endif /* _ASM_X86_PVCLOCK_ABI_H */
diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h
index 3400dba..a866bdf 100644
--- a/arch/x86/include/asm/xen/interface.h
+++ b/arch/x86/include/asm/xen/interface.h
@@ -1,189 +1,6 @@
-/******************************************************************************
- * arch-x86_32.h
- *
- * Guest OS interface to x86 Xen.
- *
- * Copyright (c) 2004, K A Fraser
- */
-
#ifndef _ASM_X86_XEN_INTERFACE_H
#define _ASM_X86_XEN_INTERFACE_H

-#ifdef __XEN__
-#define __DEFINE_GUEST_HANDLE(name, type) \
- typedef struct { type *p; } __guest_handle_ ## name
-#else
-#define __DEFINE_GUEST_HANDLE(name, type) \
- typedef type * __guest_handle_ ## name
-#endif
-
-#define DEFINE_GUEST_HANDLE_STRUCT(name) \
- __DEFINE_GUEST_HANDLE(name, struct name)
-#define DEFINE_GUEST_HANDLE(name) __DEFINE_GUEST_HANDLE(name, name)
-#define GUEST_HANDLE(name) __guest_handle_ ## name
-
-#ifdef __XEN__
-#if defined(__i386__)
-#define set_xen_guest_handle(hnd, val) \
- do { \
- if (sizeof(hnd) == 8) \
- *(uint64_t *)&(hnd) = 0; \
- (hnd).p = val; \
- } while (0)
-#elif defined(__x86_64__)
-#define set_xen_guest_handle(hnd, val) do { (hnd).p = val; } while (0)
-#endif
-#else
-#if defined(__i386__)
-#define set_xen_guest_handle(hnd, val) \
- do { \
- if (sizeof(hnd) == 8) \
- *(uint64_t *)&(hnd) = 0; \
- (hnd) = val; \
- } while (0)
-#elif defined(__x86_64__)
-#define set_xen_guest_handle(hnd, val) do { (hnd) = val; } while (0)
-#endif
-#endif
-
-#ifndef __ASSEMBLY__
-/* Explicitly size integers that represent pfns in the public interface
- * with Xen so that on ARM we can have one ABI that works for 32 and 64
- * bit guests. */
-typedef unsigned long xen_pfn_t;
-#define PRI_xen_pfn "lx"
-typedef unsigned long xen_ulong_t;
-#define PRI_xen_ulong "lx"
-typedef long xen_long_t;
-#define PRI_xen_long "lx"
-
-/* Guest handles for primitive C types. */
-__DEFINE_GUEST_HANDLE(uchar, unsigned char);
-__DEFINE_GUEST_HANDLE(uint, unsigned int);
-DEFINE_GUEST_HANDLE(char);
-DEFINE_GUEST_HANDLE(int);
-DEFINE_GUEST_HANDLE(void);
-DEFINE_GUEST_HANDLE(uint64_t);
-DEFINE_GUEST_HANDLE(uint32_t);
-DEFINE_GUEST_HANDLE(xen_pfn_t);
-DEFINE_GUEST_HANDLE(xen_ulong_t);
-#endif
-
-#ifndef HYPERVISOR_VIRT_START
-#define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START)
-#endif
-
-#define MACH2PHYS_VIRT_START mk_unsigned_long(__MACH2PHYS_VIRT_START)
-#define MACH2PHYS_VIRT_END mk_unsigned_long(__MACH2PHYS_VIRT_END)
-#define MACH2PHYS_NR_ENTRIES ((MACH2PHYS_VIRT_END-MACH2PHYS_VIRT_START)>>__MACH2PHYS_SHIFT)
-
-/* Maximum number of virtual CPUs in multi-processor guests. */
-#define MAX_VIRT_CPUS 32
-
-/*
- * SEGMENT DESCRIPTOR TABLES
- */
-/*
- * A number of GDT entries are reserved by Xen. These are not situated at the
- * start of the GDT because some stupid OSes export hard-coded selector values
- * in their ABI. These hard-coded values are always near the start of the GDT,
- * so Xen places itself out of the way, at the far end of the GDT.
- */
-#define FIRST_RESERVED_GDT_PAGE 14
-#define FIRST_RESERVED_GDT_BYTE (FIRST_RESERVED_GDT_PAGE * 4096)
-#define FIRST_RESERVED_GDT_ENTRY (FIRST_RESERVED_GDT_BYTE / 8)
-
-/*
- * Send an array of these to HYPERVISOR_set_trap_table()
- * The privilege level specifies which modes may enter a trap via a software
- * interrupt. On x86/64, since rings 1 and 2 are unavailable, we allocate
- * privilege levels as follows:
- * Level == 0: No one may enter
- * Level == 1: Kernel may enter
- * Level == 2: Kernel may enter
- * Level == 3: Everyone may enter
- */
-#define TI_GET_DPL(_ti) ((_ti)->flags & 3)
-#define TI_GET_IF(_ti) ((_ti)->flags & 4)
-#define TI_SET_DPL(_ti, _dpl) ((_ti)->flags |= (_dpl))
-#define TI_SET_IF(_ti, _if) ((_ti)->flags |= ((!!(_if))<<2))
-
-#ifndef __ASSEMBLY__
-struct trap_info {
- uint8_t vector; /* exception vector */
- uint8_t flags; /* 0-3: privilege level; 4: clear event enable? */
- uint16_t cs; /* code selector */
- unsigned long address; /* code offset */
-};
-DEFINE_GUEST_HANDLE_STRUCT(trap_info);
-
-struct arch_shared_info {
- unsigned long max_pfn; /* max pfn that appears in table */
- /* Frame containing list of mfns containing list of mfns containing p2m. */
- unsigned long pfn_to_mfn_frame_list_list;
- unsigned long nmi_reason;
-};
-#endif /* !__ASSEMBLY__ */
-
-#ifdef CONFIG_X86_32
-#include <asm/xen/interface_32.h>
-#else
-#include <asm/xen/interface_64.h>
-#endif
-
-#include <asm/pvclock-abi.h>
-
-#ifndef __ASSEMBLY__
-/*
- * The following is all CPU context. Note that the fpu_ctxt block is filled
- * in by FXSAVE if the CPU has feature FXSR; otherwise FSAVE is used.
- */
-struct vcpu_guest_context {
- /* FPU registers come first so they can be aligned for FXSAVE/FXRSTOR. */
- struct { char x[512]; } fpu_ctxt; /* User-level FPU registers */
-#define VGCF_I387_VALID (1<<0)
-#define VGCF_HVM_GUEST (1<<1)
-#define VGCF_IN_KERNEL (1<<2)
- unsigned long flags; /* VGCF_* flags */
- struct cpu_user_regs user_regs; /* User-level CPU registers */
- struct trap_info trap_ctxt[256]; /* Virtual IDT */
- unsigned long ldt_base, ldt_ents; /* LDT (linear address, # ents) */
- unsigned long gdt_frames[16], gdt_ents; /* GDT (machine frames, # ents) */
- unsigned long kernel_ss, kernel_sp; /* Virtual TSS (only SS1/SP1) */
- /* NB. User pagetable on x86/64 is placed in ctrlreg[1]. */
- unsigned long ctrlreg[8]; /* CR0-CR7 (control registers) */
- unsigned long debugreg[8]; /* DB0-DB7 (debug registers) */
-#ifdef __i386__
- unsigned long event_callback_cs; /* CS:EIP of event callback */
- unsigned long event_callback_eip;
- unsigned long failsafe_callback_cs; /* CS:EIP of failsafe callback */
- unsigned long failsafe_callback_eip;
-#else
- unsigned long event_callback_eip;
- unsigned long failsafe_callback_eip;
- unsigned long syscall_callback_eip;
-#endif
- unsigned long vm_assist; /* VMASST_TYPE_* bitmap */
-#ifdef __x86_64__
- /* Segment base addresses. */
- uint64_t fs_base;
- uint64_t gs_base_kernel;
- uint64_t gs_base_user;
-#endif
-};
-DEFINE_GUEST_HANDLE_STRUCT(vcpu_guest_context);
-#endif /* !__ASSEMBLY__ */
-
-/*
- * Prefix forces emulation of some non-trapping instructions.
- * Currently only CPUID.
- */
-#ifdef __ASSEMBLY__
-#define XEN_EMULATE_PREFIX .byte 0x0f,0x0b,0x78,0x65,0x6e ;
-#define XEN_CPUID XEN_EMULATE_PREFIX cpuid
-#else
-#define XEN_EMULATE_PREFIX ".byte 0x0f,0x0b,0x78,0x65,0x6e ; "
-#define XEN_CPUID XEN_EMULATE_PREFIX "cpuid"
-#endif
+#include <uapi/asm/xen/interface.h>

#endif /* _ASM_X86_XEN_INTERFACE_H */
diff --git a/arch/x86/include/asm/xen/interface_32.h b/arch/x86/include/asm/xen/interface_32.h
index 8413688..772174f 100644
--- a/arch/x86/include/asm/xen/interface_32.h
+++ b/arch/x86/include/asm/xen/interface_32.h
@@ -1,102 +1,6 @@
-/******************************************************************************
- * arch-x86_32.h
- *
- * Guest OS interface to x86 32-bit Xen.
- *
- * Copyright (c) 2004, K A Fraser
- */
-
#ifndef _ASM_X86_XEN_INTERFACE_32_H
#define _ASM_X86_XEN_INTERFACE_32_H

-
-/*
- * These flat segments are in the Xen-private section of every GDT. Since these
- * are also present in the initial GDT, many OSes will be able to avoid
- * installing their own GDT.
- */
-#define FLAT_RING1_CS 0xe019 /* GDT index 259 */
-#define FLAT_RING1_DS 0xe021 /* GDT index 260 */
-#define FLAT_RING1_SS 0xe021 /* GDT index 260 */
-#define FLAT_RING3_CS 0xe02b /* GDT index 261 */
-#define FLAT_RING3_DS 0xe033 /* GDT index 262 */
-#define FLAT_RING3_SS 0xe033 /* GDT index 262 */
-
-#define FLAT_KERNEL_CS FLAT_RING1_CS
-#define FLAT_KERNEL_DS FLAT_RING1_DS
-#define FLAT_KERNEL_SS FLAT_RING1_SS
-#define FLAT_USER_CS FLAT_RING3_CS
-#define FLAT_USER_DS FLAT_RING3_DS
-#define FLAT_USER_SS FLAT_RING3_SS
-
-/* And the trap vector is... */
-#define TRAP_INSTR "int $0x82"
-
-#define __MACH2PHYS_VIRT_START 0xF5800000
-#define __MACH2PHYS_VIRT_END 0xF6800000
-
-#define __MACH2PHYS_SHIFT 2
-
-/*
- * Virtual addresses beyond this are not modifiable by guest OSes. The
- * machine->physical mapping table starts at this address, read-only.
- */
-#define __HYPERVISOR_VIRT_START 0xF5800000
-
-#ifndef __ASSEMBLY__
-
-struct cpu_user_regs {
- uint32_t ebx;
- uint32_t ecx;
- uint32_t edx;
- uint32_t esi;
- uint32_t edi;
- uint32_t ebp;
- uint32_t eax;
- uint16_t error_code; /* private */
- uint16_t entry_vector; /* private */
- uint32_t eip;
- uint16_t cs;
- uint8_t saved_upcall_mask;
- uint8_t _pad0;
- uint32_t eflags; /* eflags.IF == !saved_upcall_mask */
- uint32_t esp;
- uint16_t ss, _pad1;
- uint16_t es, _pad2;
- uint16_t ds, _pad3;
- uint16_t fs, _pad4;
- uint16_t gs, _pad5;
-};
-DEFINE_GUEST_HANDLE_STRUCT(cpu_user_regs);
-
-typedef uint64_t tsc_timestamp_t; /* RDTSC timestamp */
-
-struct arch_vcpu_info {
- unsigned long cr2;
- unsigned long pad[5]; /* sizeof(struct vcpu_info) == 64 */
-};
-
-struct xen_callback {
- unsigned long cs;
- unsigned long eip;
-};
-typedef struct xen_callback xen_callback_t;
-
-#define XEN_CALLBACK(__cs, __eip) \
- ((struct xen_callback){ .cs = (__cs), .eip = (unsigned long)(__eip) })
-#endif /* !__ASSEMBLY__ */
-
-
-/*
- * Page-directory addresses above 4GB do not fit into architectural %cr3.
- * When accessing %cr3, or equivalent field in vcpu_guest_context, guests
- * must use the following accessor macros to pack/unpack valid MFNs.
- *
- * Note that Xen is using the fact that the pagetable base is always
- * page-aligned, and putting the 12 MSB of the address into the 12 LSB
- * of cr3.
- */
-#define xen_pfn_to_cr3(pfn) (((unsigned)(pfn) << 12) | ((unsigned)(pfn) >> 20))
-#define xen_cr3_to_pfn(cr3) (((unsigned)(cr3) >> 12) | ((unsigned)(cr3) << 20))
+#include <uapi/asm/xen/interface_32.h>

#endif /* _ASM_X86_XEN_INTERFACE_32_H */
diff --git a/arch/x86/include/asm/xen/interface_64.h b/arch/x86/include/asm/xen/interface_64.h
index 839a481..6d73c4c 100644
--- a/arch/x86/include/asm/xen/interface_64.h
+++ b/arch/x86/include/asm/xen/interface_64.h
@@ -1,148 +1,6 @@
#ifndef _ASM_X86_XEN_INTERFACE_64_H
#define _ASM_X86_XEN_INTERFACE_64_H

-/*
- * 64-bit segment selectors
- * These flat segments are in the Xen-private section of every GDT. Since these
- * are also present in the initial GDT, many OSes will be able to avoid
- * installing their own GDT.
- */
-
-#define FLAT_RING3_CS32 0xe023 /* GDT index 260 */
-#define FLAT_RING3_CS64 0xe033 /* GDT index 261 */
-#define FLAT_RING3_DS32 0xe02b /* GDT index 262 */
-#define FLAT_RING3_DS64 0x0000 /* NULL selector */
-#define FLAT_RING3_SS32 0xe02b /* GDT index 262 */
-#define FLAT_RING3_SS64 0xe02b /* GDT index 262 */
-
-#define FLAT_KERNEL_DS64 FLAT_RING3_DS64
-#define FLAT_KERNEL_DS32 FLAT_RING3_DS32
-#define FLAT_KERNEL_DS FLAT_KERNEL_DS64
-#define FLAT_KERNEL_CS64 FLAT_RING3_CS64
-#define FLAT_KERNEL_CS32 FLAT_RING3_CS32
-#define FLAT_KERNEL_CS FLAT_KERNEL_CS64
-#define FLAT_KERNEL_SS64 FLAT_RING3_SS64
-#define FLAT_KERNEL_SS32 FLAT_RING3_SS32
-#define FLAT_KERNEL_SS FLAT_KERNEL_SS64
-
-#define FLAT_USER_DS64 FLAT_RING3_DS64
-#define FLAT_USER_DS32 FLAT_RING3_DS32
-#define FLAT_USER_DS FLAT_USER_DS64
-#define FLAT_USER_CS64 FLAT_RING3_CS64
-#define FLAT_USER_CS32 FLAT_RING3_CS32
-#define FLAT_USER_CS FLAT_USER_CS64
-#define FLAT_USER_SS64 FLAT_RING3_SS64
-#define FLAT_USER_SS32 FLAT_RING3_SS32
-#define FLAT_USER_SS FLAT_USER_SS64
-
-#define __HYPERVISOR_VIRT_START 0xFFFF800000000000
-#define __HYPERVISOR_VIRT_END 0xFFFF880000000000
-#define __MACH2PHYS_VIRT_START 0xFFFF800000000000
-#define __MACH2PHYS_VIRT_END 0xFFFF804000000000
-#define __MACH2PHYS_SHIFT 3
-
-/*
- * int HYPERVISOR_set_segment_base(unsigned int which, unsigned long base)
- * @which == SEGBASE_* ; @base == 64-bit base address
- * Returns 0 on success.
- */
-#define SEGBASE_FS 0
-#define SEGBASE_GS_USER 1
-#define SEGBASE_GS_KERNEL 2
-#define SEGBASE_GS_USER_SEL 3 /* Set user %gs specified in base[15:0] */
-
-/*
- * int HYPERVISOR_iret(void)
- * All arguments are on the kernel stack, in the following format.
- * Never returns if successful. Current kernel context is lost.
- * The saved CS is mapped as follows:
- * RING0 -> RING3 kernel mode.
- * RING1 -> RING3 kernel mode.
- * RING2 -> RING3 kernel mode.
- * RING3 -> RING3 user mode.
- * However RING0 indicates that the guest kernel should return to iteself
- * directly with
- * orb $3,1*8(%rsp)
- * iretq
- * If flags contains VGCF_in_syscall:
- * Restore RAX, RIP, RFLAGS, RSP.
- * Discard R11, RCX, CS, SS.
- * Otherwise:
- * Restore RAX, R11, RCX, CS:RIP, RFLAGS, SS:RSP.
- * All other registers are saved on hypercall entry and restored to user.
- */
-/* Guest exited in SYSCALL context? Return to guest with SYSRET? */
-#define _VGCF_in_syscall 8
-#define VGCF_in_syscall (1<<_VGCF_in_syscall)
-#define VGCF_IN_SYSCALL VGCF_in_syscall
-
-#ifndef __ASSEMBLY__
-
-struct iret_context {
- /* Top of stack (%rsp at point of hypercall). */
- uint64_t rax, r11, rcx, flags, rip, cs, rflags, rsp, ss;
- /* Bottom of iret stack frame. */
-};
-
-#if defined(__GNUC__) && !defined(__STRICT_ANSI__)
-/* Anonymous union includes both 32- and 64-bit names (e.g., eax/rax). */
-#define __DECL_REG(name) union { \
- uint64_t r ## name, e ## name; \
- uint32_t _e ## name; \
-}
-#else
-/* Non-gcc sources must always use the proper 64-bit name (e.g., rax). */
-#define __DECL_REG(name) uint64_t r ## name
-#endif
-
-struct cpu_user_regs {
- uint64_t r15;
- uint64_t r14;
- uint64_t r13;
- uint64_t r12;
- __DECL_REG(bp);
- __DECL_REG(bx);
- uint64_t r11;
- uint64_t r10;
- uint64_t r9;
- uint64_t r8;
- __DECL_REG(ax);
- __DECL_REG(cx);
- __DECL_REG(dx);
- __DECL_REG(si);
- __DECL_REG(di);
- uint32_t error_code; /* private */
- uint32_t entry_vector; /* private */
- __DECL_REG(ip);
- uint16_t cs, _pad0[1];
- uint8_t saved_upcall_mask;
- uint8_t _pad1[3];
- __DECL_REG(flags); /* rflags.IF == !saved_upcall_mask */
- __DECL_REG(sp);
- uint16_t ss, _pad2[3];
- uint16_t es, _pad3[3];
- uint16_t ds, _pad4[3];
- uint16_t fs, _pad5[3]; /* Non-zero => takes precedence over fs_base. */
- uint16_t gs, _pad6[3]; /* Non-zero => takes precedence over gs_base_usr. */
-};
-DEFINE_GUEST_HANDLE_STRUCT(cpu_user_regs);
-
-#undef __DECL_REG
-
-#define xen_pfn_to_cr3(pfn) ((unsigned long)(pfn) << 12)
-#define xen_cr3_to_pfn(cr3) ((unsigned long)(cr3) >> 12)
-
-struct arch_vcpu_info {
- unsigned long cr2;
- unsigned long pad; /* sizeof(vcpu_info_t) == 64 */
-};
-
-typedef unsigned long xen_callback_t;
-
-#define XEN_CALLBACK(__cs, __rip) \
- ((unsigned long)(__rip))
-
-#endif /* !__ASSEMBLY__ */
-
+#include <uapi/asm/xen/interface_64.h>

#endif /* _ASM_X86_XEN_INTERFACE_64_H */
diff --git a/arch/x86/include/uapi/asm/Kbuild b/arch/x86/include/uapi/asm/Kbuild
index 3dec769..5811a82 100644
--- a/arch/x86/include/uapi/asm/Kbuild
+++ b/arch/x86/include/uapi/asm/Kbuild
@@ -41,6 +41,7 @@ header-y += prctl.h
header-y += processor-flags.h
header-y += ptrace-abi.h
header-y += ptrace.h
+header-y += pvclock-abi.h
header-y += resource.h
header-y += sembuf.h
header-y += setup.h
@@ -63,3 +64,4 @@ header-y += unistd.h
header-y += vm86.h
header-y += vmx.h
header-y += vsyscall.h
+header-y += xen/
diff --git a/arch/x86/include/uapi/asm/pvclock-abi.h b/arch/x86/include/uapi/asm/pvclock-abi.h
new file mode 100644
index 0000000..2dfc62bf
--- /dev/null
+++ b/arch/x86/include/uapi/asm/pvclock-abi.h
@@ -0,0 +1,47 @@
+#ifndef _UAPI_ASM_X86_PVCLOCK_ABI_H
+#define _UAPI_ASM_X86_PVCLOCK_ABI_H
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+
+/*
+ * These structs MUST NOT be changed.
+ * They are the ABI between hypervisor and guest OS.
+ * Both Xen and KVM are using this.
+ *
+ * pvclock_vcpu_time_info holds the system time and the tsc timestamp
+ * of the last update. So the guest can use the tsc delta to get a
+ * more precise system time. There is one per virtual cpu.
+ *
+ * pvclock_wall_clock references the point in time when the system
+ * time was zero (usually boot time), thus the guest calculates the
+ * current wall clock by adding the system time.
+ *
+ * Protocol for the "version" fields is: hypervisor raises it (making
+ * it uneven) before it starts updating the fields and raises it again
+ * (making it even) when it is done. Thus the guest can make sure the
+ * time values it got are consistent by checking the version before
+ * and after reading them.
+ */
+
+struct pvclock_vcpu_time_info {
+ __u32 version;
+ __u32 pad0;
+ __u64 tsc_timestamp;
+ __u64 system_time;
+ __u32 tsc_to_system_mul;
+ __s8 tsc_shift;
+ __u8 flags;
+ __u8 pad[2];
+} __attribute__((__packed__)); /* 32 bytes */
+
+struct pvclock_wall_clock {
+ __u32 version;
+ __u32 sec;
+ __u32 nsec;
+} __attribute__((__packed__));
+
+#define PVCLOCK_TSC_STABLE_BIT (1 << 0)
+#define PVCLOCK_GUEST_STOPPED (1 << 1)
+#endif /* __ASSEMBLY__ */
+#endif /* _UAPI_ASM_X86_PVCLOCK_ABI_H */
diff --git a/arch/x86/include/uapi/asm/xen/Kbuild b/arch/x86/include/uapi/asm/xen/Kbuild
new file mode 100644
index 0000000..6562c9d
--- /dev/null
+++ b/arch/x86/include/uapi/asm/xen/Kbuild
@@ -0,0 +1,5 @@
+# UAPI Header export list
+
+header-y += interface.h
+header-y += interface_32.h
+header-y += interface_64.h
diff --git a/arch/x86/include/uapi/asm/xen/interface.h b/arch/x86/include/uapi/asm/xen/interface.h
new file mode 100644
index 0000000..0b03ccb
--- /dev/null
+++ b/arch/x86/include/uapi/asm/xen/interface.h
@@ -0,0 +1,198 @@
+/******************************************************************************
+ * arch-x86_32.h
+ *
+ * Guest OS interface to x86 Xen.
+ *
+ * Copyright (c) 2004, K A Fraser
+ */
+
+#ifndef _UAPI_ASM_X86_XEN_INTERFACE_H
+#define _UAPI_ASM_X86_XEN_INTERFACE_H
+
+#include <linux/types.h>
+
+#ifdef __XEN__
+#define __DEFINE_GUEST_HANDLE(name, type) \
+ typedef struct { type *p; } __guest_handle_ ## name
+#else
+#define __DEFINE_GUEST_HANDLE(name, type) \
+ typedef type * __guest_handle_ ## name
+#endif
+
+#define DEFINE_GUEST_HANDLE_STRUCT(name) \
+ __DEFINE_GUEST_HANDLE(name, struct name)
+#define DEFINE_GUEST_HANDLE(name) __DEFINE_GUEST_HANDLE(name, name)
+#define GUEST_HANDLE(name) __guest_handle_ ## name
+
+#ifdef __XEN__
+#if defined(__i386__)
+#define set_xen_guest_handle(hnd, val) \
+ do { \
+ if (sizeof(hnd) == 8) \
+ *(__u64 *)&(hnd) = 0; \
+ (hnd).p = val; \
+ } while (0)
+#elif defined(__x86_64__)
+#define set_xen_guest_handle(hnd, val) do { (hnd).p = val; } while (0)
+#endif
+#else
+#if defined(__i386__)
+#define set_xen_guest_handle(hnd, val) \
+ do { \
+ if (sizeof(hnd) == 8) \
+ *(__u64 *)&(hnd) = 0; \
+ (hnd) = val; \
+ } while (0)
+#elif defined(__x86_64__)
+#define set_xen_guest_handle(hnd, val) do { (hnd) = val; } while (0)
+#endif
+#endif
+
+#ifndef __ASSEMBLY__
+/* Explicitly size integers that represent pfns in the public interface
+ * with Xen so that on ARM we can have one ABI that works for 32 and 64
+ * bit guests. */
+typedef unsigned long xen_pfn_t;
+#define PRI_xen_pfn "lx"
+typedef unsigned long xen_ulong_t;
+#define PRI_xen_ulong "lx"
+typedef long xen_long_t;
+#define PRI_xen_long "lx"
+
+/* Guest handles for primitive C types. */
+__DEFINE_GUEST_HANDLE(uchar, unsigned char);
+__DEFINE_GUEST_HANDLE(uint, unsigned int);
+DEFINE_GUEST_HANDLE(char);
+DEFINE_GUEST_HANDLE(int);
+DEFINE_GUEST_HANDLE(void);
+/* HACK many xen parts expect to find these handles, sigh */
+#ifndef uint64_t
+typedef __u64 uint64_t;
+#endif /* uint64_t */
+#ifndef uint32_t
+typedef __u32 uint32_t;
+#endif /* uint32_t */
+DEFINE_GUEST_HANDLE(uint64_t);
+DEFINE_GUEST_HANDLE(uint32_t);
+DEFINE_GUEST_HANDLE(xen_pfn_t);
+DEFINE_GUEST_HANDLE(xen_ulong_t);
+#endif
+
+#ifndef HYPERVISOR_VIRT_START
+#define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START)
+#endif
+
+#define MACH2PHYS_VIRT_START mk_unsigned_long(__MACH2PHYS_VIRT_START)
+#define MACH2PHYS_VIRT_END mk_unsigned_long(__MACH2PHYS_VIRT_END)
+#define MACH2PHYS_NR_ENTRIES ((MACH2PHYS_VIRT_END-MACH2PHYS_VIRT_START)>>__MACH2PHYS_SHIFT)
+
+/* Maximum number of virtual CPUs in multi-processor guests. */
+#define MAX_VIRT_CPUS 32
+
+/*
+ * SEGMENT DESCRIPTOR TABLES
+ */
+/*
+ * A number of GDT entries are reserved by Xen. These are not situated at the
+ * start of the GDT because some stupid OSes export hard-coded selector values
+ * in their ABI. These hard-coded values are always near the start of the GDT,
+ * so Xen places itself out of the way, at the far end of the GDT.
+ */
+#define FIRST_RESERVED_GDT_PAGE 14
+#define FIRST_RESERVED_GDT_BYTE (FIRST_RESERVED_GDT_PAGE * 4096)
+#define FIRST_RESERVED_GDT_ENTRY (FIRST_RESERVED_GDT_BYTE / 8)
+
+/*
+ * Send an array of these to HYPERVISOR_set_trap_table()
+ * The privilege level specifies which modes may enter a trap via a software
+ * interrupt. On x86/64, since rings 1 and 2 are unavailable, we allocate
+ * privilege levels as follows:
+ * Level == 0: No one may enter
+ * Level == 1: Kernel may enter
+ * Level == 2: Kernel may enter
+ * Level == 3: Everyone may enter
+ */
+#define TI_GET_DPL(_ti) ((_ti)->flags & 3)
+#define TI_GET_IF(_ti) ((_ti)->flags & 4)
+#define TI_SET_DPL(_ti, _dpl) ((_ti)->flags |= (_dpl))
+#define TI_SET_IF(_ti, _if) ((_ti)->flags |= ((!!(_if))<<2))
+
+#ifndef __ASSEMBLY__
+struct trap_info {
+ __u8 vector; /* exception vector */
+ __u8 flags; /* 0-3: privilege level; 4: clear event enable? */
+ __u16 cs; /* code selector */
+ unsigned long address; /* code offset */
+};
+DEFINE_GUEST_HANDLE_STRUCT(trap_info);
+
+struct arch_shared_info {
+ unsigned long max_pfn; /* max pfn that appears in table */
+ /* Frame containing list of mfns containing list of mfns containing p2m. */
+ unsigned long pfn_to_mfn_frame_list_list;
+ unsigned long nmi_reason;
+};
+#endif /* !__ASSEMBLY__ */
+
+#ifdef CONFIG_X86_32
+#include <asm/xen/interface_32.h>
+#else
+#include <asm/xen/interface_64.h>
+#endif
+
+#include <asm/pvclock-abi.h>
+
+#ifndef __ASSEMBLY__
+/*
+ * The following is all CPU context. Note that the fpu_ctxt block is filled
+ * in by FXSAVE if the CPU has feature FXSR; otherwise FSAVE is used.
+ */
+struct vcpu_guest_context {
+ /* FPU registers come first so they can be aligned for FXSAVE/FXRSTOR. */
+ struct { char x[512]; } fpu_ctxt; /* User-level FPU registers */
+#define VGCF_I387_VALID (1<<0)
+#define VGCF_HVM_GUEST (1<<1)
+#define VGCF_IN_KERNEL (1<<2)
+ unsigned long flags; /* VGCF_* flags */
+ struct cpu_user_regs user_regs; /* User-level CPU registers */
+ struct trap_info trap_ctxt[256]; /* Virtual IDT */
+ unsigned long ldt_base, ldt_ents; /* LDT (linear address, # ents) */
+ unsigned long gdt_frames[16], gdt_ents; /* GDT (machine frames, # ents) */
+ unsigned long kernel_ss, kernel_sp; /* Virtual TSS (only SS1/SP1) */
+ /* NB. User pagetable on x86/64 is placed in ctrlreg[1]. */
+ unsigned long ctrlreg[8]; /* CR0-CR7 (control registers) */
+ unsigned long debugreg[8]; /* DB0-DB7 (debug registers) */
+#ifdef __i386__
+ unsigned long event_callback_cs; /* CS:EIP of event callback */
+ unsigned long event_callback_eip;
+ unsigned long failsafe_callback_cs; /* CS:EIP of failsafe callback */
+ unsigned long failsafe_callback_eip;
+#else
+ unsigned long event_callback_eip;
+ unsigned long failsafe_callback_eip;
+ unsigned long syscall_callback_eip;
+#endif
+ unsigned long vm_assist; /* VMASST_TYPE_* bitmap */
+#ifdef __x86_64__
+ /* Segment base addresses. */
+ __u64 fs_base;
+ __u64 gs_base_kernel;
+ __u64 gs_base_user;
+#endif
+};
+DEFINE_GUEST_HANDLE_STRUCT(vcpu_guest_context);
+#endif /* !__ASSEMBLY__ */
+
+/*
+ * Prefix forces emulation of some non-trapping instructions.
+ * Currently only CPUID.
+ */
+#ifdef __ASSEMBLY__
+#define XEN_EMULATE_PREFIX .byte 0x0f,0x0b,0x78,0x65,0x6e ;
+#define XEN_CPUID XEN_EMULATE_PREFIX cpuid
+#else
+#define XEN_EMULATE_PREFIX ".byte 0x0f,0x0b,0x78,0x65,0x6e ; "
+#define XEN_CPUID XEN_EMULATE_PREFIX "cpuid"
+#endif
+
+#endif /* _UAPI_ASM_X86_XEN_INTERFACE_H */
diff --git a/arch/x86/include/uapi/asm/xen/interface_32.h b/arch/x86/include/uapi/asm/xen/interface_32.h
new file mode 100644
index 0000000..bb1c93e
--- /dev/null
+++ b/arch/x86/include/uapi/asm/xen/interface_32.h
@@ -0,0 +1,103 @@
+/******************************************************************************
+ * arch-x86_32.h
+ *
+ * Guest OS interface to x86 32-bit Xen.
+ *
+ * Copyright (c) 2004, K A Fraser
+ */
+
+#ifndef _UAPI_ASM_X86_XEN_INTERFACE_32_H
+#define _UAPI_ASM_X86_XEN_INTERFACE_32_H
+
+#include <linux/types.h>
+
+/*
+ * These flat segments are in the Xen-private section of every GDT. Since these
+ * are also present in the initial GDT, many OSes will be able to avoid
+ * installing their own GDT.
+ */
+#define FLAT_RING1_CS 0xe019 /* GDT index 259 */
+#define FLAT_RING1_DS 0xe021 /* GDT index 260 */
+#define FLAT_RING1_SS 0xe021 /* GDT index 260 */
+#define FLAT_RING3_CS 0xe02b /* GDT index 261 */
+#define FLAT_RING3_DS 0xe033 /* GDT index 262 */
+#define FLAT_RING3_SS 0xe033 /* GDT index 262 */
+
+#define FLAT_KERNEL_CS FLAT_RING1_CS
+#define FLAT_KERNEL_DS FLAT_RING1_DS
+#define FLAT_KERNEL_SS FLAT_RING1_SS
+#define FLAT_USER_CS FLAT_RING3_CS
+#define FLAT_USER_DS FLAT_RING3_DS
+#define FLAT_USER_SS FLAT_RING3_SS
+
+/* And the trap vector is... */
+#define TRAP_INSTR "int $0x82"
+
+#define __MACH2PHYS_VIRT_START 0xF5800000
+#define __MACH2PHYS_VIRT_END 0xF6800000
+
+#define __MACH2PHYS_SHIFT 2
+
+/*
+ * Virtual addresses beyond this are not modifiable by guest OSes. The
+ * machine->physical mapping table starts at this address, read-only.
+ */
+#define __HYPERVISOR_VIRT_START 0xF5800000
+
+#ifndef __ASSEMBLY__
+
+struct cpu_user_regs {
+ __u32 ebx;
+ __u32 ecx;
+ __u32 edx;
+ __u32 esi;
+ __u32 edi;
+ __u32 ebp;
+ __u32 eax;
+ __u16 error_code; /* private */
+ __u16 entry_vector; /* private */
+ __u32 eip;
+ __u16 cs;
+ __u8 saved_upcall_mask;
+ __u8 _pad0;
+ __u32 eflags; /* eflags.IF == !saved_upcall_mask */
+ __u32 esp;
+ __u16 ss, _pad1;
+ __u16 es, _pad2;
+ __u16 ds, _pad3;
+ __u16 fs, _pad4;
+ __u16 gs, _pad5;
+};
+DEFINE_GUEST_HANDLE_STRUCT(cpu_user_regs);
+
+typedef __u64 tsc_timestamp_t; /* RDTSC timestamp */
+
+struct arch_vcpu_info {
+ unsigned long cr2;
+ unsigned long pad[5]; /* sizeof(struct vcpu_info) == 64 */
+};
+
+struct xen_callback {
+ unsigned long cs;
+ unsigned long eip;
+};
+typedef struct xen_callback xen_callback_t;
+
+#define XEN_CALLBACK(__cs, __eip) \
+ ((struct xen_callback){ .cs = (__cs), .eip = (unsigned long)(__eip) })
+#endif /* !__ASSEMBLY__ */
+
+
+/*
+ * Page-directory addresses above 4GB do not fit into architectural %cr3.
+ * When accessing %cr3, or equivalent field in vcpu_guest_context, guests
+ * must use the following accessor macros to pack/unpack valid MFNs.
+ *
+ * Note that Xen is using the fact that the pagetable base is always
+ * page-aligned, and putting the 12 MSB of the address into the 12 LSB
+ * of cr3.
+ */
+#define xen_pfn_to_cr3(pfn) (((unsigned)(pfn) << 12) | ((unsigned)(pfn) >> 20))
+#define xen_cr3_to_pfn(cr3) (((unsigned)(cr3) >> 12) | ((unsigned)(cr3) << 20))
+
+#endif /* _UAPI_ASM_X86_XEN_INTERFACE_32_H */
diff --git a/arch/x86/include/uapi/asm/xen/interface_64.h b/arch/x86/include/uapi/asm/xen/interface_64.h
new file mode 100644
index 0000000..a4ed139
--- /dev/null
+++ b/arch/x86/include/uapi/asm/xen/interface_64.h
@@ -0,0 +1,150 @@
+#ifndef _UAPI_ASM_X86_XEN_INTERFACE_64_H
+#define _UAPI_ASM_X86_XEN_INTERFACE_64_H
+
+#include <linux/types.h>
+
+/*
+ * 64-bit segment selectors
+ * These flat segments are in the Xen-private section of every GDT. Since these
+ * are also present in the initial GDT, many OSes will be able to avoid
+ * installing their own GDT.
+ */
+
+#define FLAT_RING3_CS32 0xe023 /* GDT index 260 */
+#define FLAT_RING3_CS64 0xe033 /* GDT index 261 */
+#define FLAT_RING3_DS32 0xe02b /* GDT index 262 */
+#define FLAT_RING3_DS64 0x0000 /* NULL selector */
+#define FLAT_RING3_SS32 0xe02b /* GDT index 262 */
+#define FLAT_RING3_SS64 0xe02b /* GDT index 262 */
+
+#define FLAT_KERNEL_DS64 FLAT_RING3_DS64
+#define FLAT_KERNEL_DS32 FLAT_RING3_DS32
+#define FLAT_KERNEL_DS FLAT_KERNEL_DS64
+#define FLAT_KERNEL_CS64 FLAT_RING3_CS64
+#define FLAT_KERNEL_CS32 FLAT_RING3_CS32
+#define FLAT_KERNEL_CS FLAT_KERNEL_CS64
+#define FLAT_KERNEL_SS64 FLAT_RING3_SS64
+#define FLAT_KERNEL_SS32 FLAT_RING3_SS32
+#define FLAT_KERNEL_SS FLAT_KERNEL_SS64
+
+#define FLAT_USER_DS64 FLAT_RING3_DS64
+#define FLAT_USER_DS32 FLAT_RING3_DS32
+#define FLAT_USER_DS FLAT_USER_DS64
+#define FLAT_USER_CS64 FLAT_RING3_CS64
+#define FLAT_USER_CS32 FLAT_RING3_CS32
+#define FLAT_USER_CS FLAT_USER_CS64
+#define FLAT_USER_SS64 FLAT_RING3_SS64
+#define FLAT_USER_SS32 FLAT_RING3_SS32
+#define FLAT_USER_SS FLAT_USER_SS64
+
+#define __HYPERVISOR_VIRT_START 0xFFFF800000000000
+#define __HYPERVISOR_VIRT_END 0xFFFF880000000000
+#define __MACH2PHYS_VIRT_START 0xFFFF800000000000
+#define __MACH2PHYS_VIRT_END 0xFFFF804000000000
+#define __MACH2PHYS_SHIFT 3
+
+/*
+ * int HYPERVISOR_set_segment_base(unsigned int which, unsigned long base)
+ * @which == SEGBASE_* ; @base == 64-bit base address
+ * Returns 0 on success.
+ */
+#define SEGBASE_FS 0
+#define SEGBASE_GS_USER 1
+#define SEGBASE_GS_KERNEL 2
+#define SEGBASE_GS_USER_SEL 3 /* Set user %gs specified in base[15:0] */
+
+/*
+ * int HYPERVISOR_iret(void)
+ * All arguments are on the kernel stack, in the following format.
+ * Never returns if successful. Current kernel context is lost.
+ * The saved CS is mapped as follows:
+ * RING0 -> RING3 kernel mode.
+ * RING1 -> RING3 kernel mode.
+ * RING2 -> RING3 kernel mode.
+ * RING3 -> RING3 user mode.
+ * However RING0 indicates that the guest kernel should return to iteself
+ * directly with
+ * orb $3,1*8(%rsp)
+ * iretq
+ * If flags contains VGCF_in_syscall:
+ * Restore RAX, RIP, RFLAGS, RSP.
+ * Discard R11, RCX, CS, SS.
+ * Otherwise:
+ * Restore RAX, R11, RCX, CS:RIP, RFLAGS, SS:RSP.
+ * All other registers are saved on hypercall entry and restored to user.
+ */
+/* Guest exited in SYSCALL context? Return to guest with SYSRET? */
+#define _VGCF_in_syscall 8
+#define VGCF_in_syscall (1<<_VGCF_in_syscall)
+#define VGCF_IN_SYSCALL VGCF_in_syscall
+
+#ifndef __ASSEMBLY__
+
+struct iret_context {
+ /* Top of stack (%rsp at point of hypercall). */
+ __u64 rax, r11, rcx, flags, rip, cs, rflags, rsp, ss;
+ /* Bottom of iret stack frame. */
+};
+
+#if defined(__GNUC__) && !defined(__STRICT_ANSI__)
+/* Anonymous union includes both 32- and 64-bit names (e.g., eax/rax). */
+#define __DECL_REG(name) union { \
+ __u64 r ## name, e ## name; \
+ __u32 _e ## name; \
+}
+#else
+/* Non-gcc sources must always use the proper 64-bit name (e.g., rax). */
+#define __DECL_REG(name) __u64 r ## name
+#endif
+
+struct cpu_user_regs {
+ __u64 r15;
+ __u64 r14;
+ __u64 r13;
+ __u64 r12;
+ __DECL_REG(bp);
+ __DECL_REG(bx);
+ __u64 r11;
+ __u64 r10;
+ __u64 r9;
+ __u64 r8;
+ __DECL_REG(ax);
+ __DECL_REG(cx);
+ __DECL_REG(dx);
+ __DECL_REG(si);
+ __DECL_REG(di);
+ __u32 error_code; /* private */
+ __u32 entry_vector; /* private */
+ __DECL_REG(ip);
+ __u16 cs, _pad0[1];
+ __u8 saved_upcall_mask;
+ __u8 _pad1[3];
+ __DECL_REG(flags); /* rflags.IF == !saved_upcall_mask */
+ __DECL_REG(sp);
+ __u16 ss, _pad2[3];
+ __u16 es, _pad3[3];
+ __u16 ds, _pad4[3];
+ __u16 fs, _pad5[3]; /* Non-zero => takes precedence over fs_base. */
+ __u16 gs, _pad6[3]; /* Non-zero => takes precedence over gs_base_usr. */
+};
+DEFINE_GUEST_HANDLE_STRUCT(cpu_user_regs);
+
+#undef __DECL_REG
+
+#define xen_pfn_to_cr3(pfn) ((unsigned long)(pfn) << 12)
+#define xen_cr3_to_pfn(cr3) ((unsigned long)(cr3) >> 12)
+
+struct arch_vcpu_info {
+ unsigned long cr2;
+ unsigned long pad; /* sizeof(vcpu_info_t) == 64 */
+};
+
+typedef unsigned long xen_callback_t;
+
+#define XEN_CALLBACK(__cs, __rip) \
+ ((unsigned long)(__rip))
+
+#endif /* !__ASSEMBLY__ */
+
+
+#endif /* _UAPI_ASM_X86_XEN_INTERFACE_64_H */
diff --git a/include/uapi/xen/Kbuild b/include/uapi/xen/Kbuild
index 5c45962..7453b08 100644
--- a/include/uapi/xen/Kbuild
+++ b/include/uapi/xen/Kbuild
@@ -1,4 +1,5 @@
# UAPI Header export list
+header-y += interface/
header-y += evtchn.h
header-y += gntalloc.h
header-y += gntdev.h
diff --git a/include/uapi/xen/interface/Kbuild b/include/uapi/xen/interface/Kbuild
new file mode 100644
index 0000000..6a062ce
--- /dev/null
+++ b/include/uapi/xen/interface/Kbuild
@@ -0,0 +1,2 @@
+# UAPI Header export list
+header-y += xen.h
diff --git a/include/uapi/xen/interface/xen.h b/include/uapi/xen/interface/xen.h
new file mode 100644
index 0000000..d469852
--- /dev/null
+++ b/include/uapi/xen/interface/xen.h
@@ -0,0 +1,759 @@
+/******************************************************************************
+ * xen.h
+ *
+ * Guest OS interface to Xen.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
+ * Copyright (c) 2004, K A Fraser
+ */
+
+#ifndef __LINUX_PUBLIC_XEN_H__
+#define __LINUX_PUBLIC_XEN_H__
+
+#include <linux/types.h>
+#include <asm/xen/interface.h>
+
+/*
+ * XEN "SYSTEM CALLS" (a.k.a. HYPERCALLS).
+ */
+
+/*
+ * x86_32: EAX = vector; EBX, ECX, EDX, ESI, EDI = args 1, 2, 3, 4, 5.
+ * EAX = return value
+ * (argument registers may be clobbered on return)
+ * x86_64: RAX = vector; RDI, RSI, RDX, R10, R8, R9 = args 1, 2, 3, 4, 5, 6.
+ * RAX = return value
+ * (argument registers not clobbered on return; RCX, R11 are)
+ */
+#define __HYPERVISOR_set_trap_table 0
+#define __HYPERVISOR_mmu_update 1
+#define __HYPERVISOR_set_gdt 2
+#define __HYPERVISOR_stack_switch 3
+#define __HYPERVISOR_set_callbacks 4
+#define __HYPERVISOR_fpu_taskswitch 5
+#define __HYPERVISOR_sched_op_compat 6
+#define __HYPERVISOR_dom0_op 7
+#define __HYPERVISOR_set_debugreg 8
+#define __HYPERVISOR_get_debugreg 9
+#define __HYPERVISOR_update_descriptor 10
+#define __HYPERVISOR_memory_op 12
+#define __HYPERVISOR_multicall 13
+#define __HYPERVISOR_update_va_mapping 14
+#define __HYPERVISOR_set_timer_op 15
+#define __HYPERVISOR_event_channel_op_compat 16
+#define __HYPERVISOR_xen_version 17
+#define __HYPERVISOR_console_io 18
+#define __HYPERVISOR_physdev_op_compat 19
+#define __HYPERVISOR_grant_table_op 20
+#define __HYPERVISOR_vm_assist 21
+#define __HYPERVISOR_update_va_mapping_otherdomain 22
+#define __HYPERVISOR_iret 23 /* x86 only */
+#define __HYPERVISOR_vcpu_op 24
+#define __HYPERVISOR_set_segment_base 25 /* x86/64 only */
+#define __HYPERVISOR_mmuext_op 26
+#define __HYPERVISOR_xsm_op 27
+#define __HYPERVISOR_nmi_op 28
+#define __HYPERVISOR_sched_op 29
+#define __HYPERVISOR_callback_op 30
+#define __HYPERVISOR_xenoprof_op 31
+#define __HYPERVISOR_event_channel_op 32
+#define __HYPERVISOR_physdev_op 33
+#define __HYPERVISOR_hvm_op 34
+#define __HYPERVISOR_sysctl 35
+#define __HYPERVISOR_domctl 36
+#define __HYPERVISOR_kexec_op 37
+#define __HYPERVISOR_tmem_op 38
+#define __HYPERVISOR_xc_reserved_op 39 /* reserved for XenClient */
+
+/* Architecture-specific hypercall definitions. */
+#define __HYPERVISOR_arch_0 48
+#define __HYPERVISOR_arch_1 49
+#define __HYPERVISOR_arch_2 50
+#define __HYPERVISOR_arch_3 51
+#define __HYPERVISOR_arch_4 52
+#define __HYPERVISOR_arch_5 53
+#define __HYPERVISOR_arch_6 54
+#define __HYPERVISOR_arch_7 55
+
+/*
+ * VIRTUAL INTERRUPTS
+ *
+ * Virtual interrupts that a guest OS may receive from Xen.
+ * In the side comments, 'V.' denotes a per-VCPU VIRQ while 'G.' denotes a
+ * global VIRQ. The former can be bound once per VCPU and cannot be re-bound.
+ * The latter can be allocated only once per guest: they must initially be
+ * allocated to VCPU0 but can subsequently be re-bound.
+ */
+#define VIRQ_TIMER 0 /* V. Timebase update, and/or requested timeout. */
+#define VIRQ_DEBUG 1 /* V. Request guest to dump debug info. */
+#define VIRQ_CONSOLE 2 /* G. (DOM0) Bytes received on emergency console. */
+#define VIRQ_DOM_EXC 3 /* G. (DOM0) Exceptional event for some domain. */
+#define VIRQ_TBUF 4 /* G. (DOM0) Trace buffer has records available. */
+#define VIRQ_DEBUGGER 6 /* G. (DOM0) A domain has paused for debugging. */
+#define VIRQ_XENOPROF 7 /* V. XenOprofile interrupt: new sample available */
+#define VIRQ_CON_RING 8 /* G. (DOM0) Bytes received on console */
+#define VIRQ_PCPU_STATE 9 /* G. (DOM0) PCPU state changed */
+#define VIRQ_MEM_EVENT 10 /* G. (DOM0) A memory event has occured */
+#define VIRQ_XC_RESERVED 11 /* G. Reserved for XenClient */
+#define VIRQ_ENOMEM 12 /* G. (DOM0) Low on heap memory */
+
+/* Architecture-specific VIRQ definitions. */
+#define VIRQ_ARCH_0 16
+#define VIRQ_ARCH_1 17
+#define VIRQ_ARCH_2 18
+#define VIRQ_ARCH_3 19
+#define VIRQ_ARCH_4 20
+#define VIRQ_ARCH_5 21
+#define VIRQ_ARCH_6 22
+#define VIRQ_ARCH_7 23
+
+#define NR_VIRQS 24
+
+/*
+ * enum neg_errnoval HYPERVISOR_mmu_update(const struct mmu_update reqs[],
+ * unsigned count, unsigned *done_out,
+ * unsigned foreigndom)
+ * @reqs is an array of mmu_update_t structures ((ptr, val) pairs).
+ * @count is the length of the above array.
+ * @pdone is an output parameter indicating number of completed operations
+ * @foreigndom[15:0]: FD, the expected owner of data pages referenced in this
+ * hypercall invocation. Can be DOMID_SELF.
+ * @foreigndom[31:16]: PFD, the expected owner of pagetable pages referenced
+ * in this hypercall invocation. The value of this field
+ * (x) encodes the PFD as follows:
+ * x == 0 => PFD == DOMID_SELF
+ * x != 0 => PFD == x - 1
+ *
+ * Sub-commands: ptr[1:0] specifies the appropriate MMU_* command.
+ * -------------
+ * ptr[1:0] == MMU_NORMAL_PT_UPDATE:
+ * Updates an entry in a page table belonging to PFD. If updating an L1 table,
+ * and the new table entry is valid/present, the mapped frame must belong to
+ * FD. If attempting to map an I/O page then the caller assumes the privilege
+ * of the FD.
+ * FD == DOMID_IO: Permit /only/ I/O mappings, at the priv level of the caller.
+ * FD == DOMID_XEN: Map restricted areas of Xen's heap space.
+ * ptr[:2] -- Machine address of the page-table entry to modify.
+ * val -- Value to write.
+ *
+ * There also certain implicit requirements when using this hypercall. The
+ * pages that make up a pagetable must be mapped read-only in the guest.
+ * This prevents uncontrolled guest updates to the pagetable. Xen strictly
+ * enforces this, and will disallow any pagetable update which will end up
+ * mapping pagetable page RW, and will disallow using any writable page as a
+ * pagetable. In practice it means that when constructing a page table for a
+ * process, thread, etc, we MUST be very dilligient in following these rules:
+ * 1). Start with top-level page (PGD or in Xen language: L4). Fill out
+ * the entries.
+ * 2). Keep on going, filling out the upper (PUD or L3), and middle (PMD
+ * or L2).
+ * 3). Start filling out the PTE table (L1) with the PTE entries. Once
+ * done, make sure to set each of those entries to RO (so writeable bit
+ * is unset). Once that has been completed, set the PMD (L2) for this
+ * PTE table as RO.
+ * 4). When completed with all of the PMD (L2) entries, and all of them have
+ * been set to RO, make sure to set RO the PUD (L3). Do the same
+ * operation on PGD (L4) pagetable entries that have a PUD (L3) entry.
+ * 5). Now before you can use those pages (so setting the cr3), you MUST also
+ * pin them so that the hypervisor can verify the entries. This is done
+ * via the HYPERVISOR_mmuext_op(MMUEXT_PIN_L4_TABLE, guest physical frame
+ * number of the PGD (L4)). And this point the HYPERVISOR_mmuext_op(
+ * MMUEXT_NEW_BASEPTR, guest physical frame number of the PGD (L4)) can be
+ * issued.
+ * For 32-bit guests, the L4 is not used (as there is less pagetables), so
+ * instead use L3.
+ * At this point the pagetables can be modified using the MMU_NORMAL_PT_UPDATE
+ * hypercall. Also if so desired the OS can also try to write to the PTE
+ * and be trapped by the hypervisor (as the PTE entry is RO).
+ *
+ * To deallocate the pages, the operations are the reverse of the steps
+ * mentioned above. The argument is MMUEXT_UNPIN_TABLE for all levels and the
+ * pagetable MUST not be in use (meaning that the cr3 is not set to it).
+ *
+ * ptr[1:0] == MMU_MACHPHYS_UPDATE:
+ * Updates an entry in the machine->pseudo-physical mapping table.
+ * ptr[:2] -- Machine address within the frame whose mapping to modify.
+ * The frame must belong to the FD, if one is specified.
+ * val -- Value to write into the mapping entry.
+ *
+ * ptr[1:0] == MMU_PT_UPDATE_PRESERVE_AD:
+ * As MMU_NORMAL_PT_UPDATE above, but A/D bits currently in the PTE are ORed
+ * with those in @val.
+ *
+ * @val is usually the machine frame number along with some attributes.
+ * The attributes by default follow the architecture defined bits. Meaning that
+ * if this is a X86_64 machine and four page table layout is used, the layout
+ * of val is:
+ * - 63 if set means No execute (NX)
+ * - 46-13 the machine frame number
+ * - 12 available for guest
+ * - 11 available for guest
+ * - 10 available for guest
+ * - 9 available for guest
+ * - 8 global
+ * - 7 PAT (PSE is disabled, must use hypercall to make 4MB or 2MB pages)
+ * - 6 dirty
+ * - 5 accessed
+ * - 4 page cached disabled
+ * - 3 page write through
+ * - 2 userspace accessible
+ * - 1 writeable
+ * - 0 present
+ *
+ * The one bits that does not fit with the default layout is the PAGE_PSE
+ * also called PAGE_PAT). The MMUEXT_[UN]MARK_SUPER arguments to the
+ * HYPERVISOR_mmuext_op serve as mechanism to set a pagetable to be 4MB
+ * (or 2MB) instead of using the PAGE_PSE bit.
+ *
+ * The reason that the PAGE_PSE (bit 7) is not being utilized is due to Xen
+ * using it as the Page Attribute Table (PAT) bit - for details on it please
+ * refer to Intel SDM 10.12. The PAT allows to set the caching attributes of
+ * pages instead of using MTRRs.
+ *
+ * The PAT MSR is as follows (it is a 64-bit value, each entry is 8 bits):
+ * PAT4 PAT0
+ * +-----+-----+----+----+----+-----+----+----+
+ * | UC | UC- | WC | WB | UC | UC- | WC | WB | <= Linux
+ * +-----+-----+----+----+----+-----+----+----+
+ * | UC | UC- | WT | WB | UC | UC- | WT | WB | <= BIOS (default when machine boots)
+ * +-----+-----+----+----+----+-----+----+----+
+ * | rsv | rsv | WP | WC | UC | UC- | WT | WB | <= Xen
+ * +-----+-----+----+----+----+-----+----+----+
+ *
+ * The lookup of this index table translates to looking up
+ * Bit 7, Bit 4, and Bit 3 of val entry:
+ *
+ * PAT/PSE (bit 7) ... PCD (bit 4) .. PWT (bit 3).
+ *
+ * If all bits are off, then we are using PAT0. If bit 3 turned on,
+ * then we are using PAT1, if bit 3 and bit 4, then PAT2..
+ *
+ * As you can see, the Linux PAT1 translates to PAT4 under Xen. Which means
+ * that if a guest that follows Linux's PAT setup and would like to set Write
+ * Combined on pages it MUST use PAT4 entry. Meaning that Bit 7 (PAGE_PAT) is
+ * set. For example, under Linux it only uses PAT0, PAT1, and PAT2 for the
+ * caching as:
+ *
+ * WB = none (so PAT0)
+ * WC = PWT (bit 3 on)
+ * UC = PWT | PCD (bit 3 and 4 are on).
+ *
+ * To make it work with Xen, it needs to translate the WC bit as so:
+ *
+ * PWT (so bit 3 on) --> PAT (so bit 7 is on) and clear bit 3
+ *
+ * And to translate back it would:
+ *
+ * PAT (bit 7 on) --> PWT (bit 3 on) and clear bit 7.
+ */
+#define MMU_NORMAL_PT_UPDATE 0 /* checked '*ptr = val'. ptr is MA. */
+#define MMU_MACHPHYS_UPDATE 1 /* ptr = MA of frame to modify entry for */
+#define MMU_PT_UPDATE_PRESERVE_AD 2 /* atomically: *ptr = val | (*ptr&(A|D)) */
+
+/*
+ * MMU EXTENDED OPERATIONS
+ *
+ * enum neg_errnoval HYPERVISOR_mmuext_op(mmuext_op_t uops[],
+ * unsigned int count,
+ * unsigned int *pdone,
+ * unsigned int foreigndom)
+ */
+/* HYPERVISOR_mmuext_op() accepts a list of mmuext_op structures.
+ * A foreigndom (FD) can be specified (or DOMID_SELF for none).
+ * Where the FD has some effect, it is described below.
+ *
+ * cmd: MMUEXT_(UN)PIN_*_TABLE
+ * mfn: Machine frame number to be (un)pinned as a p.t. page.
+ * The frame must belong to the FD, if one is specified.
+ *
+ * cmd: MMUEXT_NEW_BASEPTR
+ * mfn: Machine frame number of new page-table base to install in MMU.
+ *
+ * cmd: MMUEXT_NEW_USER_BASEPTR [x86/64 only]
+ * mfn: Machine frame number of new page-table base to install in MMU
+ * when in user space.
+ *
+ * cmd: MMUEXT_TLB_FLUSH_LOCAL
+ * No additional arguments. Flushes local TLB.
+ *
+ * cmd: MMUEXT_INVLPG_LOCAL
+ * linear_addr: Linear address to be flushed from the local TLB.
+ *
+ * cmd: MMUEXT_TLB_FLUSH_MULTI
+ * vcpumask: Pointer to bitmap of VCPUs to be flushed.
+ *
+ * cmd: MMUEXT_INVLPG_MULTI
+ * linear_addr: Linear address to be flushed.
+ * vcpumask: Pointer to bitmap of VCPUs to be flushed.
+ *
+ * cmd: MMUEXT_TLB_FLUSH_ALL
+ * No additional arguments. Flushes all VCPUs' TLBs.
+ *
+ * cmd: MMUEXT_INVLPG_ALL
+ * linear_addr: Linear address to be flushed from all VCPUs' TLBs.
+ *
+ * cmd: MMUEXT_FLUSH_CACHE
+ * No additional arguments. Writes back and flushes cache contents.
+ *
+ * cmd: MMUEXT_FLUSH_CACHE_GLOBAL
+ * No additional arguments. Writes back and flushes cache contents
+ * on all CPUs in the system.
+ *
+ * cmd: MMUEXT_SET_LDT
+ * linear_addr: Linear address of LDT base (NB. must be page-aligned).
+ * nr_ents: Number of entries in LDT.
+ *
+ * cmd: MMUEXT_CLEAR_PAGE
+ * mfn: Machine frame number to be cleared.
+ *
+ * cmd: MMUEXT_COPY_PAGE
+ * mfn: Machine frame number of the destination page.
+ * src_mfn: Machine frame number of the source page.
+ *
+ * cmd: MMUEXT_[UN]MARK_SUPER
+ * mfn: Machine frame number of head of superpage to be [un]marked.
+ */
+#define MMUEXT_PIN_L1_TABLE 0
+#define MMUEXT_PIN_L2_TABLE 1
+#define MMUEXT_PIN_L3_TABLE 2
+#define MMUEXT_PIN_L4_TABLE 3
+#define MMUEXT_UNPIN_TABLE 4
+#define MMUEXT_NEW_BASEPTR 5
+#define MMUEXT_TLB_FLUSH_LOCAL 6
+#define MMUEXT_INVLPG_LOCAL 7
+#define MMUEXT_TLB_FLUSH_MULTI 8
+#define MMUEXT_INVLPG_MULTI 9
+#define MMUEXT_TLB_FLUSH_ALL 10
+#define MMUEXT_INVLPG_ALL 11
+#define MMUEXT_FLUSH_CACHE 12
+#define MMUEXT_SET_LDT 13
+#define MMUEXT_NEW_USER_BASEPTR 15
+#define MMUEXT_CLEAR_PAGE 16
+#define MMUEXT_COPY_PAGE 17
+#define MMUEXT_FLUSH_CACHE_GLOBAL 18
+#define MMUEXT_MARK_SUPER 19
+#define MMUEXT_UNMARK_SUPER 20
+
+#ifndef __ASSEMBLY__
+struct mmuext_op {
+ unsigned int cmd;
+ union {
+ /* [UN]PIN_TABLE, NEW_BASEPTR, NEW_USER_BASEPTR
+ * CLEAR_PAGE, COPY_PAGE, [UN]MARK_SUPER */
+ xen_pfn_t mfn;
+ /* INVLPG_LOCAL, INVLPG_ALL, SET_LDT */
+ unsigned long linear_addr;
+ } arg1;
+ union {
+ /* SET_LDT */
+ unsigned int nr_ents;
+ /* TLB_FLUSH_MULTI, INVLPG_MULTI */
+ void *vcpumask;
+ /* COPY_PAGE */
+ xen_pfn_t src_mfn;
+ } arg2;
+};
+DEFINE_GUEST_HANDLE_STRUCT(mmuext_op);
+#endif
+
+/* These are passed as 'flags' to update_va_mapping. They can be ORed. */
+/* When specifying UVMF_MULTI, also OR in a pointer to a CPU bitmap. */
+/* UVMF_LOCAL is merely UVMF_MULTI with a NULL bitmap pointer. */
+#define UVMF_NONE (0UL<<0) /* No flushing at all. */
+#define UVMF_TLB_FLUSH (1UL<<0) /* Flush entire TLB(s). */
+#define UVMF_INVLPG (2UL<<0) /* Flush only one entry. */
+#define UVMF_FLUSHTYPE_MASK (3UL<<0)
+#define UVMF_MULTI (0UL<<2) /* Flush subset of TLBs. */
+#define UVMF_LOCAL (0UL<<2) /* Flush local TLB. */
+#define UVMF_ALL (1UL<<2) /* Flush all TLBs. */
+
+/*
+ * Commands to HYPERVISOR_console_io().
+ */
+#define CONSOLEIO_write 0
+#define CONSOLEIO_read 1
+
+/*
+ * Commands to HYPERVISOR_vm_assist().
+ */
+#define VMASST_CMD_enable 0
+#define VMASST_CMD_disable 1
+
+/* x86/32 guests: simulate full 4GB segment limits. */
+#define VMASST_TYPE_4gb_segments 0
+
+/* x86/32 guests: trap (vector 15) whenever above vmassist is used. */
+#define VMASST_TYPE_4gb_segments_notify 1
+
+/*
+ * x86 guests: support writes to bottom-level PTEs.
+ * NB1. Page-directory entries cannot be written.
+ * NB2. Guest must continue to remove all writable mappings of PTEs.
+ */
+#define VMASST_TYPE_writable_pagetables 2
+
+/* x86/PAE guests: support PDPTs above 4GB. */
+#define VMASST_TYPE_pae_extended_cr3 3
+
+#define MAX_VMASST_TYPE 3
+
+#ifndef __ASSEMBLY__
+
+typedef __u16 domid_t;
+
+/* Domain ids >= DOMID_FIRST_RESERVED cannot be used for ordinary domains. */
+#define DOMID_FIRST_RESERVED (0x7FF0U)
+
+/* DOMID_SELF is used in certain contexts to refer to oneself. */
+#define DOMID_SELF (0x7FF0U)
+
+/*
+ * DOMID_IO is used to restrict page-table updates to mapping I/O memory.
+ * Although no Foreign Domain need be specified to map I/O pages, DOMID_IO
+ * is useful to ensure that no mappings to the OS's own heap are accidentally
+ * installed. (e.g., in Linux this could cause havoc as reference counts
+ * aren't adjusted on the I/O-mapping code path).
+ * This only makes sense in MMUEXT_SET_FOREIGNDOM, but in that context can
+ * be specified by any calling domain.
+ */
+#define DOMID_IO (0x7FF1U)
+
+/*
+ * DOMID_XEN is used to allow privileged domains to map restricted parts of
+ * Xen's heap space (e.g., the machine_to_phys table).
+ * This only makes sense in MMUEXT_SET_FOREIGNDOM, and is only permitted if
+ * the caller is privileged.
+ */
+#define DOMID_XEN (0x7FF2U)
+
+/* DOMID_COW is used as the owner of sharable pages */
+#define DOMID_COW (0x7FF3U)
+
+/* DOMID_INVALID is used to identify pages with unknown owner. */
+#define DOMID_INVALID (0x7FF4U)
+
+/* Idle domain. */
+#define DOMID_IDLE (0x7FFFU)
+
+/*
+ * Send an array of these to HYPERVISOR_mmu_update().
+ * NB. The fields are natural pointer/address size for this architecture.
+ */
+struct mmu_update {
+ __u64 ptr; /* Machine address of PTE. */
+ __u64 val; /* New contents of PTE. */
+};
+DEFINE_GUEST_HANDLE_STRUCT(mmu_update);
+
+/*
+ * Send an array of these to HYPERVISOR_multicall().
+ * NB. The fields are logically the natural register size for this
+ * architecture. In cases where xen_ulong_t is larger than this then
+ * any unused bits in the upper portion must be zero.
+ */
+struct multicall_entry {
+ xen_ulong_t op;
+ xen_long_t result;
+ xen_ulong_t args[6];
+};
+DEFINE_GUEST_HANDLE_STRUCT(multicall_entry);
+
+struct vcpu_time_info {
+ /*
+ * Updates to the following values are preceded and followed
+ * by an increment of 'version'. The guest can therefore
+ * detect updates by looking for changes to 'version'. If the
+ * least-significant bit of the version number is set then an
+ * update is in progress and the guest must wait to read a
+ * consistent set of values. The correct way to interact with
+ * the version number is similar to Linux's seqlock: see the
+ * implementations of read_seqbegin/read_seqretry.
+ */
+ __u32 version;
+ __u32 pad0;
+ __u64 tsc_timestamp; /* TSC at last update of time vals. */
+ __u64 system_time; /* Time, in nanosecs, since boot. */
+ /*
+ * Current system time:
+ * system_time + ((tsc - tsc_timestamp) << tsc_shift) * tsc_to_system_mul
+ * CPU frequency (Hz):
+ * ((10^9 << 32) / tsc_to_system_mul) >> tsc_shift
+ */
+ __u32 tsc_to_system_mul;
+ __s8 tsc_shift;
+ __s8 pad1[3];
+}; /* 32 bytes */
+
+struct vcpu_info {
+ /*
+ * 'evtchn_upcall_pending' is written non-zero by Xen to indicate
+ * a pending notification for a particular VCPU. It is then cleared
+ * by the guest OS /before/ checking for pending work, thus avoiding
+ * a set-and-check race. Note that the mask is only accessed by Xen
+ * on the CPU that is currently hosting the VCPU. This means that the
+ * pending and mask flags can be updated by the guest without special
+ * synchronisation (i.e., no need for the x86 LOCK prefix).
+ * This may seem suboptimal because if the pending flag is set by
+ * a different CPU then an IPI may be scheduled even when the mask
+ * is set. However, note:
+ * 1. The task of 'interrupt holdoff' is covered by the per-event-
+ * channel mask bits. A 'noisy' event that is continually being
+ * triggered can be masked at source at this very precise
+ * granularity.
+ * 2. The main purpose of the per-VCPU mask is therefore to restrict
+ * reentrant execution: whether for concurrency control, or to
+ * prevent unbounded stack usage. Whatever the purpose, we expect
+ * that the mask will be asserted only for short periods at a time,
+ * and so the likelihood of a 'spurious' IPI is suitably small.
+ * The mask is read before making an event upcall to the guest: a
+ * non-zero mask therefore guarantees that the VCPU will not receive
+ * an upcall activation. The mask is cleared when the VCPU requests
+ * to block: this avoids wakeup-waiting races.
+ */
+ __u8 evtchn_upcall_pending;
+ __u8 evtchn_upcall_mask;
+ xen_ulong_t evtchn_pending_sel;
+ struct arch_vcpu_info arch;
+ struct pvclock_vcpu_time_info time;
+}; /* 64 bytes (x86) */
+
+/*
+ * Xen/kernel shared data -- pointer provided in start_info.
+ * NB. We expect that this struct is smaller than a page.
+ */
+struct shared_info {
+ struct vcpu_info vcpu_info[MAX_VIRT_CPUS];
+
+ /*
+ * A domain can create "event channels" on which it can send and receive
+ * asynchronous event notifications. There are three classes of event that
+ * are delivered by this mechanism:
+ * 1. Bi-directional inter- and intra-domain connections. Domains must
+ * arrange out-of-band to set up a connection (usually by allocating
+ * an unbound 'listener' port and avertising that via a storage service
+ * such as xenstore).
+ * 2. Physical interrupts. A domain with suitable hardware-access
+ * privileges can bind an event-channel port to a physical interrupt
+ * source.
+ * 3. Virtual interrupts ('events'). A domain can bind an event-channel
+ * port to a virtual interrupt source, such as the virtual-timer
+ * device or the emergency console.
+ *
+ * Event channels are addressed by a "port index". Each channel is
+ * associated with two bits of information:
+ * 1. PENDING -- notifies the domain that there is a pending notification
+ * to be processed. This bit is cleared by the guest.
+ * 2. MASK -- if this bit is clear then a 0->1 transition of PENDING
+ * will cause an asynchronous upcall to be scheduled. This bit is only
+ * updated by the guest. It is read-only within Xen. If a channel
+ * becomes pending while the channel is masked then the 'edge' is lost
+ * (i.e., when the channel is unmasked, the guest must manually handle
+ * pending notifications as no upcall will be scheduled by Xen).
+ *
+ * To expedite scanning of pending notifications, any 0->1 pending
+ * transition on an unmasked channel causes a corresponding bit in a
+ * per-vcpu selector word to be set. Each bit in the selector covers a
+ * 'C long' in the PENDING bitfield array.
+ */
+ xen_ulong_t evtchn_pending[sizeof(xen_ulong_t) * 8];
+ xen_ulong_t evtchn_mask[sizeof(xen_ulong_t) * 8];
+
+ /*
+ * Wallclock time: updated only by control software. Guests should base
+ * their gettimeofday() syscall on this wallclock-base value.
+ */
+ struct pvclock_wall_clock wc;
+
+ struct arch_shared_info arch;
+
+};
+
+/*
+ * Start-of-day memory layout for the initial domain (DOM0):
+ * 1. The domain is started within contiguous virtual-memory region.
+ * 2. The contiguous region begins and ends on an aligned 4MB boundary.
+ * 3. The region start corresponds to the load address of the OS image.
+ * If the load address is not 4MB aligned then the address is rounded down.
+ * 4. This the order of bootstrap elements in the initial virtual region:
+ * a. relocated kernel image
+ * b. initial ram disk [mod_start, mod_len]
+ * c. list of allocated page frames [mfn_list, nr_pages]
+ * d. start_info_t structure [register ESI (x86)]
+ * e. bootstrap page tables [pt_base, CR3 (x86)]
+ * f. bootstrap stack [register ESP (x86)]
+ * 5. Bootstrap elements are packed together, but each is 4kB-aligned.
+ * 6. The initial ram disk may be omitted.
+ * 7. The list of page frames forms a contiguous 'pseudo-physical' memory
+ * layout for the domain. In particular, the bootstrap virtual-memory
+ * region is a 1:1 mapping to the first section of the pseudo-physical map.
+ * 8. All bootstrap elements are mapped read-writable for the guest OS. The
+ * only exception is the bootstrap page table, which is mapped read-only.
+ * 9. There is guaranteed to be at least 512kB padding after the final
+ * bootstrap element. If necessary, the bootstrap virtual region is
+ * extended by an extra 4MB to ensure this.
+ */
+
+#define MAX_GUEST_CMDLINE 1024
+struct start_info {
+ /* THE FOLLOWING ARE FILLED IN BOTH ON INITIAL BOOT AND ON RESUME. */
+ char magic[32]; /* "xen-<version>-<platform>". */
+ unsigned long nr_pages; /* Total pages allocated to this domain. */
+ unsigned long shared_info; /* MACHINE address of shared info struct. */
+ __u32 flags; /* SIF_xxx flags. */
+ xen_pfn_t store_mfn; /* MACHINE page number of shared page. */
+ __u32 store_evtchn; /* Event channel for store communication. */
+ union {
+ struct {
+ xen_pfn_t mfn; /* MACHINE page number of console page. */
+ __u32 evtchn; /* Event channel for console page. */
+ } domU;
+ struct {
+ __u32 info_off; /* Offset of console_info struct. */
+ __u32 info_size; /* Size of console_info struct from start.*/
+ } dom0;
+ } console;
+ /* THE FOLLOWING ARE ONLY FILLED IN ON INITIAL BOOT (NOT RESUME). */
+ unsigned long pt_base; /* VIRTUAL address of page directory. */
+ unsigned long nr_pt_frames; /* Number of bootstrap p.t. frames. */
+ unsigned long mfn_list; /* VIRTUAL address of page-frame list. */
+ unsigned long mod_start; /* VIRTUAL address of pre-loaded module. */
+ unsigned long mod_len; /* Size (bytes) of pre-loaded module. */
+ __s8 cmd_line[MAX_GUEST_CMDLINE];
+ /* The pfn range here covers both page table and p->m table frames. */
+ unsigned long first_p2m_pfn;/* 1st pfn forming initial P->M table. */
+ unsigned long nr_p2m_frames;/* # of pfns forming initial P->M table. */
+};
+
+/* These flags are passed in the 'flags' field of start_info_t. */
+#define SIF_PRIVILEGED (1<<0) /* Is the domain privileged? */
+#define SIF_INITDOMAIN (1<<1) /* Is this the initial control domain? */
+#define SIF_MULTIBOOT_MOD (1<<2) /* Is mod_start a multiboot module? */
+#define SIF_MOD_START_PFN (1<<3) /* Is mod_start a PFN? */
+#define SIF_PM_MASK (0xFF<<8) /* reserve 1 byte for xen-pm options */
+
+/*
+ * A multiboot module is a package containing modules very similar to a
+ * multiboot module array. The only differences are:
+ * - the array of module descriptors is by convention simply at the beginning
+ * of the multiboot module,
+ * - addresses in the module descriptors are based on the beginning of the
+ * multiboot module,
+ * - the number of modules is determined by a termination descriptor that has
+ * mod_start == 0.
+ *
+ * This permits to both build it statically and reference it in a configuration
+ * file, and let the PV guest easily rebase the addresses to virtual addresses
+ * and at the same time count the number of modules.
+ */
+struct xen_multiboot_mod_list {
+ /* Address of first byte of the module */
+ __u32 mod_start;
+ /* Address of last byte of the module (inclusive) */
+ __u32 mod_end;
+ /* Address of zero-terminated command line */
+ __u32 cmdline;
+ /* Unused, must be zero */
+ __u32 pad;
+};
+/*
+ * The console structure in start_info.console.dom0
+ *
+ * This structure includes a variety of information required to
+ * have a working VGA/VESA console.
+ */
+struct dom0_vga_console_info {
+ __u8 video_type;
+#define XEN_VGATYPE_TEXT_MODE_3 0x03
+#define XEN_VGATYPE_VESA_LFB 0x23
+#define XEN_VGATYPE_EFI_LFB 0x70
+
+ union {
+ struct {
+ /* Font height, in pixels. */
+ __u16 font_height;
+ /* Cursor location (column, row). */
+ __u16 cursor_x, cursor_y;
+ /* Number of rows and columns (dimensions in characters). */
+ __u16 rows, columns;
+ } text_mode_3;
+
+ struct {
+ /* Width and height, in pixels. */
+ __u16 width, height;
+ /* Bytes per scan line. */
+ __u16 bytes_per_line;
+ /* Bits per pixel. */
+ __u16 bits_per_pixel;
+ /* LFB physical address, and size (in units of 64kB). */
+ __u32 lfb_base;
+ __u32 lfb_size;
+ /* RGB mask offsets and sizes, as defined by VBE 1.2+ */
+ __u8 red_pos, red_size;
+ __u8 green_pos, green_size;
+ __u8 blue_pos, blue_size;
+ __u8 rsvd_pos, rsvd_size;
+
+ /* VESA capabilities (offset 0xa, VESA command 0x4f00). */
+ __u32 gbl_caps;
+ /* Mode attributes (offset 0x0, VESA command 0x4f01). */
+ __u16 mode_attrs;
+ } vesa_lfb;
+ } u;
+};
+
+typedef __u64 cpumap_t;
+
+typedef __u8 xen_domain_handle_t[16];
+
+/* Turn a plain number into a C unsigned long constant. */
+#define __mk_unsigned_long(x) x ## UL
+#define mk_unsigned_long(x) __mk_unsigned_long(x)
+
+#define TMEM_SPEC_VERSION 1
+
+struct tmem_op {
+ __u32 cmd;
+ __s32 pool_id;
+ union {
+ struct { /* for cmd == TMEM_NEW_POOL */
+ __u64 uuid[2];
+ __u32 flags;
+ } new;
+ struct {
+ __u64 oid[3];
+ __u32 index;
+ __u32 tmem_offset;
+ __u32 pfn_offset;
+ __u32 len;
+ GUEST_HANDLE(void) gmfn; /* guest machine page frame */
+ } gen;
+ } u;
+};
+
+DEFINE_GUEST_HANDLE(__u64);
+
+#else /* __ASSEMBLY__ */
+
+/* In assembly code we cannot use C numeric constant suffixes. */
+#define mk_unsigned_long(x) x
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __LINUX_PUBLIC_XEN_H__ */
diff --git a/include/xen/interface/xen.h b/include/xen/interface/xen.h
index a483789..f69a8de 100644
--- a/include/xen/interface/xen.h
+++ b/include/xen/interface/xen.h
@@ -1,758 +1,6 @@
-/******************************************************************************
- * xen.h
- *
- * Guest OS interface to Xen.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to
- * deal in the Software without restriction, including without limitation the
- * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
- * sell copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- *
- * Copyright (c) 2004, K A Fraser
- */
-
#ifndef __XEN_PUBLIC_XEN_H__
#define __XEN_PUBLIC_XEN_H__

-#include <asm/xen/interface.h>
-
-/*
- * XEN "SYSTEM CALLS" (a.k.a. HYPERCALLS).
- */
-
-/*
- * x86_32: EAX = vector; EBX, ECX, EDX, ESI, EDI = args 1, 2, 3, 4, 5.
- * EAX = return value
- * (argument registers may be clobbered on return)
- * x86_64: RAX = vector; RDI, RSI, RDX, R10, R8, R9 = args 1, 2, 3, 4, 5, 6.
- * RAX = return value
- * (argument registers not clobbered on return; RCX, R11 are)
- */
-#define __HYPERVISOR_set_trap_table 0
-#define __HYPERVISOR_mmu_update 1
-#define __HYPERVISOR_set_gdt 2
-#define __HYPERVISOR_stack_switch 3
-#define __HYPERVISOR_set_callbacks 4
-#define __HYPERVISOR_fpu_taskswitch 5
-#define __HYPERVISOR_sched_op_compat 6
-#define __HYPERVISOR_dom0_op 7
-#define __HYPERVISOR_set_debugreg 8
-#define __HYPERVISOR_get_debugreg 9
-#define __HYPERVISOR_update_descriptor 10
-#define __HYPERVISOR_memory_op 12
-#define __HYPERVISOR_multicall 13
-#define __HYPERVISOR_update_va_mapping 14
-#define __HYPERVISOR_set_timer_op 15
-#define __HYPERVISOR_event_channel_op_compat 16
-#define __HYPERVISOR_xen_version 17
-#define __HYPERVISOR_console_io 18
-#define __HYPERVISOR_physdev_op_compat 19
-#define __HYPERVISOR_grant_table_op 20
-#define __HYPERVISOR_vm_assist 21
-#define __HYPERVISOR_update_va_mapping_otherdomain 22
-#define __HYPERVISOR_iret 23 /* x86 only */
-#define __HYPERVISOR_vcpu_op 24
-#define __HYPERVISOR_set_segment_base 25 /* x86/64 only */
-#define __HYPERVISOR_mmuext_op 26
-#define __HYPERVISOR_xsm_op 27
-#define __HYPERVISOR_nmi_op 28
-#define __HYPERVISOR_sched_op 29
-#define __HYPERVISOR_callback_op 30
-#define __HYPERVISOR_xenoprof_op 31
-#define __HYPERVISOR_event_channel_op 32
-#define __HYPERVISOR_physdev_op 33
-#define __HYPERVISOR_hvm_op 34
-#define __HYPERVISOR_sysctl 35
-#define __HYPERVISOR_domctl 36
-#define __HYPERVISOR_kexec_op 37
-#define __HYPERVISOR_tmem_op 38
-#define __HYPERVISOR_xc_reserved_op 39 /* reserved for XenClient */
-
-/* Architecture-specific hypercall definitions. */
-#define __HYPERVISOR_arch_0 48
-#define __HYPERVISOR_arch_1 49
-#define __HYPERVISOR_arch_2 50
-#define __HYPERVISOR_arch_3 51
-#define __HYPERVISOR_arch_4 52
-#define __HYPERVISOR_arch_5 53
-#define __HYPERVISOR_arch_6 54
-#define __HYPERVISOR_arch_7 55
-
-/*
- * VIRTUAL INTERRUPTS
- *
- * Virtual interrupts that a guest OS may receive from Xen.
- * In the side comments, 'V.' denotes a per-VCPU VIRQ while 'G.' denotes a
- * global VIRQ. The former can be bound once per VCPU and cannot be re-bound.
- * The latter can be allocated only once per guest: they must initially be
- * allocated to VCPU0 but can subsequently be re-bound.
- */
-#define VIRQ_TIMER 0 /* V. Timebase update, and/or requested timeout. */
-#define VIRQ_DEBUG 1 /* V. Request guest to dump debug info. */
-#define VIRQ_CONSOLE 2 /* G. (DOM0) Bytes received on emergency console. */
-#define VIRQ_DOM_EXC 3 /* G. (DOM0) Exceptional event for some domain. */
-#define VIRQ_TBUF 4 /* G. (DOM0) Trace buffer has records available. */
-#define VIRQ_DEBUGGER 6 /* G. (DOM0) A domain has paused for debugging. */
-#define VIRQ_XENOPROF 7 /* V. XenOprofile interrupt: new sample available */
-#define VIRQ_CON_RING 8 /* G. (DOM0) Bytes received on console */
-#define VIRQ_PCPU_STATE 9 /* G. (DOM0) PCPU state changed */
-#define VIRQ_MEM_EVENT 10 /* G. (DOM0) A memory event has occured */
-#define VIRQ_XC_RESERVED 11 /* G. Reserved for XenClient */
-#define VIRQ_ENOMEM 12 /* G. (DOM0) Low on heap memory */
-
-/* Architecture-specific VIRQ definitions. */
-#define VIRQ_ARCH_0 16
-#define VIRQ_ARCH_1 17
-#define VIRQ_ARCH_2 18
-#define VIRQ_ARCH_3 19
-#define VIRQ_ARCH_4 20
-#define VIRQ_ARCH_5 21
-#define VIRQ_ARCH_6 22
-#define VIRQ_ARCH_7 23
-
-#define NR_VIRQS 24
-
-/*
- * enum neg_errnoval HYPERVISOR_mmu_update(const struct mmu_update reqs[],
- * unsigned count, unsigned *done_out,
- * unsigned foreigndom)
- * @reqs is an array of mmu_update_t structures ((ptr, val) pairs).
- * @count is the length of the above array.
- * @pdone is an output parameter indicating number of completed operations
- * @foreigndom[15:0]: FD, the expected owner of data pages referenced in this
- * hypercall invocation. Can be DOMID_SELF.
- * @foreigndom[31:16]: PFD, the expected owner of pagetable pages referenced
- * in this hypercall invocation. The value of this field
- * (x) encodes the PFD as follows:
- * x == 0 => PFD == DOMID_SELF
- * x != 0 => PFD == x - 1
- *
- * Sub-commands: ptr[1:0] specifies the appropriate MMU_* command.
- * -------------
- * ptr[1:0] == MMU_NORMAL_PT_UPDATE:
- * Updates an entry in a page table belonging to PFD. If updating an L1 table,
- * and the new table entry is valid/present, the mapped frame must belong to
- * FD. If attempting to map an I/O page then the caller assumes the privilege
- * of the FD.
- * FD == DOMID_IO: Permit /only/ I/O mappings, at the priv level of the caller.
- * FD == DOMID_XEN: Map restricted areas of Xen's heap space.
- * ptr[:2] -- Machine address of the page-table entry to modify.
- * val -- Value to write.
- *
- * There also certain implicit requirements when using this hypercall. The
- * pages that make up a pagetable must be mapped read-only in the guest.
- * This prevents uncontrolled guest updates to the pagetable. Xen strictly
- * enforces this, and will disallow any pagetable update which will end up
- * mapping pagetable page RW, and will disallow using any writable page as a
- * pagetable. In practice it means that when constructing a page table for a
- * process, thread, etc, we MUST be very dilligient in following these rules:
- * 1). Start with top-level page (PGD or in Xen language: L4). Fill out
- * the entries.
- * 2). Keep on going, filling out the upper (PUD or L3), and middle (PMD
- * or L2).
- * 3). Start filling out the PTE table (L1) with the PTE entries. Once
- * done, make sure to set each of those entries to RO (so writeable bit
- * is unset). Once that has been completed, set the PMD (L2) for this
- * PTE table as RO.
- * 4). When completed with all of the PMD (L2) entries, and all of them have
- * been set to RO, make sure to set RO the PUD (L3). Do the same
- * operation on PGD (L4) pagetable entries that have a PUD (L3) entry.
- * 5). Now before you can use those pages (so setting the cr3), you MUST also
- * pin them so that the hypervisor can verify the entries. This is done
- * via the HYPERVISOR_mmuext_op(MMUEXT_PIN_L4_TABLE, guest physical frame
- * number of the PGD (L4)). And this point the HYPERVISOR_mmuext_op(
- * MMUEXT_NEW_BASEPTR, guest physical frame number of the PGD (L4)) can be
- * issued.
- * For 32-bit guests, the L4 is not used (as there is less pagetables), so
- * instead use L3.
- * At this point the pagetables can be modified using the MMU_NORMAL_PT_UPDATE
- * hypercall. Also if so desired the OS can also try to write to the PTE
- * and be trapped by the hypervisor (as the PTE entry is RO).
- *
- * To deallocate the pages, the operations are the reverse of the steps
- * mentioned above. The argument is MMUEXT_UNPIN_TABLE for all levels and the
- * pagetable MUST not be in use (meaning that the cr3 is not set to it).
- *
- * ptr[1:0] == MMU_MACHPHYS_UPDATE:
- * Updates an entry in the machine->pseudo-physical mapping table.
- * ptr[:2] -- Machine address within the frame whose mapping to modify.
- * The frame must belong to the FD, if one is specified.
- * val -- Value to write into the mapping entry.
- *
- * ptr[1:0] == MMU_PT_UPDATE_PRESERVE_AD:
- * As MMU_NORMAL_PT_UPDATE above, but A/D bits currently in the PTE are ORed
- * with those in @val.
- *
- * @val is usually the machine frame number along with some attributes.
- * The attributes by default follow the architecture defined bits. Meaning that
- * if this is a X86_64 machine and four page table layout is used, the layout
- * of val is:
- * - 63 if set means No execute (NX)
- * - 46-13 the machine frame number
- * - 12 available for guest
- * - 11 available for guest
- * - 10 available for guest
- * - 9 available for guest
- * - 8 global
- * - 7 PAT (PSE is disabled, must use hypercall to make 4MB or 2MB pages)
- * - 6 dirty
- * - 5 accessed
- * - 4 page cached disabled
- * - 3 page write through
- * - 2 userspace accessible
- * - 1 writeable
- * - 0 present
- *
- * The one bits that does not fit with the default layout is the PAGE_PSE
- * also called PAGE_PAT). The MMUEXT_[UN]MARK_SUPER arguments to the
- * HYPERVISOR_mmuext_op serve as mechanism to set a pagetable to be 4MB
- * (or 2MB) instead of using the PAGE_PSE bit.
- *
- * The reason that the PAGE_PSE (bit 7) is not being utilized is due to Xen
- * using it as the Page Attribute Table (PAT) bit - for details on it please
- * refer to Intel SDM 10.12. The PAT allows to set the caching attributes of
- * pages instead of using MTRRs.
- *
- * The PAT MSR is as follows (it is a 64-bit value, each entry is 8 bits):
- * PAT4 PAT0
- * +-----+-----+----+----+----+-----+----+----+
- * | UC | UC- | WC | WB | UC | UC- | WC | WB | <= Linux
- * +-----+-----+----+----+----+-----+----+----+
- * | UC | UC- | WT | WB | UC | UC- | WT | WB | <= BIOS (default when machine boots)
- * +-----+-----+----+----+----+-----+----+----+
- * | rsv | rsv | WP | WC | UC | UC- | WT | WB | <= Xen
- * +-----+-----+----+----+----+-----+----+----+
- *
- * The lookup of this index table translates to looking up
- * Bit 7, Bit 4, and Bit 3 of val entry:
- *
- * PAT/PSE (bit 7) ... PCD (bit 4) .. PWT (bit 3).
- *
- * If all bits are off, then we are using PAT0. If bit 3 turned on,
- * then we are using PAT1, if bit 3 and bit 4, then PAT2..
- *
- * As you can see, the Linux PAT1 translates to PAT4 under Xen. Which means
- * that if a guest that follows Linux's PAT setup and would like to set Write
- * Combined on pages it MUST use PAT4 entry. Meaning that Bit 7 (PAGE_PAT) is
- * set. For example, under Linux it only uses PAT0, PAT1, and PAT2 for the
- * caching as:
- *
- * WB = none (so PAT0)
- * WC = PWT (bit 3 on)
- * UC = PWT | PCD (bit 3 and 4 are on).
- *
- * To make it work with Xen, it needs to translate the WC bit as so:
- *
- * PWT (so bit 3 on) --> PAT (so bit 7 is on) and clear bit 3
- *
- * And to translate back it would:
- *
- * PAT (bit 7 on) --> PWT (bit 3 on) and clear bit 7.
- */
-#define MMU_NORMAL_PT_UPDATE 0 /* checked '*ptr = val'. ptr is MA. */
-#define MMU_MACHPHYS_UPDATE 1 /* ptr = MA of frame to modify entry for */
-#define MMU_PT_UPDATE_PRESERVE_AD 2 /* atomically: *ptr = val | (*ptr&(A|D)) */
-
-/*
- * MMU EXTENDED OPERATIONS
- *
- * enum neg_errnoval HYPERVISOR_mmuext_op(mmuext_op_t uops[],
- * unsigned int count,
- * unsigned int *pdone,
- * unsigned int foreigndom)
- */
-/* HYPERVISOR_mmuext_op() accepts a list of mmuext_op structures.
- * A foreigndom (FD) can be specified (or DOMID_SELF for none).
- * Where the FD has some effect, it is described below.
- *
- * cmd: MMUEXT_(UN)PIN_*_TABLE
- * mfn: Machine frame number to be (un)pinned as a p.t. page.
- * The frame must belong to the FD, if one is specified.
- *
- * cmd: MMUEXT_NEW_BASEPTR
- * mfn: Machine frame number of new page-table base to install in MMU.
- *
- * cmd: MMUEXT_NEW_USER_BASEPTR [x86/64 only]
- * mfn: Machine frame number of new page-table base to install in MMU
- * when in user space.
- *
- * cmd: MMUEXT_TLB_FLUSH_LOCAL
- * No additional arguments. Flushes local TLB.
- *
- * cmd: MMUEXT_INVLPG_LOCAL
- * linear_addr: Linear address to be flushed from the local TLB.
- *
- * cmd: MMUEXT_TLB_FLUSH_MULTI
- * vcpumask: Pointer to bitmap of VCPUs to be flushed.
- *
- * cmd: MMUEXT_INVLPG_MULTI
- * linear_addr: Linear address to be flushed.
- * vcpumask: Pointer to bitmap of VCPUs to be flushed.
- *
- * cmd: MMUEXT_TLB_FLUSH_ALL
- * No additional arguments. Flushes all VCPUs' TLBs.
- *
- * cmd: MMUEXT_INVLPG_ALL
- * linear_addr: Linear address to be flushed from all VCPUs' TLBs.
- *
- * cmd: MMUEXT_FLUSH_CACHE
- * No additional arguments. Writes back and flushes cache contents.
- *
- * cmd: MMUEXT_FLUSH_CACHE_GLOBAL
- * No additional arguments. Writes back and flushes cache contents
- * on all CPUs in the system.
- *
- * cmd: MMUEXT_SET_LDT
- * linear_addr: Linear address of LDT base (NB. must be page-aligned).
- * nr_ents: Number of entries in LDT.
- *
- * cmd: MMUEXT_CLEAR_PAGE
- * mfn: Machine frame number to be cleared.
- *
- * cmd: MMUEXT_COPY_PAGE
- * mfn: Machine frame number of the destination page.
- * src_mfn: Machine frame number of the source page.
- *
- * cmd: MMUEXT_[UN]MARK_SUPER
- * mfn: Machine frame number of head of superpage to be [un]marked.
- */
-#define MMUEXT_PIN_L1_TABLE 0
-#define MMUEXT_PIN_L2_TABLE 1
-#define MMUEXT_PIN_L3_TABLE 2
-#define MMUEXT_PIN_L4_TABLE 3
-#define MMUEXT_UNPIN_TABLE 4
-#define MMUEXT_NEW_BASEPTR 5
-#define MMUEXT_TLB_FLUSH_LOCAL 6
-#define MMUEXT_INVLPG_LOCAL 7
-#define MMUEXT_TLB_FLUSH_MULTI 8
-#define MMUEXT_INVLPG_MULTI 9
-#define MMUEXT_TLB_FLUSH_ALL 10
-#define MMUEXT_INVLPG_ALL 11
-#define MMUEXT_FLUSH_CACHE 12
-#define MMUEXT_SET_LDT 13
-#define MMUEXT_NEW_USER_BASEPTR 15
-#define MMUEXT_CLEAR_PAGE 16
-#define MMUEXT_COPY_PAGE 17
-#define MMUEXT_FLUSH_CACHE_GLOBAL 18
-#define MMUEXT_MARK_SUPER 19
-#define MMUEXT_UNMARK_SUPER 20
-
-#ifndef __ASSEMBLY__
-struct mmuext_op {
- unsigned int cmd;
- union {
- /* [UN]PIN_TABLE, NEW_BASEPTR, NEW_USER_BASEPTR
- * CLEAR_PAGE, COPY_PAGE, [UN]MARK_SUPER */
- xen_pfn_t mfn;
- /* INVLPG_LOCAL, INVLPG_ALL, SET_LDT */
- unsigned long linear_addr;
- } arg1;
- union {
- /* SET_LDT */
- unsigned int nr_ents;
- /* TLB_FLUSH_MULTI, INVLPG_MULTI */
- void *vcpumask;
- /* COPY_PAGE */
- xen_pfn_t src_mfn;
- } arg2;
-};
-DEFINE_GUEST_HANDLE_STRUCT(mmuext_op);
-#endif
-
-/* These are passed as 'flags' to update_va_mapping. They can be ORed. */
-/* When specifying UVMF_MULTI, also OR in a pointer to a CPU bitmap. */
-/* UVMF_LOCAL is merely UVMF_MULTI with a NULL bitmap pointer. */
-#define UVMF_NONE (0UL<<0) /* No flushing at all. */
-#define UVMF_TLB_FLUSH (1UL<<0) /* Flush entire TLB(s). */
-#define UVMF_INVLPG (2UL<<0) /* Flush only one entry. */
-#define UVMF_FLUSHTYPE_MASK (3UL<<0)
-#define UVMF_MULTI (0UL<<2) /* Flush subset of TLBs. */
-#define UVMF_LOCAL (0UL<<2) /* Flush local TLB. */
-#define UVMF_ALL (1UL<<2) /* Flush all TLBs. */
-
-/*
- * Commands to HYPERVISOR_console_io().
- */
-#define CONSOLEIO_write 0
-#define CONSOLEIO_read 1
-
-/*
- * Commands to HYPERVISOR_vm_assist().
- */
-#define VMASST_CMD_enable 0
-#define VMASST_CMD_disable 1
-
-/* x86/32 guests: simulate full 4GB segment limits. */
-#define VMASST_TYPE_4gb_segments 0
-
-/* x86/32 guests: trap (vector 15) whenever above vmassist is used. */
-#define VMASST_TYPE_4gb_segments_notify 1
-
-/*
- * x86 guests: support writes to bottom-level PTEs.
- * NB1. Page-directory entries cannot be written.
- * NB2. Guest must continue to remove all writable mappings of PTEs.
- */
-#define VMASST_TYPE_writable_pagetables 2
-
-/* x86/PAE guests: support PDPTs above 4GB. */
-#define VMASST_TYPE_pae_extended_cr3 3
-
-#define MAX_VMASST_TYPE 3
-
-#ifndef __ASSEMBLY__
-
-typedef uint16_t domid_t;
-
-/* Domain ids >= DOMID_FIRST_RESERVED cannot be used for ordinary domains. */
-#define DOMID_FIRST_RESERVED (0x7FF0U)
-
-/* DOMID_SELF is used in certain contexts to refer to oneself. */
-#define DOMID_SELF (0x7FF0U)
-
-/*
- * DOMID_IO is used to restrict page-table updates to mapping I/O memory.
- * Although no Foreign Domain need be specified to map I/O pages, DOMID_IO
- * is useful to ensure that no mappings to the OS's own heap are accidentally
- * installed. (e.g., in Linux this could cause havoc as reference counts
- * aren't adjusted on the I/O-mapping code path).
- * This only makes sense in MMUEXT_SET_FOREIGNDOM, but in that context can
- * be specified by any calling domain.
- */
-#define DOMID_IO (0x7FF1U)
-
-/*
- * DOMID_XEN is used to allow privileged domains to map restricted parts of
- * Xen's heap space (e.g., the machine_to_phys table).
- * This only makes sense in MMUEXT_SET_FOREIGNDOM, and is only permitted if
- * the caller is privileged.
- */
-#define DOMID_XEN (0x7FF2U)
-
-/* DOMID_COW is used as the owner of sharable pages */
-#define DOMID_COW (0x7FF3U)
-
-/* DOMID_INVALID is used to identify pages with unknown owner. */
-#define DOMID_INVALID (0x7FF4U)
-
-/* Idle domain. */
-#define DOMID_IDLE (0x7FFFU)
-
-/*
- * Send an array of these to HYPERVISOR_mmu_update().
- * NB. The fields are natural pointer/address size for this architecture.
- */
-struct mmu_update {
- uint64_t ptr; /* Machine address of PTE. */
- uint64_t val; /* New contents of PTE. */
-};
-DEFINE_GUEST_HANDLE_STRUCT(mmu_update);
-
-/*
- * Send an array of these to HYPERVISOR_multicall().
- * NB. The fields are logically the natural register size for this
- * architecture. In cases where xen_ulong_t is larger than this then
- * any unused bits in the upper portion must be zero.
- */
-struct multicall_entry {
- xen_ulong_t op;
- xen_long_t result;
- xen_ulong_t args[6];
-};
-DEFINE_GUEST_HANDLE_STRUCT(multicall_entry);
-
-struct vcpu_time_info {
- /*
- * Updates to the following values are preceded and followed
- * by an increment of 'version'. The guest can therefore
- * detect updates by looking for changes to 'version'. If the
- * least-significant bit of the version number is set then an
- * update is in progress and the guest must wait to read a
- * consistent set of values. The correct way to interact with
- * the version number is similar to Linux's seqlock: see the
- * implementations of read_seqbegin/read_seqretry.
- */
- uint32_t version;
- uint32_t pad0;
- uint64_t tsc_timestamp; /* TSC at last update of time vals. */
- uint64_t system_time; /* Time, in nanosecs, since boot. */
- /*
- * Current system time:
- * system_time + ((tsc - tsc_timestamp) << tsc_shift) * tsc_to_system_mul
- * CPU frequency (Hz):
- * ((10^9 << 32) / tsc_to_system_mul) >> tsc_shift
- */
- uint32_t tsc_to_system_mul;
- int8_t tsc_shift;
- int8_t pad1[3];
-}; /* 32 bytes */
-
-struct vcpu_info {
- /*
- * 'evtchn_upcall_pending' is written non-zero by Xen to indicate
- * a pending notification for a particular VCPU. It is then cleared
- * by the guest OS /before/ checking for pending work, thus avoiding
- * a set-and-check race. Note that the mask is only accessed by Xen
- * on the CPU that is currently hosting the VCPU. This means that the
- * pending and mask flags can be updated by the guest without special
- * synchronisation (i.e., no need for the x86 LOCK prefix).
- * This may seem suboptimal because if the pending flag is set by
- * a different CPU then an IPI may be scheduled even when the mask
- * is set. However, note:
- * 1. The task of 'interrupt holdoff' is covered by the per-event-
- * channel mask bits. A 'noisy' event that is continually being
- * triggered can be masked at source at this very precise
- * granularity.
- * 2. The main purpose of the per-VCPU mask is therefore to restrict
- * reentrant execution: whether for concurrency control, or to
- * prevent unbounded stack usage. Whatever the purpose, we expect
- * that the mask will be asserted only for short periods at a time,
- * and so the likelihood of a 'spurious' IPI is suitably small.
- * The mask is read before making an event upcall to the guest: a
- * non-zero mask therefore guarantees that the VCPU will not receive
- * an upcall activation. The mask is cleared when the VCPU requests
- * to block: this avoids wakeup-waiting races.
- */
- uint8_t evtchn_upcall_pending;
- uint8_t evtchn_upcall_mask;
- xen_ulong_t evtchn_pending_sel;
- struct arch_vcpu_info arch;
- struct pvclock_vcpu_time_info time;
-}; /* 64 bytes (x86) */
-
-/*
- * Xen/kernel shared data -- pointer provided in start_info.
- * NB. We expect that this struct is smaller than a page.
- */
-struct shared_info {
- struct vcpu_info vcpu_info[MAX_VIRT_CPUS];
-
- /*
- * A domain can create "event channels" on which it can send and receive
- * asynchronous event notifications. There are three classes of event that
- * are delivered by this mechanism:
- * 1. Bi-directional inter- and intra-domain connections. Domains must
- * arrange out-of-band to set up a connection (usually by allocating
- * an unbound 'listener' port and avertising that via a storage service
- * such as xenstore).
- * 2. Physical interrupts. A domain with suitable hardware-access
- * privileges can bind an event-channel port to a physical interrupt
- * source.
- * 3. Virtual interrupts ('events'). A domain can bind an event-channel
- * port to a virtual interrupt source, such as the virtual-timer
- * device or the emergency console.
- *
- * Event channels are addressed by a "port index". Each channel is
- * associated with two bits of information:
- * 1. PENDING -- notifies the domain that there is a pending notification
- * to be processed. This bit is cleared by the guest.
- * 2. MASK -- if this bit is clear then a 0->1 transition of PENDING
- * will cause an asynchronous upcall to be scheduled. This bit is only
- * updated by the guest. It is read-only within Xen. If a channel
- * becomes pending while the channel is masked then the 'edge' is lost
- * (i.e., when the channel is unmasked, the guest must manually handle
- * pending notifications as no upcall will be scheduled by Xen).
- *
- * To expedite scanning of pending notifications, any 0->1 pending
- * transition on an unmasked channel causes a corresponding bit in a
- * per-vcpu selector word to be set. Each bit in the selector covers a
- * 'C long' in the PENDING bitfield array.
- */
- xen_ulong_t evtchn_pending[sizeof(xen_ulong_t) * 8];
- xen_ulong_t evtchn_mask[sizeof(xen_ulong_t) * 8];
-
- /*
- * Wallclock time: updated only by control software. Guests should base
- * their gettimeofday() syscall on this wallclock-base value.
- */
- struct pvclock_wall_clock wc;
-
- struct arch_shared_info arch;
-
-};
-
-/*
- * Start-of-day memory layout for the initial domain (DOM0):
- * 1. The domain is started within contiguous virtual-memory region.
- * 2. The contiguous region begins and ends on an aligned 4MB boundary.
- * 3. The region start corresponds to the load address of the OS image.
- * If the load address is not 4MB aligned then the address is rounded down.
- * 4. This the order of bootstrap elements in the initial virtual region:
- * a. relocated kernel image
- * b. initial ram disk [mod_start, mod_len]
- * c. list of allocated page frames [mfn_list, nr_pages]
- * d. start_info_t structure [register ESI (x86)]
- * e. bootstrap page tables [pt_base, CR3 (x86)]
- * f. bootstrap stack [register ESP (x86)]
- * 5. Bootstrap elements are packed together, but each is 4kB-aligned.
- * 6. The initial ram disk may be omitted.
- * 7. The list of page frames forms a contiguous 'pseudo-physical' memory
- * layout for the domain. In particular, the bootstrap virtual-memory
- * region is a 1:1 mapping to the first section of the pseudo-physical map.
- * 8. All bootstrap elements are mapped read-writable for the guest OS. The
- * only exception is the bootstrap page table, which is mapped read-only.
- * 9. There is guaranteed to be at least 512kB padding after the final
- * bootstrap element. If necessary, the bootstrap virtual region is
- * extended by an extra 4MB to ensure this.
- */
-
-#define MAX_GUEST_CMDLINE 1024
-struct start_info {
- /* THE FOLLOWING ARE FILLED IN BOTH ON INITIAL BOOT AND ON RESUME. */
- char magic[32]; /* "xen-<version>-<platform>". */
- unsigned long nr_pages; /* Total pages allocated to this domain. */
- unsigned long shared_info; /* MACHINE address of shared info struct. */
- uint32_t flags; /* SIF_xxx flags. */
- xen_pfn_t store_mfn; /* MACHINE page number of shared page. */
- uint32_t store_evtchn; /* Event channel for store communication. */
- union {
- struct {
- xen_pfn_t mfn; /* MACHINE page number of console page. */
- uint32_t evtchn; /* Event channel for console page. */
- } domU;
- struct {
- uint32_t info_off; /* Offset of console_info struct. */
- uint32_t info_size; /* Size of console_info struct from start.*/
- } dom0;
- } console;
- /* THE FOLLOWING ARE ONLY FILLED IN ON INITIAL BOOT (NOT RESUME). */
- unsigned long pt_base; /* VIRTUAL address of page directory. */
- unsigned long nr_pt_frames; /* Number of bootstrap p.t. frames. */
- unsigned long mfn_list; /* VIRTUAL address of page-frame list. */
- unsigned long mod_start; /* VIRTUAL address of pre-loaded module. */
- unsigned long mod_len; /* Size (bytes) of pre-loaded module. */
- int8_t cmd_line[MAX_GUEST_CMDLINE];
- /* The pfn range here covers both page table and p->m table frames. */
- unsigned long first_p2m_pfn;/* 1st pfn forming initial P->M table. */
- unsigned long nr_p2m_frames;/* # of pfns forming initial P->M table. */
-};
-
-/* These flags are passed in the 'flags' field of start_info_t. */
-#define SIF_PRIVILEGED (1<<0) /* Is the domain privileged? */
-#define SIF_INITDOMAIN (1<<1) /* Is this the initial control domain? */
-#define SIF_MULTIBOOT_MOD (1<<2) /* Is mod_start a multiboot module? */
-#define SIF_MOD_START_PFN (1<<3) /* Is mod_start a PFN? */
-#define SIF_PM_MASK (0xFF<<8) /* reserve 1 byte for xen-pm options */
-
-/*
- * A multiboot module is a package containing modules very similar to a
- * multiboot module array. The only differences are:
- * - the array of module descriptors is by convention simply at the beginning
- * of the multiboot module,
- * - addresses in the module descriptors are based on the beginning of the
- * multiboot module,
- * - the number of modules is determined by a termination descriptor that has
- * mod_start == 0.
- *
- * This permits to both build it statically and reference it in a configuration
- * file, and let the PV guest easily rebase the addresses to virtual addresses
- * and at the same time count the number of modules.
- */
-struct xen_multiboot_mod_list {
- /* Address of first byte of the module */
- uint32_t mod_start;
- /* Address of last byte of the module (inclusive) */
- uint32_t mod_end;
- /* Address of zero-terminated command line */
- uint32_t cmdline;
- /* Unused, must be zero */
- uint32_t pad;
-};
-/*
- * The console structure in start_info.console.dom0
- *
- * This structure includes a variety of information required to
- * have a working VGA/VESA console.
- */
-struct dom0_vga_console_info {
- uint8_t video_type;
-#define XEN_VGATYPE_TEXT_MODE_3 0x03
-#define XEN_VGATYPE_VESA_LFB 0x23
-#define XEN_VGATYPE_EFI_LFB 0x70
-
- union {
- struct {
- /* Font height, in pixels. */
- uint16_t font_height;
- /* Cursor location (column, row). */
- uint16_t cursor_x, cursor_y;
- /* Number of rows and columns (dimensions in characters). */
- uint16_t rows, columns;
- } text_mode_3;
-
- struct {
- /* Width and height, in pixels. */
- uint16_t width, height;
- /* Bytes per scan line. */
- uint16_t bytes_per_line;
- /* Bits per pixel. */
- uint16_t bits_per_pixel;
- /* LFB physical address, and size (in units of 64kB). */
- uint32_t lfb_base;
- uint32_t lfb_size;
- /* RGB mask offsets and sizes, as defined by VBE 1.2+ */
- uint8_t red_pos, red_size;
- uint8_t green_pos, green_size;
- uint8_t blue_pos, blue_size;
- uint8_t rsvd_pos, rsvd_size;
-
- /* VESA capabilities (offset 0xa, VESA command 0x4f00). */
- uint32_t gbl_caps;
- /* Mode attributes (offset 0x0, VESA command 0x4f01). */
- uint16_t mode_attrs;
- } vesa_lfb;
- } u;
-};
-
-typedef uint64_t cpumap_t;
-
-typedef uint8_t xen_domain_handle_t[16];
-
-/* Turn a plain number into a C unsigned long constant. */
-#define __mk_unsigned_long(x) x ## UL
-#define mk_unsigned_long(x) __mk_unsigned_long(x)
-
-#define TMEM_SPEC_VERSION 1
-
-struct tmem_op {
- uint32_t cmd;
- int32_t pool_id;
- union {
- struct { /* for cmd == TMEM_NEW_POOL */
- uint64_t uuid[2];
- uint32_t flags;
- } new;
- struct {
- uint64_t oid[3];
- uint32_t index;
- uint32_t tmem_offset;
- uint32_t pfn_offset;
- uint32_t len;
- GUEST_HANDLE(void) gmfn; /* guest machine page frame */
- } gen;
- } u;
-};
-
-DEFINE_GUEST_HANDLE(u64);
-
-#else /* __ASSEMBLY__ */
-
-/* In assembly code we cannot use C numeric constant suffixes. */
-#define mk_unsigned_long(x) x
-
-#endif /* !__ASSEMBLY__ */
+#include <uapi/xen/interface/xen.h>

#endif /* __XEN_PUBLIC_XEN_H__ */
--
2.1.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Next message: Mikko Rapeli: "[PATCH 77/98] include/uapi/linux/errqueue.h: include linux/time.h"
Previous message: Mikko Rapeli: "[PATCH 70/98] include/uapi/linux/netfilter/xt_HMARK.h: include linux/netfilter.h"
In reply to: Mikko Rapeli: "[PATCH 70/98] include/uapi/linux/netfilter/xt_HMARK.h: include linux/netfilter.h"
Next in thread: Andrew Cooper: "Re: [Xen-devel] [PATCH 95/98] HACK: fix include/uapi/xen/privcmd.h compilation in userspace"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]