Eric Lee / smarc-fsl-linux-kernel

Commit ecbf29cdb3990c83d90d0c4187c89fb2ce423367

Authored by Jeremy Fitzhardinge 17 years ago

Committed by Ingo Molnar 17 years ago

Exists in master and in 39 other branches

xen: clean up asm/xen/hypervisor.h

Impact: cleanup

hypervisor.h had accumulated a lot of crud, including lots of spurious
#includes.  Clean it all up, and go around fixing up everything else
accordingly.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

Showing 8 changed files with 31 additions and 33 deletions Inline Diff

arch/x86/include/asm/xen/hypercall.h
arch/x86/include/asm/xen/hypervisor.h
arch/x86/include/asm/xen/page.h
arch/x86/xen/enlighten.c
drivers/xen/balloon.c
drivers/xen/features.c
drivers/xen/grant-table.c
include/xen/interface/event_channel.h

arch/x86/include/asm/xen/hypercall.h

Diff comments View file @ ecbf29c

 /******************************************************************************
  * hypercall.h
  *
  * Linux-specific hypervisor handling.
  *
  * Copyright (c) 2002-2004, K A Fraser
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License version 2
  * as published by the Free Software Foundation; or, when distributed
  * separately from the Linux kernel or incorporated into other
  * software packages, subject to the following license:
  *
  * Permission is hereby granted, free of charge, to any person obtaining a copy
  * of this source file (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.
  */
 #ifndef _ASM_X86_XEN_HYPERCALL_H
 #define _ASM_X86_XEN_HYPERCALL_H
+#include <linux/kernel.h>
+#include <linux/spinlock.h>
 #include <linux/errno.h>
 #include <linux/string.h>
+#include <linux/types.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
 #include <xen/interface/xen.h>
 #include <xen/interface/sched.h>
 #include <xen/interface/physdev.h>
 /*
  * The hypercall asms have to meet several constraints:
  * - Work on 32- and 64-bit.
  *    The two architectures put their arguments in different sets of
  *    registers.
  *
  * - Work around asm syntax quirks
  *    It isn't possible to specify one of the rNN registers in a
  *    constraint, so we use explicit register variables to get the
  *    args into the right place.
  *
  * - Mark all registers as potentially clobbered
  *    Even unused parameters can be clobbered by the hypervisor, so we
  *    need to make sure gcc knows it.
  *
  * - Avoid compiler bugs.
  *    This is the tricky part.  Because x86_32 has such a constrained
  *    register set, gcc versions below 4.3 have trouble generating
  *    code when all the arg registers and memory are trashed by the
  *    asm.  There are syntactically simpler ways of achieving the
  *    semantics below, but they cause the compiler to crash.
  *
  *    The only combination I found which works is:
  *     - assign the __argX variables first
  *     - list all actually used parameters as "+r" (__argX)
  *     - clobber the rest
  *
  * The result certainly isn't pretty, and it really shows up cpp's
  * weakness as as macro language.  Sorry.  (But let's just give thanks
  * there aren't more than 5 arguments...)
  */
 extern struct { char _entry[32]; } hypercall_page[];
 #define __HYPERCALL		"call hypercall_page+%c[offset]"
 #define __HYPERCALL_ENTRY(x)						\
 	[offset] "i" (__HYPERVISOR_##x * sizeof(hypercall_page[0]))
 #ifdef CONFIG_X86_32
 #define __HYPERCALL_RETREG	"eax"
 #define __HYPERCALL_ARG1REG	"ebx"
 #define __HYPERCALL_ARG2REG	"ecx"
 #define __HYPERCALL_ARG3REG	"edx"
 #define __HYPERCALL_ARG4REG	"esi"
 #define __HYPERCALL_ARG5REG	"edi"
 #else
 #define __HYPERCALL_RETREG	"rax"
 #define __HYPERCALL_ARG1REG	"rdi"
 #define __HYPERCALL_ARG2REG	"rsi"
 #define __HYPERCALL_ARG3REG	"rdx"
 #define __HYPERCALL_ARG4REG	"r10"
 #define __HYPERCALL_ARG5REG	"r8"
 #endif
 #define __HYPERCALL_DECLS						\
 	register unsigned long __res  asm(__HYPERCALL_RETREG);		\
 	register unsigned long __arg1 asm(__HYPERCALL_ARG1REG) = __arg1; \
 	register unsigned long __arg2 asm(__HYPERCALL_ARG2REG) = __arg2; \
 	register unsigned long __arg3 asm(__HYPERCALL_ARG3REG) = __arg3; \
 	register unsigned long __arg4 asm(__HYPERCALL_ARG4REG) = __arg4; \
 	register unsigned long __arg5 asm(__HYPERCALL_ARG5REG) = __arg5;
 #define __HYPERCALL_0PARAM	"=r" (__res)
 #define __HYPERCALL_1PARAM	__HYPERCALL_0PARAM, "+r" (__arg1)
 #define __HYPERCALL_2PARAM	__HYPERCALL_1PARAM, "+r" (__arg2)
 #define __HYPERCALL_3PARAM	__HYPERCALL_2PARAM, "+r" (__arg3)
 #define __HYPERCALL_4PARAM	__HYPERCALL_3PARAM, "+r" (__arg4)
 #define __HYPERCALL_5PARAM	__HYPERCALL_4PARAM, "+r" (__arg5)
 #define __HYPERCALL_0ARG()
 #define __HYPERCALL_1ARG(a1)						\
 	__HYPERCALL_0ARG()		__arg1 = (unsigned long)(a1);
 #define __HYPERCALL_2ARG(a1,a2)						\
 	__HYPERCALL_1ARG(a1)		__arg2 = (unsigned long)(a2);
 #define __HYPERCALL_3ARG(a1,a2,a3)					\
 	__HYPERCALL_2ARG(a1,a2)		__arg3 = (unsigned long)(a3);
 #define __HYPERCALL_4ARG(a1,a2,a3,a4)					\
 	__HYPERCALL_3ARG(a1,a2,a3)	__arg4 = (unsigned long)(a4);
 #define __HYPERCALL_5ARG(a1,a2,a3,a4,a5)				\
 	__HYPERCALL_4ARG(a1,a2,a3,a4)	__arg5 = (unsigned long)(a5);
 #define __HYPERCALL_CLOBBER5	"memory"
 #define __HYPERCALL_CLOBBER4	__HYPERCALL_CLOBBER5, __HYPERCALL_ARG5REG
 #define __HYPERCALL_CLOBBER3	__HYPERCALL_CLOBBER4, __HYPERCALL_ARG4REG
 #define __HYPERCALL_CLOBBER2	__HYPERCALL_CLOBBER3, __HYPERCALL_ARG3REG
 #define __HYPERCALL_CLOBBER1	__HYPERCALL_CLOBBER2, __HYPERCALL_ARG2REG
 #define __HYPERCALL_CLOBBER0	__HYPERCALL_CLOBBER1, __HYPERCALL_ARG1REG
 #define _hypercall0(type, name)						\
 ({									\
 	__HYPERCALL_DECLS;						\
 	__HYPERCALL_0ARG();						\
 	asm volatile (__HYPERCALL					\
 		      : __HYPERCALL_0PARAM				\
 		      : __HYPERCALL_ENTRY(name)				\
 		      : __HYPERCALL_CLOBBER0);				\
 	(type)__res;							\
 })
 #define _hypercall1(type, name, a1)					\
 ({									\
 	__HYPERCALL_DECLS;						\
 	__HYPERCALL_1ARG(a1);						\
 	asm volatile (__HYPERCALL					\
 		      : __HYPERCALL_1PARAM				\
 		      : __HYPERCALL_ENTRY(name)				\
 		      : __HYPERCALL_CLOBBER1);				\
 	(type)__res;							\
 })
 #define _hypercall2(type, name, a1, a2)					\
 ({									\
 	__HYPERCALL_DECLS;						\
 	__HYPERCALL_2ARG(a1, a2);					\
 	asm volatile (__HYPERCALL					\
 		      : __HYPERCALL_2PARAM				\
 		      : __HYPERCALL_ENTRY(name)				\
 		      : __HYPERCALL_CLOBBER2);				\
 	(type)__res;							\
 })
 #define _hypercall3(type, name, a1, a2, a3)				\
 ({									\
 	__HYPERCALL_DECLS;						\
 	__HYPERCALL_3ARG(a1, a2, a3);					\
 	asm volatile (__HYPERCALL					\
 		      : __HYPERCALL_3PARAM				\
 		      : __HYPERCALL_ENTRY(name)				\
 		      : __HYPERCALL_CLOBBER3);				\
 	(type)__res;							\
 })
 #define _hypercall4(type, name, a1, a2, a3, a4)				\
 ({									\
 	__HYPERCALL_DECLS;						\
 	__HYPERCALL_4ARG(a1, a2, a3, a4);				\
 	asm volatile (__HYPERCALL					\
 		      : __HYPERCALL_4PARAM				\
 		      : __HYPERCALL_ENTRY(name)				\
 		      : __HYPERCALL_CLOBBER4);				\
 	(type)__res;							\
 })
 #define _hypercall5(type, name, a1, a2, a3, a4, a5)			\
 ({									\
 	__HYPERCALL_DECLS;						\
 	__HYPERCALL_5ARG(a1, a2, a3, a4, a5);				\
 	asm volatile (__HYPERCALL					\
 		      : __HYPERCALL_5PARAM				\
 		      : __HYPERCALL_ENTRY(name)				\
 		      : __HYPERCALL_CLOBBER5);				\
 	(type)__res;							\
 })
 static inline int
 HYPERVISOR_set_trap_table(struct trap_info *table)
 {
 	return _hypercall1(int, set_trap_table, table);
 }
 static inline int
 HYPERVISOR_mmu_update(struct mmu_update *req, int count,
 		      int *success_count, domid_t domid)
 {
 	return _hypercall4(int, mmu_update, req, count, success_count, domid);
 }
 static inline int
 HYPERVISOR_mmuext_op(struct mmuext_op *op, int count,
 		     int *success_count, domid_t domid)
 {
 	return _hypercall4(int, mmuext_op, op, count, success_count, domid);
 }
 static inline int
 HYPERVISOR_set_gdt(unsigned long *frame_list, int entries)
 {
 	return _hypercall2(int, set_gdt, frame_list, entries);
 }
 static inline int
 HYPERVISOR_stack_switch(unsigned long ss, unsigned long esp)
 {
 	return _hypercall2(int, stack_switch, ss, esp);
 }
 #ifdef CONFIG_X86_32
 static inline int
 HYPERVISOR_set_callbacks(unsigned long event_selector,
 			 unsigned long event_address,
 			 unsigned long failsafe_selector,
 			 unsigned long failsafe_address)
 {
 	return _hypercall4(int, set_callbacks,
 			   event_selector, event_address,
 			   failsafe_selector, failsafe_address);
 }
 #else  /* CONFIG_X86_64 */
 static inline int
 HYPERVISOR_set_callbacks(unsigned long event_address,
 			unsigned long failsafe_address,
 			unsigned long syscall_address)
 {
 	return _hypercall3(int, set_callbacks,
 			   event_address, failsafe_address,
 			   syscall_address);
 }
 #endif  /* CONFIG_X86_{32,64} */
 static inline int
 HYPERVISOR_callback_op(int cmd, void *arg)
 {
 	return _hypercall2(int, callback_op, cmd, arg);
 }
 static inline int
 HYPERVISOR_fpu_taskswitch(int set)
 {
 	return _hypercall1(int, fpu_taskswitch, set);
 }
 static inline int
 HYPERVISOR_sched_op(int cmd, void *arg)
 {
 	return _hypercall2(int, sched_op_new, cmd, arg);
 }
 static inline long
 HYPERVISOR_set_timer_op(u64 timeout)
 {
 	unsigned long timeout_hi = (unsigned long)(timeout>>32);
 	unsigned long timeout_lo = (unsigned long)timeout;
 	return _hypercall2(long, set_timer_op, timeout_lo, timeout_hi);
 }
 static inline int
 HYPERVISOR_set_debugreg(int reg, unsigned long value)
 {
 	return _hypercall2(int, set_debugreg, reg, value);
 }
 static inline unsigned long
 HYPERVISOR_get_debugreg(int reg)
 {
 	return _hypercall1(unsigned long, get_debugreg, reg);
 }
 static inline int
 HYPERVISOR_update_descriptor(u64 ma, u64 desc)
 {
 	return _hypercall4(int, update_descriptor, ma, ma>>32, desc, desc>>32);
 }
 static inline int
 HYPERVISOR_memory_op(unsigned int cmd, void *arg)
 {
 	return _hypercall2(int, memory_op, cmd, arg);
 }
 static inline int
 HYPERVISOR_multicall(void *call_list, int nr_calls)
 {
 	return _hypercall2(int, multicall, call_list, nr_calls);
 }
 static inline int
 HYPERVISOR_update_va_mapping(unsigned long va, pte_t new_val,
 			     unsigned long flags)
 {
 	if (sizeof(new_val) == sizeof(long))
 		return _hypercall3(int, update_va_mapping, va,
 				   new_val.pte, flags);
 	else
 		return _hypercall4(int, update_va_mapping, va,
 				   new_val.pte, new_val.pte >> 32, flags);
 }
 static inline int
 HYPERVISOR_event_channel_op(int cmd, void *arg)
 {
 	int rc = _hypercall2(int, event_channel_op, cmd, arg);
 	if (unlikely(rc == -ENOSYS)) {
 		struct evtchn_op op;
 		op.cmd = cmd;
 		memcpy(&op.u, arg, sizeof(op.u));
 		rc = _hypercall1(int, event_channel_op_compat, &op);
 		memcpy(arg, &op.u, sizeof(op.u));
 	}
 	return rc;
 }
 static inline int
 HYPERVISOR_xen_version(int cmd, void *arg)
 {
 	return _hypercall2(int, xen_version, cmd, arg);
 }
 static inline int
 HYPERVISOR_console_io(int cmd, int count, char *str)
 {
 	return _hypercall3(int, console_io, cmd, count, str);
 }
 static inline int
 HYPERVISOR_physdev_op(int cmd, void *arg)
 {
 	int rc = _hypercall2(int, physdev_op, cmd, arg);
 	if (unlikely(rc == -ENOSYS)) {
 		struct physdev_op op;
 		op.cmd = cmd;
 		memcpy(&op.u, arg, sizeof(op.u));
 		rc = _hypercall1(int, physdev_op_compat, &op);
 		memcpy(arg, &op.u, sizeof(op.u));
 	}
 	return rc;
 }
 static inline int
 HYPERVISOR_grant_table_op(unsigned int cmd, void *uop, unsigned int count)
 {
 	return _hypercall3(int, grant_table_op, cmd, uop, count);
 }
 static inline int
 HYPERVISOR_update_va_mapping_otherdomain(unsigned long va, pte_t new_val,
 					 unsigned long flags, domid_t domid)
 {
 	if (sizeof(new_val) == sizeof(long))
 		return _hypercall4(int, update_va_mapping_otherdomain, va,
 				   new_val.pte, flags, domid);
 	else
 		return _hypercall5(int, update_va_mapping_otherdomain, va,
 				   new_val.pte, new_val.pte >> 32,
 				   flags, domid);
 }
 static inline int
 HYPERVISOR_vm_assist(unsigned int cmd, unsigned int type)
 {
 	return _hypercall2(int, vm_assist, cmd, type);
 }
 static inline int
 HYPERVISOR_vcpu_op(int cmd, int vcpuid, void *extra_args)
 {
 	return _hypercall3(int, vcpu_op, cmd, vcpuid, extra_args);
 }
 #ifdef CONFIG_X86_64
 static inline int
 HYPERVISOR_set_segment_base(int reg, unsigned long value)
 {
 	return _hypercall2(int, set_segment_base, reg, value);
 }
 #endif
 static inline int
 HYPERVISOR_suspend(unsigned long srec)
 {
 	return _hypercall3(int, sched_op, SCHEDOP_shutdown,
 			   SHUTDOWN_suspend, srec);
 }
 static inline int
 HYPERVISOR_nmi_op(unsigned long op, unsigned long arg)
 {
 	return _hypercall2(int, nmi_op, op, arg);
 }
 static inline void
 MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set)
 {
 	mcl->op = __HYPERVISOR_fpu_taskswitch;
 	mcl->args[0] = set;
 }
 static inline void
 MULTI_update_va_mapping(struct multicall_entry *mcl, unsigned long va,
 			pte_t new_val, unsigned long flags)
 {
 	mcl->op = __HYPERVISOR_update_va_mapping;
 	mcl->args[0] = va;
 	if (sizeof(new_val) == sizeof(long)) {
 		mcl->args[1] = new_val.pte;
 		mcl->args[2] = flags;
 	} else {
 		mcl->args[1] = new_val.pte;
 		mcl->args[2] = new_val.pte >> 32;
 		mcl->args[3] = flags;
 	}
 }
 static inline void
 MULTI_grant_table_op(struct multicall_entry *mcl, unsigned int cmd,
 		     void *uop, unsigned int count)
 {
 	mcl->op = __HYPERVISOR_grant_table_op;
 	mcl->args[0] = cmd;
 	mcl->args[1] = (unsigned long)uop;
 	mcl->args[2] = count;
 }
 static inline void
 MULTI_update_va_mapping_otherdomain(struct multicall_entry *mcl, unsigned long va,
 				    pte_t new_val, unsigned long flags,
 				    domid_t domid)
 {
 	mcl->op = __HYPERVISOR_update_va_mapping_otherdomain;
 	mcl->args[0] = va;
 	if (sizeof(new_val) == sizeof(long)) {
 		mcl->args[1] = new_val.pte;
 		mcl->args[2] = flags;
 		mcl->args[3] = domid;
 	} else {
 		mcl->args[1] = new_val.pte;
 		mcl->args[2] = new_val.pte >> 32;
 		mcl->args[3] = flags;
 		mcl->args[4] = domid;
 	}
 }
 static inline void
 MULTI_update_descriptor(struct multicall_entry *mcl, u64 maddr,
 			struct desc_struct desc)
 {
 	mcl->op = __HYPERVISOR_update_descriptor;
 	if (sizeof(maddr) == sizeof(long)) {
 		mcl->args[0] = maddr;
 		mcl->args[1] = *(unsigned long *)&desc;
 	} else {
 		mcl->args[0] = maddr;
 		mcl->args[1] = maddr >> 32;
 		mcl->args[2] = desc.a;
 		mcl->args[3] = desc.b;
 	}
 }
 static inline void
 MULTI_memory_op(struct multicall_entry *mcl, unsigned int cmd, void *arg)
 {
 	mcl->op = __HYPERVISOR_memory_op;
 	mcl->args[0] = cmd;
 	mcl->args[1] = (unsigned long)arg;
 }
 static inline void
 MULTI_mmu_update(struct multicall_entry *mcl, struct mmu_update *req,
 		 int count, int *success_count, domid_t domid)
 {
 	mcl->op = __HYPERVISOR_mmu_update;
 	mcl->args[0] = (unsigned long)req;
 	mcl->args[1] = count;
 	mcl->args[2] = (unsigned long)success_count;
 	mcl->args[3] = domid;
 }
 static inline void
 MULTI_mmuext_op(struct multicall_entry *mcl, struct mmuext_op *op, int count,
 		int *success_count, domid_t domid)
 {
 	mcl->op = __HYPERVISOR_mmuext_op;
 	mcl->args[0] = (unsigned long)op;
 	mcl->args[1] = count;
 	mcl->args[2] = (unsigned long)success_count;
 	mcl->args[3] = domid;
 }
 static inline void
 MULTI_set_gdt(struct multicall_entry *mcl, unsigned long *frames, int entries)
 {
 	mcl->op = __HYPERVISOR_set_gdt;
 	mcl->args[0] = (unsigned long)frames;
 	mcl->args[1] = entries;
 }
 static inline void
 MULTI_stack_switch(struct multicall_entry *mcl,
 		   unsigned long ss, unsigned long esp)
 {
 	mcl->op = __HYPERVISOR_stack_switch;
 	mcl->args[0] = ss;
 	mcl->args[1] = esp;
 }
 #endif /* _ASM_X86_XEN_HYPERCALL_H */

arch/x86/include/asm/xen/hypervisor.h

Diff comments View file @ ecbf29c

 /******************************************************************************
  * hypervisor.h
  *
  * Linux-specific hypervisor handling.
  *
  * Copyright (c) 2002-2004, K A Fraser
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License version 2
  * as published by the Free Software Foundation; or, when distributed
  * separately from the Linux kernel or incorporated into other
  * software packages, subject to the following license:
  *
  * Permission is hereby granted, free of charge, to any person obtaining a copy
  * of this source file (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.
  */
 #ifndef _ASM_X86_XEN_HYPERVISOR_H
 #define _ASM_X86_XEN_HYPERVISOR_H
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <xen/interface/xen.h>
-#include <xen/interface/version.h>
-#include <asm/ptrace.h>
-#include <asm/page.h>
-#include <asm/desc.h>
-#if defined(__i386__)
-#  ifdef CONFIG_X86_PAE
-#   include <asm-generic/pgtable-nopud.h>
-#  else
-#   include <asm-generic/pgtable-nopmd.h>
-#  endif
-#endif
-#include <asm/xen/hypercall.h>
 /* arch/i386/kernel/setup.c */
 extern struct shared_info *HYPERVISOR_shared_info;
 extern struct start_info *xen_start_info;
-/* arch/i386/mach-xen/evtchn.c */
-/* Force a proper event-channel callback from Xen. */
-extern void force_evtchn_callback(void);
-/* Turn jiffies into Xen system time. */
-u64 jiffies_to_st(unsigned long jiffies);
-#define MULTI_UVMFLAGS_INDEX 3
-#define MULTI_UVMDOMID_INDEX 4
 enum xen_domain_type {
 	XEN_NATIVE,
 	XEN_PV_DOMAIN,
 	XEN_HVM_DOMAIN,
 };
 extern enum xen_domain_type xen_domain_type;
+#ifdef CONFIG_XEN
 #define xen_domain()		(xen_domain_type != XEN_NATIVE)
-#define xen_pv_domain()		(xen_domain_type == XEN_PV_DOMAIN)
+#else
+#define xen_domain()		(0)
+#endif
+#define xen_pv_domain()		(xen_domain() && xen_domain_type == XEN_PV_DOMAIN)

arch/x86/include/asm/xen/page.h

Diff comments View file @ ecbf29c

 #ifndef _ASM_X86_XEN_PAGE_H
 #define _ASM_X86_XEN_PAGE_H
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/spinlock.h>
 #include <linux/pfn.h>
 #include <asm/uaccess.h>
+#include <asm/page.h>
 #include <asm/pgtable.h>
+#include <xen/interface/xen.h>
 #include <xen/features.h>
 /* Xen machine address */
 typedef struct xmaddr {
 	phys_addr_t maddr;
 } xmaddr_t;
 /* Xen pseudo-physical address */
 typedef struct xpaddr {
 	phys_addr_t paddr;
 } xpaddr_t;
 #define XMADDR(x)	((xmaddr_t) { .maddr = (x) })
 #define XPADDR(x)	((xpaddr_t) { .paddr = (x) })
 /**** MACHINE <-> PHYSICAL CONVERSION MACROS ****/
 #define INVALID_P2M_ENTRY	(~0UL)
 #define FOREIGN_FRAME_BIT	(1UL<<31)
 #define FOREIGN_FRAME(m)	((m) | FOREIGN_FRAME_BIT)
 /* Maximum amount of memory we can handle in a domain in pages */
 #define MAX_DOMAIN_PAGES						\
     ((unsigned long)((u64)CONFIG_XEN_MAX_DOMAIN_MEMORY * 1024 * 1024 * 1024 / PAGE_SIZE))
 extern unsigned long get_phys_to_machine(unsigned long pfn);
 extern void set_phys_to_machine(unsigned long pfn, unsigned long mfn);
 static inline unsigned long pfn_to_mfn(unsigned long pfn)
 {
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return pfn;
 	return get_phys_to_machine(pfn) & ~FOREIGN_FRAME_BIT;
 }
 static inline int phys_to_machine_mapping_valid(unsigned long pfn)
 {
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return 1;
 	return get_phys_to_machine(pfn) != INVALID_P2M_ENTRY;
 }
 static inline unsigned long mfn_to_pfn(unsigned long mfn)
 {
 	unsigned long pfn;
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return mfn;
 #if 0
 	if (unlikely((mfn >> machine_to_phys_order) != 0))
 		return max_mapnr;
 #endif
 	pfn = 0;
 	/*
 	 * The array access can fail (e.g., device space beyond end of RAM).
 	 * In such cases it doesn't matter what we return (we return garbage),
 	 * but we must handle the fault without crashing!
 	 */
 	__get_user(pfn, &machine_to_phys_mapping[mfn]);
 	return pfn;
 }
 static inline xmaddr_t phys_to_machine(xpaddr_t phys)
 {
 	unsigned offset = phys.paddr & ~PAGE_MASK;
 	return XMADDR(PFN_PHYS(pfn_to_mfn(PFN_DOWN(phys.paddr))) | offset);
 }
 static inline xpaddr_t machine_to_phys(xmaddr_t machine)
 {
 	unsigned offset = machine.maddr & ~PAGE_MASK;
 	return XPADDR(PFN_PHYS(mfn_to_pfn(PFN_DOWN(machine.maddr))) | offset);
 }
 /*
  * We detect special mappings in one of two ways:
  *  1. If the MFN is an I/O page then Xen will set the m2p entry
  *     to be outside our maximum possible pseudophys range.
  *  2. If the MFN belongs to a different domain then we will certainly
  *     not have MFN in our p2m table. Conversely, if the page is ours,
  *     then we'll have p2m(m2p(MFN))==MFN.
  * If we detect a special mapping then it doesn't have a 'struct page'.
  * We force !pfn_valid() by returning an out-of-range pointer.
  *
  * NB. These checks require that, for any MFN that is not in our reservation,
  * there is no PFN such that p2m(PFN) == MFN. Otherwise we can get confused if
  * we are foreign-mapping the MFN, and the other domain as m2p(MFN) == PFN.
  * Yikes! Various places must poke in INVALID_P2M_ENTRY for safety.
  *
  * NB2. When deliberately mapping foreign pages into the p2m table, you *must*
  *      use FOREIGN_FRAME(). This will cause pte_pfn() to choke on it, as we
  *      require. In all the cases we care about, the FOREIGN_FRAME bit is
  *      masked (e.g., pfn_to_mfn()) so behaviour there is correct.
  */
 static inline unsigned long mfn_to_local_pfn(unsigned long mfn)
 {
 	extern unsigned long max_mapnr;
 	unsigned long pfn = mfn_to_pfn(mfn);
 	if ((pfn < max_mapnr)
 	    && !xen_feature(XENFEAT_auto_translated_physmap)
 	    && (get_phys_to_machine(pfn) != mfn))
 		return max_mapnr; /* force !pfn_valid() */
 	/* XXX fixme; not true with sparsemem */
 	return pfn;
 }
 /* VIRT <-> MACHINE conversion */
 #define virt_to_machine(v)	(phys_to_machine(XPADDR(__pa(v))))
 #define virt_to_mfn(v)		(pfn_to_mfn(PFN_DOWN(__pa(v))))
 #define mfn_to_virt(m)		(__va(mfn_to_pfn(m) << PAGE_SHIFT))
 static inline unsigned long pte_mfn(pte_t pte)
 {
 	return (pte.pte & PTE_PFN_MASK) >> PAGE_SHIFT;
 }
 static inline pte_t mfn_pte(unsigned long page_nr, pgprot_t pgprot)
 {
 	pte_t pte;
 	pte.pte = ((phys_addr_t)page_nr << PAGE_SHIFT) |
 		(pgprot_val(pgprot) & __supported_pte_mask);
 	return pte;
 }
 static inline pteval_t pte_val_ma(pte_t pte)
 {
 	return pte.pte;
 }
 static inline pte_t __pte_ma(pteval_t x)
 {
 	return (pte_t) { .pte = x };
 }
 #define pmd_val_ma(v) ((v).pmd)
 #ifdef __PAGETABLE_PUD_FOLDED
 #define pud_val_ma(v) ((v).pgd.pgd)
 #else
 #define pud_val_ma(v) ((v).pud)
 #endif
 #define __pmd_ma(x)	((pmd_t) { (x) } )
 #define pgd_val_ma(x)	((x).pgd)
 xmaddr_t arbitrary_virt_to_machine(void *address);
 void make_lowmem_page_readonly(void *vaddr);
 void make_lowmem_page_readwrite(void *vaddr);
 #endif /* _ASM_X86_XEN_PAGE_H */

arch/x86/xen/enlighten.c

Diff comments View file @ ecbf29c

 /*
  * Core of Xen paravirt_ops implementation.
  *
  * This file contains the xen_paravirt_ops structure itself, and the
  * implementations for:
  * - privileged instructions
  * - interrupt flags
  * - segment operations
  * - booting and setup
  *
  * Jeremy Fitzhardinge <jeremy@xensource.com>, XenSource Inc, 2007
  */
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/smp.h>
 #include <linux/preempt.h>
 #include <linux/hardirq.h>
 #include <linux/percpu.h>
 #include <linux/delay.h>
 #include <linux/start_kernel.h>
 #include <linux/sched.h>
 #include <linux/bootmem.h>
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/page-flags.h>
 #include <linux/highmem.h>
 #include <linux/console.h>
 #include <xen/interface/xen.h>
+#include <xen/interface/version.h>
 #include <xen/interface/physdev.h>
 #include <xen/interface/vcpu.h>
 #include <xen/features.h>
 #include <xen/page.h>
 #include <xen/hvc-console.h>
 #include <asm/paravirt.h>
 #include <asm/apic.h>
 #include <asm/page.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/hypervisor.h>
 #include <asm/fixmap.h>
 #include <asm/processor.h>
 #include <asm/msr-index.h>
 #include <asm/setup.h>
 #include <asm/desc.h>
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/reboot.h>
 #include "xen-ops.h"
 #include "mmu.h"
 #include "multicalls.h"
 EXPORT_SYMBOL_GPL(hypercall_page);
 DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
 DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info);
 enum xen_domain_type xen_domain_type = XEN_NATIVE;
 EXPORT_SYMBOL_GPL(xen_domain_type);
 /*
  * Identity map, in addition to plain kernel map.  This needs to be
  * large enough to allocate page table pages to allocate the rest.
  * Each page can map 2MB.
  */
 static pte_t level1_ident_pgt[PTRS_PER_PTE * 4] __page_aligned_bss;
 #ifdef CONFIG_X86_64
 /* l3 pud for userspace vsyscall mapping */
 static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss;
 #endif /* CONFIG_X86_64 */
 /*
  * Note about cr3 (pagetable base) values:
  *
  * xen_cr3 contains the current logical cr3 value; it contains the
  * last set cr3.  This may not be the current effective cr3, because
  * its update may be being lazily deferred.  However, a vcpu looking
  * at its own cr3 can use this value knowing that it everything will
  * be self-consistent.
  *
  * xen_current_cr3 contains the actual vcpu cr3; it is set once the
  * hypercall to set the vcpu cr3 is complete (so it may be a little
  * out of date, but it will never be set early).  If one vcpu is
  * looking at another vcpu's cr3 value, it should use this variable.
  */
 DEFINE_PER_CPU(unsigned long, xen_cr3);	 /* cr3 stored as physaddr */
 DEFINE_PER_CPU(unsigned long, xen_current_cr3);	 /* actual vcpu cr3 */
 struct start_info *xen_start_info;
 EXPORT_SYMBOL_GPL(xen_start_info);
 struct shared_info xen_dummy_shared_info;
 /*
  * Point at some empty memory to start with. We map the real shared_info
  * page as soon as fixmap is up and running.
  */
 struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info;
 /*
  * Flag to determine whether vcpu info placement is available on all
  * VCPUs.  We assume it is to start with, and then set it to zero on
  * the first failure.  This is because it can succeed on some VCPUs
  * and not others, since it can involve hypervisor memory allocation,
  * or because the guest failed to guarantee all the appropriate
  * constraints on all VCPUs (ie buffer can't cross a page boundary).
  *
  * Note that any particular CPU may be using a placed vcpu structure,
  * but we can only optimise if the all are.
  *
  * 0: not available, 1: available
  */
 static int have_vcpu_info_placement =
 #ifdef CONFIG_X86_32
 	1
 #else
 	0
 #endif
 	;
 static void xen_vcpu_setup(int cpu)
 {
 	struct vcpu_register_vcpu_info info;
 	int err;
 	struct vcpu_info *vcpup;
 	BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info);
 	per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
 	if (!have_vcpu_info_placement)
 		return;		/* already tested, not available */
 	vcpup = &per_cpu(xen_vcpu_info, cpu);
 	info.mfn = virt_to_mfn(vcpup);
 	info.offset = offset_in_page(vcpup);
 	printk(KERN_DEBUG "trying to map vcpu_info %d at %p, mfn %llx, offset %d\n",
 	       cpu, vcpup, info.mfn, info.offset);
 	/* Check to see if the hypervisor will put the vcpu_info
 	   structure where we want it, which allows direct access via
 	   a percpu-variable. */
 	err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, cpu, &info);
 	if (err) {
 		printk(KERN_DEBUG "register_vcpu_info failed: err=%d\n", err);
 		have_vcpu_info_placement = 0;
 	} else {
 		/* This cpu is using the registered vcpu info, even if
 		   later ones fail to. */
 		per_cpu(xen_vcpu, cpu) = vcpup;
 		printk(KERN_DEBUG "cpu %d using vcpu_info at %p\n",
 		       cpu, vcpup);
 	}
 }
 /*
  * On restore, set the vcpu placement up again.
  * If it fails, then we're in a bad state, since
  * we can't back out from using it...
  */
 void xen_vcpu_restore(void)
 {
 	if (have_vcpu_info_placement) {
 		int cpu;
 		for_each_online_cpu(cpu) {
 			bool other_cpu = (cpu != smp_processor_id());
 			if (other_cpu &&
 			    HYPERVISOR_vcpu_op(VCPUOP_down, cpu, NULL))
 				BUG();
 			xen_vcpu_setup(cpu);
 			if (other_cpu &&
 			    HYPERVISOR_vcpu_op(VCPUOP_up, cpu, NULL))
 				BUG();
 		}
 		BUG_ON(!have_vcpu_info_placement);
 	}
 }
 static void __init xen_banner(void)
 {
 	unsigned version = HYPERVISOR_xen_version(XENVER_version, NULL);
 	struct xen_extraversion extra;
 	HYPERVISOR_xen_version(XENVER_extraversion, &extra);
 	printk(KERN_INFO "Booting paravirtualized kernel on %s\n",
 	       pv_info.name);
 	printk(KERN_INFO "Xen version: %d.%d%s%s\n",
 	       version >> 16, version & 0xffff, extra.extraversion,
 	       xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : "");
 }
 static void xen_cpuid(unsigned int *ax, unsigned int *bx,
 		      unsigned int *cx, unsigned int *dx)
 {
 	unsigned maskedx = ~0;
 	/*
 	 * Mask out inconvenient features, to try and disable as many
 	 * unsupported kernel subsystems as possible.
 	 */
 	if (*ax == 1)
 		maskedx = ~((1 << X86_FEATURE_APIC) |  /* disable APIC */
 			    (1 << X86_FEATURE_ACPI) |  /* disable ACPI */
 			    (1 << X86_FEATURE_MCE)  |  /* disable MCE */
 			    (1 << X86_FEATURE_MCA)  |  /* disable MCA */
 			    (1 << X86_FEATURE_ACC));   /* thermal monitoring */
 	asm(XEN_EMULATE_PREFIX "cpuid"
 		: "=a" (*ax),
 		  "=b" (*bx),
 		  "=c" (*cx),
 		  "=d" (*dx)
 		: "0" (*ax), "2" (*cx));
 	*dx &= maskedx;
 }
 static void xen_set_debugreg(int reg, unsigned long val)
 {
 	HYPERVISOR_set_debugreg(reg, val);
 }
 static unsigned long xen_get_debugreg(int reg)
 {
 	return HYPERVISOR_get_debugreg(reg);
 }
 static void xen_leave_lazy(void)
 {
 	paravirt_leave_lazy(paravirt_get_lazy_mode());
 	xen_mc_flush();
 }
 static unsigned long xen_store_tr(void)
 {
 	return 0;
 }
 /*
  * Set the page permissions for a particular virtual address.  If the
  * address is a vmalloc mapping (or other non-linear mapping), then
  * find the linear mapping of the page and also set its protections to
  * match.
  */
 static void set_aliased_prot(void *v, pgprot_t prot)
 {
 	int level;
 	pte_t *ptep;
 	pte_t pte;
 	unsigned long pfn;
 	struct page *page;
 	ptep = lookup_address((unsigned long)v, &level);
 	BUG_ON(ptep == NULL);
 	pfn = pte_pfn(*ptep);
 	page = pfn_to_page(pfn);
 	pte = pfn_pte(pfn, prot);
 	if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0))
 		BUG();
 	if (!PageHighMem(page)) {
 		void *av = __va(PFN_PHYS(pfn));
 		if (av != v)
 			if (HYPERVISOR_update_va_mapping((unsigned long)av, pte, 0))
 				BUG();
 	} else
 		kmap_flush_unused();
 }
 static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries)
 {
 	const unsigned entries_per_page = PAGE_SIZE / LDT_ENTRY_SIZE;
 	int i;
 	for(i = 0; i < entries; i += entries_per_page)
 		set_aliased_prot(ldt + i, PAGE_KERNEL_RO);
 }
 static void xen_free_ldt(struct desc_struct *ldt, unsigned entries)
 {
 	const unsigned entries_per_page = PAGE_SIZE / LDT_ENTRY_SIZE;
 	int i;
 	for(i = 0; i < entries; i += entries_per_page)
 		set_aliased_prot(ldt + i, PAGE_KERNEL);
 }
 static void xen_set_ldt(const void *addr, unsigned entries)
 {
 	struct mmuext_op *op;
 	struct multicall_space mcs = xen_mc_entry(sizeof(*op));
 	op = mcs.args;
 	op->cmd = MMUEXT_SET_LDT;
 	op->arg1.linear_addr = (unsigned long)addr;
 	op->arg2.nr_ents = entries;
 	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
 	xen_mc_issue(PARAVIRT_LAZY_CPU);
 }
 static void xen_load_gdt(const struct desc_ptr *dtr)
 {
 	unsigned long *frames;
 	unsigned long va = dtr->address;
 	unsigned int size = dtr->size + 1;
 	unsigned pages = (size + PAGE_SIZE - 1) / PAGE_SIZE;
 	int f;
 	struct multicall_space mcs;
 	/* A GDT can be up to 64k in size, which corresponds to 8192
 	   8-byte entries, or 16 4k pages.. */
 	BUG_ON(size > 65536);
 	BUG_ON(va & ~PAGE_MASK);
 	mcs = xen_mc_entry(sizeof(*frames) * pages);
 	frames = mcs.args;
 	for (f = 0; va < dtr->address + size; va += PAGE_SIZE, f++) {
 		frames[f] = virt_to_mfn(va);
 		make_lowmem_page_readonly((void *)va);
 	}
 	MULTI_set_gdt(mcs.mc, frames, size / sizeof(struct desc_struct));
 	xen_mc_issue(PARAVIRT_LAZY_CPU);
 }
 static void load_TLS_descriptor(struct thread_struct *t,
 				unsigned int cpu, unsigned int i)
 {
 	struct desc_struct *gdt = get_cpu_gdt_table(cpu);
 	xmaddr_t maddr = virt_to_machine(&gdt[GDT_ENTRY_TLS_MIN+i]);
 	struct multicall_space mc = __xen_mc_entry(0);
 	MULTI_update_descriptor(mc.mc, maddr.maddr, t->tls_array[i]);
 }
 static void xen_load_tls(struct thread_struct *t, unsigned int cpu)
 {
 	/*
 	 * XXX sleazy hack: If we're being called in a lazy-cpu zone,
 	 * it means we're in a context switch, and %gs has just been
 	 * saved.  This means we can zero it out to prevent faults on
 	 * exit from the hypervisor if the next process has no %gs.
 	 * Either way, it has been saved, and the new value will get
 	 * loaded properly.  This will go away as soon as Xen has been
 	 * modified to not save/restore %gs for normal hypercalls.
 	 *
 	 * On x86_64, this hack is not used for %gs, because gs points
 	 * to KERNEL_GS_BASE (and uses it for PDA references), so we
 	 * must not zero %gs on x86_64
 	 *
 	 * For x86_64, we need to zero %fs, otherwise we may get an
 	 * exception between the new %fs descriptor being loaded and
 	 * %fs being effectively cleared at __switch_to().
 	 */
 	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU) {
 #ifdef CONFIG_X86_32
 		loadsegment(gs, 0);
 #else
 		loadsegment(fs, 0);
 #endif
 	}
 	xen_mc_batch();
 	load_TLS_descriptor(t, cpu, 0);
 	load_TLS_descriptor(t, cpu, 1);
 	load_TLS_descriptor(t, cpu, 2);
 	xen_mc_issue(PARAVIRT_LAZY_CPU);
 }
 #ifdef CONFIG_X86_64
 static void xen_load_gs_index(unsigned int idx)
 {
 	if (HYPERVISOR_set_segment_base(SEGBASE_GS_USER_SEL, idx))
 		BUG();
 }
 #endif
 static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum,
 				const void *ptr)
 {
 	xmaddr_t mach_lp = arbitrary_virt_to_machine(&dt[entrynum]);
 	u64 entry = *(u64 *)ptr;
 	preempt_disable();
 	xen_mc_flush();
 	if (HYPERVISOR_update_descriptor(mach_lp.maddr, entry))
 		BUG();
 	preempt_enable();
 }
 static int cvt_gate_to_trap(int vector, const gate_desc *val,
 			    struct trap_info *info)
 {
 	if (val->type != 0xf && val->type != 0xe)
 		return 0;
 	info->vector = vector;
 	info->address = gate_offset(*val);
 	info->cs = gate_segment(*val);
 	info->flags = val->dpl;
 	/* interrupt gates clear IF */
 	if (val->type == 0xe)
 		info->flags |= 4;
 	return 1;
 }
 /* Locations of each CPU's IDT */
 static DEFINE_PER_CPU(struct desc_ptr, idt_desc);
 /* Set an IDT entry.  If the entry is part of the current IDT, then
    also update Xen. */
 static void xen_write_idt_entry(gate_desc *dt, int entrynum, const gate_desc *g)
 {
 	unsigned long p = (unsigned long)&dt[entrynum];
 	unsigned long start, end;
 	preempt_disable();
 	start = __get_cpu_var(idt_desc).address;
 	end = start + __get_cpu_var(idt_desc).size + 1;
 	xen_mc_flush();
 	native_write_idt_entry(dt, entrynum, g);
 	if (p >= start && (p + 8) <= end) {
 		struct trap_info info[2];
 		info[1].address = 0;
 		if (cvt_gate_to_trap(entrynum, g, &info[0]))
 			if (HYPERVISOR_set_trap_table(info))
 				BUG();
 	}
 	preempt_enable();
 }
 static void xen_convert_trap_info(const struct desc_ptr *desc,
 				  struct trap_info *traps)
 {
 	unsigned in, out, count;
 	count = (desc->size+1) / sizeof(gate_desc);
 	BUG_ON(count > 256);
 	for (in = out = 0; in < count; in++) {
 		gate_desc *entry = (gate_desc*)(desc->address) + in;
 		if (cvt_gate_to_trap(in, entry, &traps[out]))
 			out++;
 	}
 	traps[out].address = 0;
 }
 void xen_copy_trap_info(struct trap_info *traps)
 {
 	const struct desc_ptr *desc = &__get_cpu_var(idt_desc);
 	xen_convert_trap_info(desc, traps);
 }
 /* Load a new IDT into Xen.  In principle this can be per-CPU, so we
    hold a spinlock to protect the static traps[] array (static because
    it avoids allocation, and saves stack space). */
 static void xen_load_idt(const struct desc_ptr *desc)
 {
 	static DEFINE_SPINLOCK(lock);
 	static struct trap_info traps[257];
 	spin_lock(&lock);
 	__get_cpu_var(idt_desc) = *desc;
 	xen_convert_trap_info(desc, traps);
 	xen_mc_flush();
 	if (HYPERVISOR_set_trap_table(traps))
 		BUG();
 	spin_unlock(&lock);
 }
 /* Write a GDT descriptor entry.  Ignore LDT descriptors, since
    they're handled differently. */
 static void xen_write_gdt_entry(struct desc_struct *dt, int entry,
 				const void *desc, int type)
 {
 	preempt_disable();
 	switch (type) {
 	case DESC_LDT:
 	case DESC_TSS:
 		/* ignore */
 		break;
 	default: {
 		xmaddr_t maddr = virt_to_machine(&dt[entry]);
 		xen_mc_flush();
 		if (HYPERVISOR_update_descriptor(maddr.maddr, *(u64 *)desc))
 			BUG();
 	}
 	}
 	preempt_enable();
 }
 static void xen_load_sp0(struct tss_struct *tss,
 			 struct thread_struct *thread)
 {
 	struct multicall_space mcs = xen_mc_entry(0);
 	MULTI_stack_switch(mcs.mc, __KERNEL_DS, thread->sp0);
 	xen_mc_issue(PARAVIRT_LAZY_CPU);
 }
 static void xen_set_iopl_mask(unsigned mask)
 {
 	struct physdev_set_iopl set_iopl;
 	/* Force the change at ring 0. */
 	set_iopl.iopl = (mask == 0) ? 1 : (mask >> 12) & 3;
 	HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl);
 }
 static void xen_io_delay(void)
 {
 }
 #ifdef CONFIG_X86_LOCAL_APIC
 static u32 xen_apic_read(u32 reg)
 {
 	return 0;
 }
 static void xen_apic_write(u32 reg, u32 val)
 {
 	/* Warn to see if there's any stray references */
 	WARN_ON(1);
 }
 static u64 xen_apic_icr_read(void)
 {
 	return 0;
 }
 static void xen_apic_icr_write(u32 low, u32 id)
 {
 	/* Warn to see if there's any stray references */
 	WARN_ON(1);
 }
 static void xen_apic_wait_icr_idle(void)
 {
         return;
 }
 static u32 xen_safe_apic_wait_icr_idle(void)
 {
         return 0;
 }
 static struct apic_ops xen_basic_apic_ops = {
 	.read = xen_apic_read,
 	.write = xen_apic_write,
 	.icr_read = xen_apic_icr_read,
 	.icr_write = xen_apic_icr_write,
 	.wait_icr_idle = xen_apic_wait_icr_idle,
 	.safe_wait_icr_idle = xen_safe_apic_wait_icr_idle,
 };
 #endif
 static void xen_flush_tlb(void)
 {
 	struct mmuext_op *op;
 	struct multicall_space mcs;
 	preempt_disable();
 	mcs = xen_mc_entry(sizeof(*op));
 	op = mcs.args;
 	op->cmd = MMUEXT_TLB_FLUSH_LOCAL;
 	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
 	xen_mc_issue(PARAVIRT_LAZY_MMU);
 	preempt_enable();
 }
 static void xen_flush_tlb_single(unsigned long addr)
 {
 	struct mmuext_op *op;
 	struct multicall_space mcs;
 	preempt_disable();
 	mcs = xen_mc_entry(sizeof(*op));
 	op = mcs.args;
 	op->cmd = MMUEXT_INVLPG_LOCAL;
 	op->arg1.linear_addr = addr & PAGE_MASK;
 	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
 	xen_mc_issue(PARAVIRT_LAZY_MMU);
 	preempt_enable();
 }
 static void xen_flush_tlb_others(const cpumask_t *cpus, struct mm_struct *mm,
 				 unsigned long va)
 {
 	struct {
 		struct mmuext_op op;
 		cpumask_t mask;
 	} *args;
 	cpumask_t cpumask = *cpus;
 	struct multicall_space mcs;
 	/*
 	 * A couple of (to be removed) sanity checks:
 	 *
 	 * - current CPU must not be in mask
 	 * - mask must exist :)
 	 */
 	BUG_ON(cpus_empty(cpumask));
 	BUG_ON(cpu_isset(smp_processor_id(), cpumask));
 	BUG_ON(!mm);
 	/* If a CPU which we ran on has gone down, OK. */
 	cpus_and(cpumask, cpumask, cpu_online_map);
 	if (cpus_empty(cpumask))
 		return;
 	mcs = xen_mc_entry(sizeof(*args));
 	args = mcs.args;
 	args->mask = cpumask;
 	args->op.arg2.vcpumask = &args->mask;
 	if (va == TLB_FLUSH_ALL) {
 		args->op.cmd = MMUEXT_TLB_FLUSH_MULTI;
 	} else {
 		args->op.cmd = MMUEXT_INVLPG_MULTI;
 		args->op.arg1.linear_addr = va;
 	}
 	MULTI_mmuext_op(mcs.mc, &args->op, 1, NULL, DOMID_SELF);
 	xen_mc_issue(PARAVIRT_LAZY_MMU);
 }
 static void xen_clts(void)
 {
 	struct multicall_space mcs;
 	mcs = xen_mc_entry(0);
 	MULTI_fpu_taskswitch(mcs.mc, 0);
 	xen_mc_issue(PARAVIRT_LAZY_CPU);
 }
 static void xen_write_cr0(unsigned long cr0)
 {
 	struct multicall_space mcs;
 	/* Only pay attention to cr0.TS; everything else is
 	   ignored. */
 	mcs = xen_mc_entry(0);
 	MULTI_fpu_taskswitch(mcs.mc, (cr0 & X86_CR0_TS) != 0);
 	xen_mc_issue(PARAVIRT_LAZY_CPU);
 }
 static void xen_write_cr2(unsigned long cr2)
 {
 	x86_read_percpu(xen_vcpu)->arch.cr2 = cr2;
 }
 static unsigned long xen_read_cr2(void)
 {
 	return x86_read_percpu(xen_vcpu)->arch.cr2;
 }
 static unsigned long xen_read_cr2_direct(void)
 {
 	return x86_read_percpu(xen_vcpu_info.arch.cr2);
 }
 static void xen_write_cr4(unsigned long cr4)
 {
 	cr4 &= ~X86_CR4_PGE;
 	cr4 &= ~X86_CR4_PSE;
 	native_write_cr4(cr4);
 }
 static unsigned long xen_read_cr3(void)
 {
 	return x86_read_percpu(xen_cr3);
 }
 static void set_current_cr3(void *v)
 {
 	x86_write_percpu(xen_current_cr3, (unsigned long)v);
 }
 static void __xen_write_cr3(bool kernel, unsigned long cr3)
 {
 	struct mmuext_op *op;
 	struct multicall_space mcs;
 	unsigned long mfn;
 	if (cr3)
 		mfn = pfn_to_mfn(PFN_DOWN(cr3));
 	else
 		mfn = 0;
 	WARN_ON(mfn == 0 && kernel);
 	mcs = __xen_mc_entry(sizeof(*op));
 	op = mcs.args;
 	op->cmd = kernel ? MMUEXT_NEW_BASEPTR : MMUEXT_NEW_USER_BASEPTR;
 	op->arg1.mfn = mfn;
 	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
 	if (kernel) {
 		x86_write_percpu(xen_cr3, cr3);
 		/* Update xen_current_cr3 once the batch has actually
 		   been submitted. */
 		xen_mc_callback(set_current_cr3, (void *)cr3);
 	}
 }
 static void xen_write_cr3(unsigned long cr3)
 {
 	BUG_ON(preemptible());
 	xen_mc_batch();  /* disables interrupts */
 	/* Update while interrupts are disabled, so its atomic with
 	   respect to ipis */
 	x86_write_percpu(xen_cr3, cr3);
 	__xen_write_cr3(true, cr3);
 #ifdef CONFIG_X86_64
 	{
 		pgd_t *user_pgd = xen_get_user_pgd(__va(cr3));
 		if (user_pgd)
 			__xen_write_cr3(false, __pa(user_pgd));
 		else
 			__xen_write_cr3(false, 0);
 	}
 #endif
 	xen_mc_issue(PARAVIRT_LAZY_CPU);  /* interrupts restored */
 }
 static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
 {
 	int ret;
 	ret = 0;
 	switch (msr) {
 #ifdef CONFIG_X86_64
 		unsigned which;
 		u64 base;
 	case MSR_FS_BASE:		which = SEGBASE_FS; goto set;
 	case MSR_KERNEL_GS_BASE:	which = SEGBASE_GS_USER; goto set;
 	case MSR_GS_BASE:		which = SEGBASE_GS_KERNEL; goto set;
 	set:
 		base = ((u64)high << 32) | low;
 		if (HYPERVISOR_set_segment_base(which, base) != 0)
 			ret = -EFAULT;
 		break;
 #endif
 	case MSR_STAR:
 	case MSR_CSTAR:
 	case MSR_LSTAR:
 	case MSR_SYSCALL_MASK:
 	case MSR_IA32_SYSENTER_CS:
 	case MSR_IA32_SYSENTER_ESP:
 	case MSR_IA32_SYSENTER_EIP:
 		/* Fast syscall setup is all done in hypercalls, so
 		   these are all ignored.  Stub them out here to stop
 		   Xen console noise. */
 		break;
 	default:
 		ret = native_write_msr_safe(msr, low, high);
 	}
 	return ret;
 }
 /* Early in boot, while setting up the initial pagetable, assume
    everything is pinned. */
 static __init void xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn)
 {
 #ifdef CONFIG_FLATMEM
 	BUG_ON(mem_map);	/* should only be used early */
 #endif
 	make_lowmem_page_readonly(__va(PFN_PHYS(pfn)));
 }
 /* Early release_pte assumes that all pts are pinned, since there's
    only init_mm and anything attached to that is pinned. */
 static void xen_release_pte_init(unsigned long pfn)
 {
 	make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
 }
 static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
 {
 	struct mmuext_op op;
 	op.cmd = cmd;
 	op.arg1.mfn = pfn_to_mfn(pfn);
 	if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF))
 		BUG();
 }
 /* This needs to make sure the new pte page is pinned iff its being
    attached to a pinned pagetable. */
 static void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn, unsigned level)
 {
 	struct page *page = pfn_to_page(pfn);
 	if (PagePinned(virt_to_page(mm->pgd))) {
 		SetPagePinned(page);
 		vm_unmap_aliases();
 		if (!PageHighMem(page)) {
 			make_lowmem_page_readonly(__va(PFN_PHYS((unsigned long)pfn)));
 			if (level == PT_PTE && USE_SPLIT_PTLOCKS)
 				pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
 		} else {
 			/* make sure there are no stray mappings of
 			   this page */
 			kmap_flush_unused();
 		}
 	}
 }
 static void xen_alloc_pte(struct mm_struct *mm, unsigned long pfn)
 {
 	xen_alloc_ptpage(mm, pfn, PT_PTE);
 }
 static void xen_alloc_pmd(struct mm_struct *mm, unsigned long pfn)
 {
 	xen_alloc_ptpage(mm, pfn, PT_PMD);
 }
 static int xen_pgd_alloc(struct mm_struct *mm)
 {
 	pgd_t *pgd = mm->pgd;
 	int ret = 0;
 	BUG_ON(PagePinned(virt_to_page(pgd)));
 #ifdef CONFIG_X86_64
 	{
 		struct page *page = virt_to_page(pgd);
 		pgd_t *user_pgd;
 		BUG_ON(page->private != 0);
 		ret = -ENOMEM;
 		user_pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
 		page->private = (unsigned long)user_pgd;
 		if (user_pgd != NULL) {
 			user_pgd[pgd_index(VSYSCALL_START)] =
 				__pgd(__pa(level3_user_vsyscall) | _PAGE_TABLE);
 			ret = 0;
 		}
 		BUG_ON(PagePinned(virt_to_page(xen_get_user_pgd(pgd))));
 	}
 #endif
 	return ret;
 }
 static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
 #ifdef CONFIG_X86_64
 	pgd_t *user_pgd = xen_get_user_pgd(pgd);
 	if (user_pgd)
 		free_page((unsigned long)user_pgd);
 #endif
 }
 /* This should never happen until we're OK to use struct page */
 static void xen_release_ptpage(unsigned long pfn, unsigned level)
 {
 	struct page *page = pfn_to_page(pfn);
 	if (PagePinned(page)) {
 		if (!PageHighMem(page)) {
 			if (level == PT_PTE && USE_SPLIT_PTLOCKS)
 				pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
 			make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
 		}
 		ClearPagePinned(page);
 	}
 }
 static void xen_release_pte(unsigned long pfn)
 {
 	xen_release_ptpage(pfn, PT_PTE);
 }
 static void xen_release_pmd(unsigned long pfn)
 {
 	xen_release_ptpage(pfn, PT_PMD);
 }
 #if PAGETABLE_LEVELS == 4
 static void xen_alloc_pud(struct mm_struct *mm, unsigned long pfn)
 {
 	xen_alloc_ptpage(mm, pfn, PT_PUD);
 }
 static void xen_release_pud(unsigned long pfn)
 {
 	xen_release_ptpage(pfn, PT_PUD);
 }
 #endif
 #ifdef CONFIG_HIGHPTE
 static void *xen_kmap_atomic_pte(struct page *page, enum km_type type)
 {
 	pgprot_t prot = PAGE_KERNEL;
 	if (PagePinned(page))
 		prot = PAGE_KERNEL_RO;
 	if (0 && PageHighMem(page))
 		printk("mapping highpte %lx type %d prot %s\n",
 		       page_to_pfn(page), type,
 		       (unsigned long)pgprot_val(prot) & _PAGE_RW ? "WRITE" : "READ");
 	return kmap_atomic_prot(page, type, prot);
 }
 #endif
 #ifdef CONFIG_X86_32
 static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
 {
 	/* If there's an existing pte, then don't allow _PAGE_RW to be set */
 	if (pte_val_ma(*ptep) & _PAGE_PRESENT)
 		pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) &
 			       pte_val_ma(pte));
 	return pte;
 }
 /* Init-time set_pte while constructing initial pagetables, which
    doesn't allow RO pagetable pages to be remapped RW */
 static __init void xen_set_pte_init(pte_t *ptep, pte_t pte)
 {
 	pte = mask_rw_pte(ptep, pte);
 	xen_set_pte(ptep, pte);
 }
 #endif
 static __init void xen_pagetable_setup_start(pgd_t *base)
 {
 }
 void xen_setup_shared_info(void)
 {
 	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
 		set_fixmap(FIX_PARAVIRT_BOOTMAP,
 			   xen_start_info->shared_info);
 		HYPERVISOR_shared_info =
 			(struct shared_info *)fix_to_virt(FIX_PARAVIRT_BOOTMAP);
 	} else
 		HYPERVISOR_shared_info =
 			(struct shared_info *)__va(xen_start_info->shared_info);
 #ifndef CONFIG_SMP
 	/* In UP this is as good a place as any to set up shared info */
 	xen_setup_vcpu_info_placement();
 #endif
 	xen_setup_mfn_list_list();
 }
 static __init void xen_pagetable_setup_done(pgd_t *base)
 {
 	xen_setup_shared_info();
 }
 static __init void xen_post_allocator_init(void)
 {
 	pv_mmu_ops.set_pte = xen_set_pte;
 	pv_mmu_ops.set_pmd = xen_set_pmd;
 	pv_mmu_ops.set_pud = xen_set_pud;
 #if PAGETABLE_LEVELS == 4
 	pv_mmu_ops.set_pgd = xen_set_pgd;
 #endif
 	/* This will work as long as patching hasn't happened yet
 	   (which it hasn't) */
 	pv_mmu_ops.alloc_pte = xen_alloc_pte;
 	pv_mmu_ops.alloc_pmd = xen_alloc_pmd;
 	pv_mmu_ops.release_pte = xen_release_pte;
 	pv_mmu_ops.release_pmd = xen_release_pmd;
 #if PAGETABLE_LEVELS == 4
 	pv_mmu_ops.alloc_pud = xen_alloc_pud;
 	pv_mmu_ops.release_pud = xen_release_pud;
 #endif
 #ifdef CONFIG_X86_64
 	SetPagePinned(virt_to_page(level3_user_vsyscall));
 #endif
 	xen_mark_init_mm_pinned();
 }
 /* This is called once we have the cpu_possible_map */
 void xen_setup_vcpu_info_placement(void)
 {
 	int cpu;
 	for_each_possible_cpu(cpu)
 		xen_vcpu_setup(cpu);
 	/* xen_vcpu_setup managed to place the vcpu_info within the
 	   percpu area for all cpus, so make use of it */
 	if (have_vcpu_info_placement) {
 		printk(KERN_INFO "Xen: using vcpu_info placement\n");
 		pv_irq_ops.save_fl = xen_save_fl_direct;
 		pv_irq_ops.restore_fl = xen_restore_fl_direct;
 		pv_irq_ops.irq_disable = xen_irq_disable_direct;
 		pv_irq_ops.irq_enable = xen_irq_enable_direct;
 		pv_mmu_ops.read_cr2 = xen_read_cr2_direct;
 	}
 }
 static unsigned xen_patch(u8 type, u16 clobbers, void *insnbuf,
 			  unsigned long addr, unsigned len)
 {
 	char *start, *end, *reloc;
 	unsigned ret;
 	start = end = reloc = NULL;
 #define SITE(op, x)							\
 	case PARAVIRT_PATCH(op.x):					\
 	if (have_vcpu_info_placement) {					\
 		start = (char *)xen_##x##_direct;			\
 		end = xen_##x##_direct_end;				\
 		reloc = xen_##x##_direct_reloc;				\
 	}								\
 	goto patch_site
 	switch (type) {
 		SITE(pv_irq_ops, irq_enable);
 		SITE(pv_irq_ops, irq_disable);
 		SITE(pv_irq_ops, save_fl);
 		SITE(pv_irq_ops, restore_fl);
 #undef SITE
 	patch_site:
 		if (start == NULL || (end-start) > len)
 			goto default_patch;
 		ret = paravirt_patch_insns(insnbuf, len, start, end);
 		/* Note: because reloc is assigned from something that
 		   appears to be an array, gcc assumes it's non-null,
 		   but doesn't know its relationship with start and
 		   end. */
 		if (reloc > start && reloc < end) {
 			int reloc_off = reloc - start;
 			long *relocp = (long *)(insnbuf + reloc_off);
 			long delta = start - (char *)addr;
 			*relocp += delta;
 		}
 		break;
 	default_patch:
 	default:
 		ret = paravirt_patch_default(type, clobbers, insnbuf,
 					     addr, len);
 		break;
 	}
 	return ret;
 }
 static void xen_set_fixmap(unsigned idx, unsigned long phys, pgprot_t prot)
 {
 	pte_t pte;
 	phys >>= PAGE_SHIFT;
 	switch (idx) {
 	case FIX_BTMAP_END ... FIX_BTMAP_BEGIN:
 #ifdef CONFIG_X86_F00F_BUG
 	case FIX_F00F_IDT:
 #endif
 #ifdef CONFIG_X86_32
 	case FIX_WP_TEST:
 	case FIX_VDSO:
 # ifdef CONFIG_HIGHMEM
 	case FIX_KMAP_BEGIN ... FIX_KMAP_END:
 # endif
 #else
 	case VSYSCALL_LAST_PAGE ... VSYSCALL_FIRST_PAGE:
 #endif
 #ifdef CONFIG_X86_LOCAL_APIC
 	case FIX_APIC_BASE:	/* maps dummy local APIC */
 #endif
 		pte = pfn_pte(phys, prot);
 		break;
 	default:
 		pte = mfn_pte(phys, prot);
 		break;
 	}
 	__native_set_fixmap(idx, pte);
 #ifdef CONFIG_X86_64
 	/* Replicate changes to map the vsyscall page into the user
 	   pagetable vsyscall mapping. */
 	if (idx >= VSYSCALL_LAST_PAGE && idx <= VSYSCALL_FIRST_PAGE) {
 		unsigned long vaddr = __fix_to_virt(idx);
 		set_pte_vaddr_pud(level3_user_vsyscall, vaddr, pte);
 	}
 #endif
 }
 static const struct pv_info xen_info __initdata = {
 	.paravirt_enabled = 1,
 	.shared_kernel_pmd = 0,
 	.name = "Xen",
 };
 static const struct pv_init_ops xen_init_ops __initdata = {
 	.patch = xen_patch,
 	.banner = xen_banner,
 	.memory_setup = xen_memory_setup,
 	.arch_setup = xen_arch_setup,
 	.post_allocator_init = xen_post_allocator_init,
 };
 static const struct pv_time_ops xen_time_ops __initdata = {
 	.time_init = xen_time_init,
 	.set_wallclock = xen_set_wallclock,
 	.get_wallclock = xen_get_wallclock,
 	.get_tsc_khz = xen_tsc_khz,
 	.sched_clock = xen_sched_clock,
 };
 static const struct pv_cpu_ops xen_cpu_ops __initdata = {
 	.cpuid = xen_cpuid,
 	.set_debugreg = xen_set_debugreg,
 	.get_debugreg = xen_get_debugreg,
 	.clts = xen_clts,
 	.read_cr0 = native_read_cr0,
 	.write_cr0 = xen_write_cr0,
 	.read_cr4 = native_read_cr4,
 	.read_cr4_safe = native_read_cr4_safe,
 	.write_cr4 = xen_write_cr4,
 	.wbinvd = native_wbinvd,
 	.read_msr = native_read_msr_safe,
 	.write_msr = xen_write_msr_safe,
 	.read_tsc = native_read_tsc,
 	.read_pmc = native_read_pmc,
 	.iret = xen_iret,
 	.irq_enable_sysexit = xen_sysexit,
 #ifdef CONFIG_X86_64
 	.usergs_sysret32 = xen_sysret32,
 	.usergs_sysret64 = xen_sysret64,
 #endif
 	.load_tr_desc = paravirt_nop,
 	.set_ldt = xen_set_ldt,
 	.load_gdt = xen_load_gdt,
 	.load_idt = xen_load_idt,
 	.load_tls = xen_load_tls,
 #ifdef CONFIG_X86_64
 	.load_gs_index = xen_load_gs_index,
 #endif
 	.alloc_ldt = xen_alloc_ldt,
 	.free_ldt = xen_free_ldt,
 	.store_gdt = native_store_gdt,
 	.store_idt = native_store_idt,
 	.store_tr = xen_store_tr,
 	.write_ldt_entry = xen_write_ldt_entry,
 	.write_gdt_entry = xen_write_gdt_entry,
 	.write_idt_entry = xen_write_idt_entry,
 	.load_sp0 = xen_load_sp0,
 	.set_iopl_mask = xen_set_iopl_mask,
 	.io_delay = xen_io_delay,
 	/* Xen takes care of %gs when switching to usermode for us */
 	.swapgs = paravirt_nop,
 	.lazy_mode = {
 		.enter = paravirt_enter_lazy_cpu,
 		.leave = xen_leave_lazy,
 	},
 };
 static const struct pv_apic_ops xen_apic_ops __initdata = {
 #ifdef CONFIG_X86_LOCAL_APIC
 	.setup_boot_clock = paravirt_nop,
 	.setup_secondary_clock = paravirt_nop,
 	.startup_ipi_hook = paravirt_nop,
 #endif
 };
 static const struct pv_mmu_ops xen_mmu_ops __initdata = {
 	.pagetable_setup_start = xen_pagetable_setup_start,
 	.pagetable_setup_done = xen_pagetable_setup_done,
 	.read_cr2 = xen_read_cr2,
 	.write_cr2 = xen_write_cr2,
 	.read_cr3 = xen_read_cr3,
 	.write_cr3 = xen_write_cr3,
 	.flush_tlb_user = xen_flush_tlb,
 	.flush_tlb_kernel = xen_flush_tlb,
 	.flush_tlb_single = xen_flush_tlb_single,
 	.flush_tlb_others = xen_flush_tlb_others,
 	.pte_update = paravirt_nop,
 	.pte_update_defer = paravirt_nop,
 	.pgd_alloc = xen_pgd_alloc,
 	.pgd_free = xen_pgd_free,
 	.alloc_pte = xen_alloc_pte_init,
 	.release_pte = xen_release_pte_init,
 	.alloc_pmd = xen_alloc_pte_init,
 	.alloc_pmd_clone = paravirt_nop,
 	.release_pmd = xen_release_pte_init,
 #ifdef CONFIG_HIGHPTE
 	.kmap_atomic_pte = xen_kmap_atomic_pte,
 #endif
 #ifdef CONFIG_X86_64
 	.set_pte = xen_set_pte,
 #else
 	.set_pte = xen_set_pte_init,
 #endif
 	.set_pte_at = xen_set_pte_at,
 	.set_pmd = xen_set_pmd_hyper,
 	.ptep_modify_prot_start = __ptep_modify_prot_start,
 	.ptep_modify_prot_commit = __ptep_modify_prot_commit,
 	.pte_val = xen_pte_val,
 	.pte_flags = native_pte_flags,
 	.pgd_val = xen_pgd_val,
 	.make_pte = xen_make_pte,
 	.make_pgd = xen_make_pgd,
 #ifdef CONFIG_X86_PAE
 	.set_pte_atomic = xen_set_pte_atomic,
 	.set_pte_present = xen_set_pte_at,
 	.pte_clear = xen_pte_clear,
 	.pmd_clear = xen_pmd_clear,
 #endif	/* CONFIG_X86_PAE */
 	.set_pud = xen_set_pud_hyper,
 	.make_pmd = xen_make_pmd,
 	.pmd_val = xen_pmd_val,
 #if PAGETABLE_LEVELS == 4
 	.pud_val = xen_pud_val,
 	.make_pud = xen_make_pud,
 	.set_pgd = xen_set_pgd_hyper,
 	.alloc_pud = xen_alloc_pte_init,
 	.release_pud = xen_release_pte_init,
 #endif	/* PAGETABLE_LEVELS == 4 */
 	.activate_mm = xen_activate_mm,
 	.dup_mmap = xen_dup_mmap,
 	.exit_mmap = xen_exit_mmap,
 	.lazy_mode = {
 		.enter = paravirt_enter_lazy_mmu,
 		.leave = xen_leave_lazy,
 	},
 	.set_fixmap = xen_set_fixmap,
 };
 static void xen_reboot(int reason)
 {
 	struct sched_shutdown r = { .reason = reason };
 #ifdef CONFIG_SMP
 	smp_send_stop();
 #endif
 	if (HYPERVISOR_sched_op(SCHEDOP_shutdown, &r))
 		BUG();
 }
 static void xen_restart(char *msg)
 {
 	xen_reboot(SHUTDOWN_reboot);
 }
 static void xen_emergency_restart(void)
 {
 	xen_reboot(SHUTDOWN_reboot);
 }
 static void xen_machine_halt(void)
 {
 	xen_reboot(SHUTDOWN_poweroff);
 }
 static void xen_crash_shutdown(struct pt_regs *regs)
 {
 	xen_reboot(SHUTDOWN_crash);
 }
 static const struct machine_ops __initdata xen_machine_ops = {
 	.restart = xen_restart,
 	.halt = xen_machine_halt,
 	.power_off = xen_machine_halt,
 	.shutdown = xen_machine_halt,
 	.crash_shutdown = xen_crash_shutdown,
 	.emergency_restart = xen_emergency_restart,
 };
 static void __init xen_reserve_top(void)
 {
 #ifdef CONFIG_X86_32
 	unsigned long top = HYPERVISOR_VIRT_START;
 	struct xen_platform_parameters pp;
 	if (HYPERVISOR_xen_version(XENVER_platform_parameters, &pp) == 0)
 		top = pp.virt_start;
 	reserve_top_address(-top);
 #endif	/* CONFIG_X86_32 */
 }
 /*
  * Like __va(), but returns address in the kernel mapping (which is
  * all we have until the physical memory mapping has been set up.
  */
 static void *__ka(phys_addr_t paddr)
 {
 #ifdef CONFIG_X86_64
 	return (void *)(paddr + __START_KERNEL_map);
 #else
 	return __va(paddr);
 #endif
 }
 /* Convert a machine address to physical address */
 static unsigned long m2p(phys_addr_t maddr)
 {
 	phys_addr_t paddr;
 	maddr &= PTE_PFN_MASK;
 	paddr = mfn_to_pfn(maddr >> PAGE_SHIFT) << PAGE_SHIFT;
 	return paddr;
 }
 /* Convert a machine address to kernel virtual */
 static void *m2v(phys_addr_t maddr)
 {
 	return __ka(m2p(maddr));
 }
 static void set_page_prot(void *addr, pgprot_t prot)
 {
 	unsigned long pfn = __pa(addr) >> PAGE_SHIFT;
 	pte_t pte = pfn_pte(pfn, prot);
 	if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, 0))
 		BUG();
 }
 static __init void xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
 {
 	unsigned pmdidx, pteidx;
 	unsigned ident_pte;
 	unsigned long pfn;
 	ident_pte = 0;
 	pfn = 0;
 	for (pmdidx = 0; pmdidx < PTRS_PER_PMD && pfn < max_pfn; pmdidx++) {
 		pte_t *pte_page;
 		/* Reuse or allocate a page of ptes */
 		if (pmd_present(pmd[pmdidx]))
 			pte_page = m2v(pmd[pmdidx].pmd);
 		else {
 			/* Check for free pte pages */
 			if (ident_pte == ARRAY_SIZE(level1_ident_pgt))
 				break;
 			pte_page = &level1_ident_pgt[ident_pte];
 			ident_pte += PTRS_PER_PTE;
 			pmd[pmdidx] = __pmd(__pa(pte_page) | _PAGE_TABLE);
 		}
 		/* Install mappings */
 		for (pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) {
 			pte_t pte;
 			if (pfn > max_pfn_mapped)
 				max_pfn_mapped = pfn;
 			if (!pte_none(pte_page[pteidx]))
 				continue;
 			pte = pfn_pte(pfn, PAGE_KERNEL_EXEC);
 			pte_page[pteidx] = pte;
 		}
 	}
 	for (pteidx = 0; pteidx < ident_pte; pteidx += PTRS_PER_PTE)
 		set_page_prot(&level1_ident_pgt[pteidx], PAGE_KERNEL_RO);
 	set_page_prot(pmd, PAGE_KERNEL_RO);
 }
 #ifdef CONFIG_X86_64
 static void convert_pfn_mfn(void *v)
 {
 	pte_t *pte = v;
 	int i;
 	/* All levels are converted the same way, so just treat them
 	   as ptes. */
 	for (i = 0; i < PTRS_PER_PTE; i++)
 		pte[i] = xen_make_pte(pte[i].pte);
 }
 /*
  * Set up the inital kernel pagetable.
  *
  * We can construct this by grafting the Xen provided pagetable into
  * head_64.S's preconstructed pagetables.  We copy the Xen L2's into
  * level2_ident_pgt, level2_kernel_pgt and level2_fixmap_pgt.  This
  * means that only the kernel has a physical mapping to start with -
  * but that's enough to get __va working.  We need to fill in the rest
  * of the physical mapping once some sort of allocator has been set
  * up.
  */
 static __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
 						unsigned long max_pfn)
 {
 	pud_t *l3;
 	pmd_t *l2;
 	/* Zap identity mapping */
 	init_level4_pgt[0] = __pgd(0);
 	/* Pre-constructed entries are in pfn, so convert to mfn */
 	convert_pfn_mfn(init_level4_pgt);
 	convert_pfn_mfn(level3_ident_pgt);
 	convert_pfn_mfn(level3_kernel_pgt);
 	l3 = m2v(pgd[pgd_index(__START_KERNEL_map)].pgd);
 	l2 = m2v(l3[pud_index(__START_KERNEL_map)].pud);
 	memcpy(level2_ident_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD);
 	memcpy(level2_kernel_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD);
 	l3 = m2v(pgd[pgd_index(__START_KERNEL_map + PMD_SIZE)].pgd);
 	l2 = m2v(l3[pud_index(__START_KERNEL_map + PMD_SIZE)].pud);
 	memcpy(level2_fixmap_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD);
 	/* Set up identity map */
 	xen_map_identity_early(level2_ident_pgt, max_pfn);
 	/* Make pagetable pieces RO */
 	set_page_prot(init_level4_pgt, PAGE_KERNEL_RO);
 	set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO);
 	set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO);
 	set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO);
 	set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
 	set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO);
 	/* Pin down new L4 */
 	pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE,
 			  PFN_DOWN(__pa_symbol(init_level4_pgt)));
 	/* Unpin Xen-provided one */
 	pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
 	/* Switch over */
 	pgd = init_level4_pgt;
 	/*
 	 * At this stage there can be no user pgd, and no page
 	 * structure to attach it to, so make sure we just set kernel
 	 * pgd.
 	 */
 	xen_mc_batch();
 	__xen_write_cr3(true, __pa(pgd));
 	xen_mc_issue(PARAVIRT_LAZY_CPU);
 	reserve_early(__pa(xen_start_info->pt_base),
 		      __pa(xen_start_info->pt_base +
 			   xen_start_info->nr_pt_frames * PAGE_SIZE),
 		      "XEN PAGETABLES");
 	return pgd;
 }
 #else	/* !CONFIG_X86_64 */
 static pmd_t level2_kernel_pgt[PTRS_PER_PMD] __page_aligned_bss;
 static __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
 						unsigned long max_pfn)
 {
 	pmd_t *kernel_pmd;
 	init_pg_tables_start = __pa(pgd);
 	init_pg_tables_end = __pa(pgd) + xen_start_info->nr_pt_frames*PAGE_SIZE;
 	max_pfn_mapped = PFN_DOWN(init_pg_tables_end + 512*1024);
 	kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd);
 	memcpy(level2_kernel_pgt, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD);
 	xen_map_identity_early(level2_kernel_pgt, max_pfn);
 	memcpy(swapper_pg_dir, pgd, sizeof(pgd_t) * PTRS_PER_PGD);
 	set_pgd(&swapper_pg_dir[KERNEL_PGD_BOUNDARY],
 			__pgd(__pa(level2_kernel_pgt) | _PAGE_PRESENT));
 	set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
 	set_page_prot(swapper_pg_dir, PAGE_KERNEL_RO);
 	set_page_prot(empty_zero_page, PAGE_KERNEL_RO);
 	pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
 	xen_write_cr3(__pa(swapper_pg_dir));
 	pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(swapper_pg_dir)));
 	return swapper_pg_dir;
 }
 #endif	/* CONFIG_X86_64 */
 /* First C function to be called on Xen boot */
 asmlinkage void __init xen_start_kernel(void)
 {
 	pgd_t *pgd;
 	if (!xen_start_info)
 		return;
 	xen_domain_type = XEN_PV_DOMAIN;
 	BUG_ON(memcmp(xen_start_info->magic, "xen-3", 5) != 0);
 	xen_setup_features();
 	/* Install Xen paravirt ops */
 	pv_info = xen_info;
 	pv_init_ops = xen_init_ops;
 	pv_time_ops = xen_time_ops;
 	pv_cpu_ops = xen_cpu_ops;
 	pv_apic_ops = xen_apic_ops;
 	pv_mmu_ops = xen_mmu_ops;
 	xen_init_irq_ops();
 #ifdef CONFIG_X86_LOCAL_APIC
 	/*
 	 * set up the basic apic ops.
 	 */
 	apic_ops = &xen_basic_apic_ops;
 #endif
 	if (xen_feature(XENFEAT_mmu_pt_update_preserve_ad)) {
 		pv_mmu_ops.ptep_modify_prot_start = xen_ptep_modify_prot_start;
 		pv_mmu_ops.ptep_modify_prot_commit = xen_ptep_modify_prot_commit;
 	}
 	machine_ops = xen_machine_ops;
 #ifdef CONFIG_X86_64
 	/* Disable until direct per-cpu data access. */
 	have_vcpu_info_placement = 0;
 	x86_64_init_pda();
 #endif
 	xen_smp_init();
 	/* Get mfn list */
 	if (!xen_feature(XENFEAT_auto_translated_physmap))
 		xen_build_dynamic_phys_to_machine();
 	pgd = (pgd_t *)xen_start_info->pt_base;
 	/* Prevent unwanted bits from being set in PTEs. */
 	__supported_pte_mask &= ~_PAGE_GLOBAL;
 	if (!xen_initial_domain())
 		__supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
 	/* Don't do the full vcpu_info placement stuff until we have a
 	   possible map and a non-dummy shared_info. */
 	per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0];
 	xen_raw_console_write("mapping kernel into physical memory\n");
 	pgd = xen_setup_kernel_pagetable(pgd, xen_start_info->nr_pages);
 	init_mm.pgd = pgd;
 	/* keep using Xen gdt for now; no urgent need to change it */
 	pv_info.kernel_rpl = 1;
 	if (xen_feature(XENFEAT_supervisor_mode_kernel))
 		pv_info.kernel_rpl = 0;
 	/* set the limit of our address space */
 	xen_reserve_top();
 #ifdef CONFIG_X86_32
 	/* set up basic CPUID stuff */
 	cpu_detect(&new_cpu_data);
 	new_cpu_data.hard_math = 1;
 	new_cpu_data.x86_capability[0] = cpuid_edx(1);
 #endif
 	/* Poke various useful things into boot_params */
 	boot_params.hdr.type_of_loader = (9 << 4) | 0;
 	boot_params.hdr.ramdisk_image = xen_start_info->mod_start
 		? __pa(xen_start_info->mod_start) : 0;
 	boot_params.hdr.ramdisk_size = xen_start_info->mod_len;
 	boot_params.hdr.cmd_line_ptr = __pa(xen_start_info->cmd_line);
 	if (!xen_initial_domain()) {
 		add_preferred_console("xenboot", 0, NULL);
 		add_preferred_console("tty", 0, NULL);
 		add_preferred_console("hvc", 0, NULL);
 	}
 	xen_raw_console_write("about to get started...\n");
 	/* Start the world */
 #ifdef CONFIG_X86_32
 	i386_start_kernel();
 #else
 	x86_64_start_reservations((char *)__pa_symbol(&boot_params));
 #endif
 }

drivers/xen/balloon.c

Diff comments View file @ ecbf29c

 /******************************************************************************
  * balloon.c
  *
  * Xen balloon driver - enables returning/claiming memory to/from Xen.
  *
  * Copyright (c) 2003, B Dragovic
  * Copyright (c) 2003-2004, M Williamson, K Fraser
  * Copyright (c) 2005 Dan M. Smith, IBM Corporation
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License version 2
  * as published by the Free Software Foundation; or, when distributed
  * separately from the Linux kernel or incorporated into other
  * software packages, subject to the following license:
  *
  * Permission is hereby granted, free of charge, to any person obtaining a copy
  * of this source file (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.
  */
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/errno.h>
 #include <linux/mm.h>
 #include <linux/bootmem.h>
 #include <linux/pagemap.h>
 #include <linux/highmem.h>
 #include <linux/mutex.h>
 #include <linux/list.h>
 #include <linux/sysdev.h>
-#include <asm/xen/hypervisor.h>
 #include <asm/page.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
 #include <asm/uaccess.h>
 #include <asm/tlb.h>
+#include <asm/xen/hypervisor.h>
+#include <asm/xen/hypercall.h>
+#include <xen/interface/xen.h>
 #include <xen/interface/memory.h>
 #include <xen/xenbus.h>
 #include <xen/features.h>
 #include <xen/page.h>
 #define PAGES2KB(_p) ((_p)<<(PAGE_SHIFT-10))
 #define BALLOON_CLASS_NAME "xen_memory"
 struct balloon_stats {
 	/* We aim for 'current allocation' == 'target allocation'. */
 	unsigned long current_pages;
 	unsigned long target_pages;
 	/* We may hit the hard limit in Xen. If we do then we remember it. */
 	unsigned long hard_limit;
 	/*
 	 * Drivers may alter the memory reservation independently, but they
 	 * must inform the balloon driver so we avoid hitting the hard limit.
 	 */
 	unsigned long driver_pages;
 	/* Number of pages in high- and low-memory balloons. */
 	unsigned long balloon_low;
 	unsigned long balloon_high;
 };
 static DEFINE_MUTEX(balloon_mutex);
 static struct sys_device balloon_sysdev;
 static int register_balloon(struct sys_device *sysdev);
 /*
  * Protects atomic reservation decrease/increase against concurrent increases.
  * Also protects non-atomic updates of current_pages and driver_pages, and
  * balloon lists.
  */
 static DEFINE_SPINLOCK(balloon_lock);
 static struct balloon_stats balloon_stats;
 /* We increase/decrease in batches which fit in a page */
 static unsigned long frame_list[PAGE_SIZE / sizeof(unsigned long)];
 /* VM /proc information for memory */
 extern unsigned long totalram_pages;
 #ifdef CONFIG_HIGHMEM
 extern unsigned long totalhigh_pages;
 #define inc_totalhigh_pages() (totalhigh_pages++)
 #define dec_totalhigh_pages() (totalhigh_pages--)
 #else
 #define inc_totalhigh_pages() do {} while(0)
 #define dec_totalhigh_pages() do {} while(0)
 #endif
 /* List of ballooned pages, threaded through the mem_map array. */
 static LIST_HEAD(ballooned_pages);
 /* Main work function, always executed in process context. */
 static void balloon_process(struct work_struct *work);
 static DECLARE_WORK(balloon_worker, balloon_process);
 static struct timer_list balloon_timer;
 /* When ballooning out (allocating memory to return to Xen) we don't really
    want the kernel to try too hard since that can trigger the oom killer. */
 #define GFP_BALLOON \
 	(GFP_HIGHUSER | __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC)
 static void scrub_page(struct page *page)
 {
 #ifdef CONFIG_XEN_SCRUB_PAGES
 	clear_highpage(page);
 #endif
 }
 /* balloon_append: add the given page to the balloon. */
 static void balloon_append(struct page *page)
 {
 	/* Lowmem is re-populated first, so highmem pages go at list tail. */
 	if (PageHighMem(page)) {
 		list_add_tail(&page->lru, &ballooned_pages);
 		balloon_stats.balloon_high++;
 		dec_totalhigh_pages();
 	} else {
 		list_add(&page->lru, &ballooned_pages);
 		balloon_stats.balloon_low++;
 	}
 }
 /* balloon_retrieve: rescue a page from the balloon, if it is not empty. */
 static struct page *balloon_retrieve(void)
 {
 	struct page *page;
 	if (list_empty(&ballooned_pages))
 		return NULL;
 	page = list_entry(ballooned_pages.next, struct page, lru);
 	list_del(&page->lru);
 	if (PageHighMem(page)) {
 		balloon_stats.balloon_high--;
 		inc_totalhigh_pages();
 	}
 	else
 		balloon_stats.balloon_low--;
 	return page;
 }
 static struct page *balloon_first_page(void)
 {
 	if (list_empty(&ballooned_pages))
 		return NULL;
 	return list_entry(ballooned_pages.next, struct page, lru);
 }
 static struct page *balloon_next_page(struct page *page)
 {
 	struct list_head *next = page->lru.next;
 	if (next == &ballooned_pages)
 		return NULL;
 	return list_entry(next, struct page, lru);
 }
 static void balloon_alarm(unsigned long unused)
 {
 	schedule_work(&balloon_worker);
 }
 static unsigned long current_target(void)
 {
 	unsigned long target = min(balloon_stats.target_pages, balloon_stats.hard_limit);
 	target = min(target,
 		     balloon_stats.current_pages +
 		     balloon_stats.balloon_low +
 		     balloon_stats.balloon_high);
 	return target;
 }
 static int increase_reservation(unsigned long nr_pages)
 {
 	unsigned long  pfn, i, flags;
 	struct page   *page;
 	long           rc;
 	struct xen_memory_reservation reservation = {
 		.address_bits = 0,
 		.extent_order = 0,
 		.domid        = DOMID_SELF
 	};
 	if (nr_pages > ARRAY_SIZE(frame_list))
 		nr_pages = ARRAY_SIZE(frame_list);
 	spin_lock_irqsave(&balloon_lock, flags);
 	page = balloon_first_page();
 	for (i = 0; i < nr_pages; i++) {
 		BUG_ON(page == NULL);
 		frame_list[i] = page_to_pfn(page);;
 		page = balloon_next_page(page);
 	}
 	set_xen_guest_handle(reservation.extent_start, frame_list);
 	reservation.nr_extents = nr_pages;
 	rc = HYPERVISOR_memory_op(XENMEM_populate_physmap, &reservation);
 	if (rc < nr_pages) {
 		if (rc > 0) {
 			int ret;
 			/* We hit the Xen hard limit: reprobe. */
 			reservation.nr_extents = rc;
 			ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation,
 						   &reservation);
 			BUG_ON(ret != rc);
 		}
 		if (rc >= 0)
 			balloon_stats.hard_limit = (balloon_stats.current_pages + rc -
 						    balloon_stats.driver_pages);
 		goto out;
 	}
 	for (i = 0; i < nr_pages; i++) {
 		page = balloon_retrieve();
 		BUG_ON(page == NULL);
 		pfn = page_to_pfn(page);
 		BUG_ON(!xen_feature(XENFEAT_auto_translated_physmap) &&
 		       phys_to_machine_mapping_valid(pfn));
 		set_phys_to_machine(pfn, frame_list[i]);
 		/* Link back into the page tables if not highmem. */
 		if (pfn < max_low_pfn) {
 			int ret;
 			ret = HYPERVISOR_update_va_mapping(
 				(unsigned long)__va(pfn << PAGE_SHIFT),
 				mfn_pte(frame_list[i], PAGE_KERNEL),
 				0);
 			BUG_ON(ret);
 		}
 		/* Relinquish the page back to the allocator. */
 		ClearPageReserved(page);
 		init_page_count(page);
 		__free_page(page);
 	}
 	balloon_stats.current_pages += nr_pages;
 	totalram_pages = balloon_stats.current_pages;
  out:
 	spin_unlock_irqrestore(&balloon_lock, flags);
 	return 0;
 }
 static int decrease_reservation(unsigned long nr_pages)
 {
 	unsigned long  pfn, i, flags;
 	struct page   *page;
 	int            need_sleep = 0;
 	int ret;
 	struct xen_memory_reservation reservation = {
 		.address_bits = 0,
 		.extent_order = 0,
 		.domid        = DOMID_SELF
 	};
 	if (nr_pages > ARRAY_SIZE(frame_list))
 		nr_pages = ARRAY_SIZE(frame_list);
 	for (i = 0; i < nr_pages; i++) {
 		if ((page = alloc_page(GFP_BALLOON)) == NULL) {
 			nr_pages = i;
 			need_sleep = 1;
 			break;
 		}
 		pfn = page_to_pfn(page);
 		frame_list[i] = pfn_to_mfn(pfn);
 		scrub_page(page);
 	}
 	/* Ensure that ballooned highmem pages don't have kmaps. */
 	kmap_flush_unused();
 	flush_tlb_all();
 	spin_lock_irqsave(&balloon_lock, flags);
 	/* No more mappings: invalidate P2M and add to balloon. */
 	for (i = 0; i < nr_pages; i++) {
 		pfn = mfn_to_pfn(frame_list[i]);
 		set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
 		balloon_append(pfn_to_page(pfn));
 	}
 	set_xen_guest_handle(reservation.extent_start, frame_list);
 	reservation.nr_extents   = nr_pages;
 	ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation, &reservation);
 	BUG_ON(ret != nr_pages);
 	balloon_stats.current_pages -= nr_pages;
 	totalram_pages = balloon_stats.current_pages;
 	spin_unlock_irqrestore(&balloon_lock, flags);
 	return need_sleep;
 }
 /*
  * We avoid multiple worker processes conflicting via the balloon mutex.
  * We may of course race updates of the target counts (which are protected
  * by the balloon lock), or with changes to the Xen hard limit, but we will
  * recover from these in time.
  */
 static void balloon_process(struct work_struct *work)
 {
 	int need_sleep = 0;
 	long credit;
 	mutex_lock(&balloon_mutex);
 	do {
 		credit = current_target() - balloon_stats.current_pages;
 		if (credit > 0)
 			need_sleep = (increase_reservation(credit) != 0);
 		if (credit < 0)
 			need_sleep = (decrease_reservation(-credit) != 0);
 #ifndef CONFIG_PREEMPT
 		if (need_resched())
 			schedule();
 #endif
 	} while ((credit != 0) && !need_sleep);
 	/* Schedule more work if there is some still to be done. */
 	if (current_target() != balloon_stats.current_pages)
 		mod_timer(&balloon_timer, jiffies + HZ);
 	mutex_unlock(&balloon_mutex);
 }
 /* Resets the Xen limit, sets new target, and kicks off processing. */
 static void balloon_set_new_target(unsigned long target)
 {
 	/* No need for lock. Not read-modify-write updates. */
 	balloon_stats.hard_limit   = ~0UL;
 	balloon_stats.target_pages = target;
 	schedule_work(&balloon_worker);
 }
 static struct xenbus_watch target_watch =
 {
 	.node = "memory/target"
 };
 /* React to a change in the target key */
 static void watch_target(struct xenbus_watch *watch,
 			 const char **vec, unsigned int len)
 {
 	unsigned long long new_target;
 	int err;
 	err = xenbus_scanf(XBT_NIL, "memory", "target", "%llu", &new_target);
 	if (err != 1) {
 		/* This is ok (for domain0 at least) - so just return */
 		return;
 	}
 	/* The given memory/target value is in KiB, so it needs converting to
 	 * pages. PAGE_SHIFT converts bytes to pages, hence PAGE_SHIFT - 10.
 	 */
 	balloon_set_new_target(new_target >> (PAGE_SHIFT - 10));
 }
 static int balloon_init_watcher(struct notifier_block *notifier,
 				unsigned long event,
 				void *data)
 {
 	int err;
 	err = register_xenbus_watch(&target_watch);
 	if (err)
 		printk(KERN_ERR "Failed to set balloon watcher\n");
 	return NOTIFY_DONE;
 }
 static struct notifier_block xenstore_notifier;
 static int __init balloon_init(void)
 {
 	unsigned long pfn;
 	struct page *page;
 	if (!xen_pv_domain())
 		return -ENODEV;
 	pr_info("xen_balloon: Initialising balloon driver.\n");
 	balloon_stats.current_pages = min(xen_start_info->nr_pages, max_pfn);
 	totalram_pages   = balloon_stats.current_pages;
 	balloon_stats.target_pages  = balloon_stats.current_pages;
 	balloon_stats.balloon_low   = 0;
 	balloon_stats.balloon_high  = 0;
 	balloon_stats.driver_pages  = 0UL;
 	balloon_stats.hard_limit    = ~0UL;
 	init_timer(&balloon_timer);
 	balloon_timer.data = 0;
 	balloon_timer.function = balloon_alarm;
 	register_balloon(&balloon_sysdev);
 	/* Initialise the balloon with excess memory space. */
 	for (pfn = xen_start_info->nr_pages; pfn < max_pfn; pfn++) {
 		page = pfn_to_page(pfn);
 		if (!PageReserved(page))
 			balloon_append(page);
 	}
 	target_watch.callback = watch_target;
 	xenstore_notifier.notifier_call = balloon_init_watcher;
 	register_xenstore_notifier(&xenstore_notifier);
 	return 0;
 }
 subsys_initcall(balloon_init);
 static void balloon_exit(void)
 {
     /* XXX - release balloon here */
     return;
 }
 module_exit(balloon_exit);
 #define BALLOON_SHOW(name, format, args...)				\
 	static ssize_t show_##name(struct sys_device *dev,		\
 				   struct sysdev_attribute *attr,	\
 				   char *buf)				\
 	{								\
 		return sprintf(buf, format, ##args);			\
 	}								\
 	static SYSDEV_ATTR(name, S_IRUGO, show_##name, NULL)
 BALLOON_SHOW(current_kb, "%lu\n", PAGES2KB(balloon_stats.current_pages));
 BALLOON_SHOW(low_kb, "%lu\n", PAGES2KB(balloon_stats.balloon_low));
 BALLOON_SHOW(high_kb, "%lu\n", PAGES2KB(balloon_stats.balloon_high));
 BALLOON_SHOW(hard_limit_kb,
 	     (balloon_stats.hard_limit!=~0UL) ? "%lu\n" : "???\n",
 	     (balloon_stats.hard_limit!=~0UL) ? PAGES2KB(balloon_stats.hard_limit) : 0);
 BALLOON_SHOW(driver_kb, "%lu\n", PAGES2KB(balloon_stats.driver_pages));
 static ssize_t show_target_kb(struct sys_device *dev, struct sysdev_attribute *attr,
 			      char *buf)
 {
 	return sprintf(buf, "%lu\n", PAGES2KB(balloon_stats.target_pages));
 }
 static ssize_t store_target_kb(struct sys_device *dev,
 			       struct sysdev_attribute *attr,
 			       const char *buf,
 			       size_t count)
 {
 	char *endchar;
 	unsigned long long target_bytes;
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 	target_bytes = memparse(buf, &endchar);
 	balloon_set_new_target(target_bytes >> PAGE_SHIFT);
 	return count;
 }
 static SYSDEV_ATTR(target_kb, S_IRUGO | S_IWUSR,
 		   show_target_kb, store_target_kb);
 static struct sysdev_attribute *balloon_attrs[] = {
 	&attr_target_kb,
 };
 static struct attribute *balloon_info_attrs[] = {
 	&attr_current_kb.attr,
 	&attr_low_kb.attr,
 	&attr_high_kb.attr,
 	&attr_hard_limit_kb.attr,
 	&attr_driver_kb.attr,
 	NULL
 };
 static struct attribute_group balloon_info_group = {
 	.name = "info",
 	.attrs = balloon_info_attrs,
 };
 static struct sysdev_class balloon_sysdev_class = {
 	.name = BALLOON_CLASS_NAME,
 };
 static int register_balloon(struct sys_device *sysdev)
 {
 	int i, error;
 	error = sysdev_class_register(&balloon_sysdev_class);
 	if (error)
 		return error;
 	sysdev->id = 0;
 	sysdev->cls = &balloon_sysdev_class;
 	error = sysdev_register(sysdev);
 	if (error) {
 		sysdev_class_unregister(&balloon_sysdev_class);
 		return error;
 	}
 	for (i = 0; i < ARRAY_SIZE(balloon_attrs); i++) {
 		error = sysdev_create_file(sysdev, balloon_attrs[i]);
 		if (error)
 			goto fail;
 	}
 	error = sysfs_create_group(&sysdev->kobj, &balloon_info_group);
 	if (error)
 		goto fail;
 	return 0;
  fail:
 	while (--i >= 0)
 		sysdev_remove_file(sysdev, balloon_attrs[i]);
 	sysdev_unregister(sysdev);
 	sysdev_class_unregister(&balloon_sysdev_class);
 	return error;
 }
 MODULE_LICENSE("GPL");

drivers/xen/features.c

Diff comments View file @ ecbf29c

1	/******************************************************************************	1	/******************************************************************************
2	* features.c	2	* features.c
3	*	3	*
4	* Xen feature flags.	4	* Xen feature flags.
5	*	5	*
6	* Copyright (c) 2006, Ian Campbell, XenSource Inc.	6	* Copyright (c) 2006, Ian Campbell, XenSource Inc.
7	*/	7	*/
8	#include <linux/types.h>	8	#include <linux/types.h>
9	#include <linux/cache.h>	9	#include <linux/cache.h>
10	#include <linux/module.h>	10	#include <linux/module.h>
11	#include <asm/xen/hypervisor.h>	11
		12	#include <asm/xen/hypercall.h>
		13
		14	#include <xen/interface/xen.h>
		15	#include <xen/interface/version.h>
12	#include <xen/features.h>	16	#include <xen/features.h>
13		17
14	u8 xen_features[XENFEAT_NR_SUBMAPS * 32] __read_mostly;	18	u8 xen_features[XENFEAT_NR_SUBMAPS * 32] __read_mostly;
15	EXPORT_SYMBOL_GPL(xen_features);	19	EXPORT_SYMBOL_GPL(xen_features);
16		20
17	void xen_setup_features(void)	21	void xen_setup_features(void)
18	{	22	{
19	struct xen_feature_info fi;	23	struct xen_feature_info fi;
20	int i, j;	24	int i, j;
21		25
22	for (i = 0; i < XENFEAT_NR_SUBMAPS; i++) {	26	for (i = 0; i < XENFEAT_NR_SUBMAPS; i++) {
23	fi.submap_idx = i;	27	fi.submap_idx = i;
24	if (HYPERVISOR_xen_version(XENVER_get_features, &fi) < 0)	28	if (HYPERVISOR_xen_version(XENVER_get_features, &fi) < 0)
25	break;	29	break;
26	for (j = 0; j < 32; j++)	30	for (j = 0; j < 32; j++)
27	xen_features[i * 32 + j] = !!(fi.submap & 1<<j);	31	xen_features[i * 32 + j] = !!(fi.submap & 1<<j);
28	}	32	}
29	}	33	}
30		34

drivers/xen/grant-table.c

Diff comments View file @ ecbf29c

 /******************************************************************************
  * grant_table.c
  *
  * Granting foreign access to our memory reservation.
  *
  * Copyright (c) 2005-2006, Christopher Clark
  * Copyright (c) 2004-2005, K A Fraser
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License version 2
  * as published by the Free Software Foundation; or, when distributed
  * separately from the Linux kernel or incorporated into other
  * software packages, subject to the following license:
  *
  * Permission is hereby granted, free of charge, to any person obtaining a copy
  * of this source file (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.
  */
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
 #include <xen/interface/xen.h>
 #include <xen/page.h>
 #include <xen/grant_table.h>
+#include <asm/xen/hypercall.h>
 #include <asm/pgtable.h>
 #include <asm/sync_bitops.h>
 /* External tools reserve first few grant table entries. */
 #define NR_RESERVED_ENTRIES 8
 #define GNTTAB_LIST_END 0xffffffff
 #define GREFS_PER_GRANT_FRAME (PAGE_SIZE / sizeof(struct grant_entry))
 static grant_ref_t **gnttab_list;
 static unsigned int nr_grant_frames;
 static unsigned int boot_max_nr_grant_frames;
 static int gnttab_free_count;
 static grant_ref_t gnttab_free_head;
 static DEFINE_SPINLOCK(gnttab_list_lock);
 static struct grant_entry *shared;
 static struct gnttab_free_callback *gnttab_free_callback_list;
 static int gnttab_expand(unsigned int req_entries);
 #define RPP (PAGE_SIZE / sizeof(grant_ref_t))
 static inline grant_ref_t *__gnttab_entry(grant_ref_t entry)
 {
 	return &gnttab_list[(entry) / RPP][(entry) % RPP];
 }
 /* This can be used as an l-value */
 #define gnttab_entry(entry) (*__gnttab_entry(entry))
 static int get_free_entries(unsigned count)
 {
 	unsigned long flags;
 	int ref, rc;
 	grant_ref_t head;
 	spin_lock_irqsave(&gnttab_list_lock, flags);
 	if ((gnttab_free_count < count) &&
 	    ((rc = gnttab_expand(count - gnttab_free_count)) < 0)) {
 		spin_unlock_irqrestore(&gnttab_list_lock, flags);
 		return rc;
 	}
 	ref = head = gnttab_free_head;
 	gnttab_free_count -= count;
 	while (count-- > 1)
 		head = gnttab_entry(head);
 	gnttab_free_head = gnttab_entry(head);
 	gnttab_entry(head) = GNTTAB_LIST_END;
 	spin_unlock_irqrestore(&gnttab_list_lock, flags);
 	return ref;
 }
 static void do_free_callbacks(void)
 {
 	struct gnttab_free_callback *callback, *next;
 	callback = gnttab_free_callback_list;
 	gnttab_free_callback_list = NULL;
 	while (callback != NULL) {
 		next = callback->next;
 		if (gnttab_free_count >= callback->count) {
 			callback->next = NULL;
 			callback->fn(callback->arg);
 		} else {
 			callback->next = gnttab_free_callback_list;
 			gnttab_free_callback_list = callback;
 		}
 		callback = next;
 	}
 }
 static inline void check_free_callbacks(void)
 {
 	if (unlikely(gnttab_free_callback_list))
 		do_free_callbacks();
 }
 static void put_free_entry(grant_ref_t ref)
 {
 	unsigned long flags;
 	spin_lock_irqsave(&gnttab_list_lock, flags);
 	gnttab_entry(ref) = gnttab_free_head;
 	gnttab_free_head = ref;
 	gnttab_free_count++;
 	check_free_callbacks();
 	spin_unlock_irqrestore(&gnttab_list_lock, flags);
 }
 static void update_grant_entry(grant_ref_t ref, domid_t domid,
 			       unsigned long frame, unsigned flags)
 {
 	/*
 	 * Introducing a valid entry into the grant table:
 	 *  1. Write ent->domid.
 	 *  2. Write ent->frame:
 	 *      GTF_permit_access:   Frame to which access is permitted.
 	 *      GTF_accept_transfer: Pseudo-phys frame slot being filled by new
 	 *                           frame, or zero if none.
 	 *  3. Write memory barrier (WMB).
 	 *  4. Write ent->flags, inc. valid type.
 	 */
 	shared[ref].frame = frame;
 	shared[ref].domid = domid;
 	wmb();
 	shared[ref].flags = flags;
 }
 /*
  * Public grant-issuing interface functions
  */
 void gnttab_grant_foreign_access_ref(grant_ref_t ref, domid_t domid,
 				     unsigned long frame, int readonly)
 {
 	update_grant_entry(ref, domid, frame,
 			   GTF_permit_access | (readonly ? GTF_readonly : 0));
 }
 EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access_ref);
 int gnttab_grant_foreign_access(domid_t domid, unsigned long frame,
 				int readonly)
 {
 	int ref;
 	ref = get_free_entries(1);
 	if (unlikely(ref < 0))
 		return -ENOSPC;
 	gnttab_grant_foreign_access_ref(ref, domid, frame, readonly);
 	return ref;
 }
 EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access);
 int gnttab_query_foreign_access(grant_ref_t ref)
 {
 	u16 nflags;
 	nflags = shared[ref].flags;
 	return (nflags & (GTF_reading|GTF_writing));
 }
 EXPORT_SYMBOL_GPL(gnttab_query_foreign_access);
 int gnttab_end_foreign_access_ref(grant_ref_t ref, int readonly)
 {
 	u16 flags, nflags;
 	nflags = shared[ref].flags;
 	do {
 		flags = nflags;
 		if (flags & (GTF_reading|GTF_writing)) {
 			printk(KERN_ALERT "WARNING: g.e. still in use!\n");
 			return 0;
 		}
 	} while ((nflags = sync_cmpxchg(&shared[ref].flags, flags, 0)) != flags);
 	return 1;
 }
 EXPORT_SYMBOL_GPL(gnttab_end_foreign_access_ref);
 void gnttab_end_foreign_access(grant_ref_t ref, int readonly,
 			       unsigned long page)
 {
 	if (gnttab_end_foreign_access_ref(ref, readonly)) {
 		put_free_entry(ref);
 		if (page != 0)
 			free_page(page);
 	} else {
 		/* XXX This needs to be fixed so that the ref and page are
 		   placed on a list to be freed up later. */
 		printk(KERN_WARNING
 		       "WARNING: leaking g.e. and page still in use!\n");
 	}
 }
 EXPORT_SYMBOL_GPL(gnttab_end_foreign_access);
 int gnttab_grant_foreign_transfer(domid_t domid, unsigned long pfn)
 {
 	int ref;
 	ref = get_free_entries(1);
 	if (unlikely(ref < 0))
 		return -ENOSPC;
 	gnttab_grant_foreign_transfer_ref(ref, domid, pfn);
 	return ref;
 }
 EXPORT_SYMBOL_GPL(gnttab_grant_foreign_transfer);
 void gnttab_grant_foreign_transfer_ref(grant_ref_t ref, domid_t domid,
 				       unsigned long pfn)
 {
 	update_grant_entry(ref, domid, pfn, GTF_accept_transfer);
 }
 EXPORT_SYMBOL_GPL(gnttab_grant_foreign_transfer_ref);
 unsigned long gnttab_end_foreign_transfer_ref(grant_ref_t ref)
 {
 	unsigned long frame;
 	u16           flags;
 	/*
 	 * If a transfer is not even yet started, try to reclaim the grant
 	 * reference and return failure (== 0).
 	 */
 	while (!((flags = shared[ref].flags) & GTF_transfer_committed)) {
 		if (sync_cmpxchg(&shared[ref].flags, flags, 0) == flags)
 			return 0;
 		cpu_relax();
 	}
 	/* If a transfer is in progress then wait until it is completed. */
 	while (!(flags & GTF_transfer_completed)) {
 		flags = shared[ref].flags;
 		cpu_relax();
 	}
 	rmb();	/* Read the frame number /after/ reading completion status. */
 	frame = shared[ref].frame;
 	BUG_ON(frame == 0);
 	return frame;
 }
 EXPORT_SYMBOL_GPL(gnttab_end_foreign_transfer_ref);
 unsigned long gnttab_end_foreign_transfer(grant_ref_t ref)
 {
 	unsigned long frame = gnttab_end_foreign_transfer_ref(ref);
 	put_free_entry(ref);
 	return frame;
 }
 EXPORT_SYMBOL_GPL(gnttab_end_foreign_transfer);
 void gnttab_free_grant_reference(grant_ref_t ref)
 {
 	put_free_entry(ref);
 }
 EXPORT_SYMBOL_GPL(gnttab_free_grant_reference);
 void gnttab_free_grant_references(grant_ref_t head)
 {
 	grant_ref_t ref;
 	unsigned long flags;
 	int count = 1;
 	if (head == GNTTAB_LIST_END)
 		return;
 	spin_lock_irqsave(&gnttab_list_lock, flags);
 	ref = head;
 	while (gnttab_entry(ref) != GNTTAB_LIST_END) {
 		ref = gnttab_entry(ref);
 		count++;
 	}
 	gnttab_entry(ref) = gnttab_free_head;
 	gnttab_free_head = head;
 	gnttab_free_count += count;
 	check_free_callbacks();
 	spin_unlock_irqrestore(&gnttab_list_lock, flags);
 }
 EXPORT_SYMBOL_GPL(gnttab_free_grant_references);
 int gnttab_alloc_grant_references(u16 count, grant_ref_t *head)
 {
 	int h = get_free_entries(count);
 	if (h < 0)
 		return -ENOSPC;
 	*head = h;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(gnttab_alloc_grant_references);
 int gnttab_empty_grant_references(const grant_ref_t *private_head)
 {
 	return (*private_head == GNTTAB_LIST_END);
 }
 EXPORT_SYMBOL_GPL(gnttab_empty_grant_references);
 int gnttab_claim_grant_reference(grant_ref_t *private_head)
 {
 	grant_ref_t g = *private_head;
 	if (unlikely(g == GNTTAB_LIST_END))
 		return -ENOSPC;
 	*private_head = gnttab_entry(g);
 	return g;
 }
 EXPORT_SYMBOL_GPL(gnttab_claim_grant_reference);
 void gnttab_release_grant_reference(grant_ref_t *private_head,
 				    grant_ref_t release)
 {
 	gnttab_entry(release) = *private_head;
 	*private_head = release;
 }
 EXPORT_SYMBOL_GPL(gnttab_release_grant_reference);
 void gnttab_request_free_callback(struct gnttab_free_callback *callback,
 				  void (*fn)(void *), void *arg, u16 count)
 {
 	unsigned long flags;
 	spin_lock_irqsave(&gnttab_list_lock, flags);
 	if (callback->next)
 		goto out;
 	callback->fn = fn;
 	callback->arg = arg;
 	callback->count = count;
 	callback->next = gnttab_free_callback_list;
 	gnttab_free_callback_list = callback;
 	check_free_callbacks();
 out:
 	spin_unlock_irqrestore(&gnttab_list_lock, flags);
 }
 EXPORT_SYMBOL_GPL(gnttab_request_free_callback);
 void gnttab_cancel_free_callback(struct gnttab_free_callback *callback)
 {
 	struct gnttab_free_callback **pcb;
 	unsigned long flags;
 	spin_lock_irqsave(&gnttab_list_lock, flags);
 	for (pcb = &gnttab_free_callback_list; *pcb; pcb = &(*pcb)->next) {
 		if (*pcb == callback) {
 			*pcb = callback->next;
 			break;
 		}
 	}
 	spin_unlock_irqrestore(&gnttab_list_lock, flags);
 }
 EXPORT_SYMBOL_GPL(gnttab_cancel_free_callback);
 static int grow_gnttab_list(unsigned int more_frames)
 {
 	unsigned int new_nr_grant_frames, extra_entries, i;
 	unsigned int nr_glist_frames, new_nr_glist_frames;
 	new_nr_grant_frames = nr_grant_frames + more_frames;
 	extra_entries       = more_frames * GREFS_PER_GRANT_FRAME;
 	nr_glist_frames = (nr_grant_frames * GREFS_PER_GRANT_FRAME + RPP - 1) / RPP;
 	new_nr_glist_frames =
 		(new_nr_grant_frames * GREFS_PER_GRANT_FRAME + RPP - 1) / RPP;
 	for (i = nr_glist_frames; i < new_nr_glist_frames; i++) {
 		gnttab_list[i] = (grant_ref_t *)__get_free_page(GFP_ATOMIC);
 		if (!gnttab_list[i])
 			goto grow_nomem;
 	}
 	for (i = GREFS_PER_GRANT_FRAME * nr_grant_frames;
 	     i < GREFS_PER_GRANT_FRAME * new_nr_grant_frames - 1; i++)
 		gnttab_entry(i) = i + 1;
 	gnttab_entry(i) = gnttab_free_head;
 	gnttab_free_head = GREFS_PER_GRANT_FRAME * nr_grant_frames;
 	gnttab_free_count += extra_entries;
 	nr_grant_frames = new_nr_grant_frames;
 	check_free_callbacks();
 	return 0;
 grow_nomem:
 	for ( ; i >= nr_glist_frames; i--)
 		free_page((unsigned long) gnttab_list[i]);
 	return -ENOMEM;
 }
 static unsigned int __max_nr_grant_frames(void)
 {
 	struct gnttab_query_size query;
 	int rc;
 	query.dom = DOMID_SELF;
 	rc = HYPERVISOR_grant_table_op(GNTTABOP_query_size, &query, 1);
 	if ((rc < 0) || (query.status != GNTST_okay))
 		return 4; /* Legacy max supported number of frames */
 	return query.max_nr_frames;
 }
 static inline unsigned int max_nr_grant_frames(void)
 {
 	unsigned int xen_max = __max_nr_grant_frames();
 	if (xen_max > boot_max_nr_grant_frames)
 		return boot_max_nr_grant_frames;
 	return xen_max;
 }
 static int gnttab_map(unsigned int start_idx, unsigned int end_idx)
 {
 	struct gnttab_setup_table setup;
 	unsigned long *frames;
 	unsigned int nr_gframes = end_idx + 1;
 	int rc;
 	frames = kmalloc(nr_gframes * sizeof(unsigned long), GFP_ATOMIC);
 	if (!frames)
 		return -ENOMEM;
 	setup.dom        = DOMID_SELF;
 	setup.nr_frames  = nr_gframes;
 	set_xen_guest_handle(setup.frame_list, frames);
 	rc = HYPERVISOR_grant_table_op(GNTTABOP_setup_table, &setup, 1);
 	if (rc == -ENOSYS) {
 		kfree(frames);
 		return -ENOSYS;
 	}
 	BUG_ON(rc || setup.status);
 	rc = arch_gnttab_map_shared(frames, nr_gframes, max_nr_grant_frames(),
 				    &shared);
 	BUG_ON(rc);
 	kfree(frames);
 	return 0;
 }
 int gnttab_resume(void)
 {
 	if (max_nr_grant_frames() < nr_grant_frames)
 		return -ENOSYS;
 	return gnttab_map(0, nr_grant_frames - 1);
 }
 int gnttab_suspend(void)
 {
 	arch_gnttab_unmap_shared(shared, nr_grant_frames);
 	return 0;
 }
 static int gnttab_expand(unsigned int req_entries)
 {
 	int rc;
 	unsigned int cur, extra;
 	cur = nr_grant_frames;
 	extra = ((req_entries + (GREFS_PER_GRANT_FRAME-1)) /
 		 GREFS_PER_GRANT_FRAME);
 	if (cur + extra > max_nr_grant_frames())
 		return -ENOSPC;
 	rc = gnttab_map(cur, cur + extra - 1);
 	if (rc == 0)
 		rc = grow_gnttab_list(extra);
 	return rc;
 }
 static int __devinit gnttab_init(void)
 {
 	int i;
 	unsigned int max_nr_glist_frames, nr_glist_frames;
 	unsigned int nr_init_grefs;
 	if (!xen_domain())
 		return -ENODEV;
 	nr_grant_frames = 1;
 	boot_max_nr_grant_frames = __max_nr_grant_frames();
 	/* Determine the maximum number of frames required for the
 	 * grant reference free list on the current hypervisor.
 	 */
 	max_nr_glist_frames = (boot_max_nr_grant_frames *
 			       GREFS_PER_GRANT_FRAME / RPP);
 	gnttab_list = kmalloc(max_nr_glist_frames * sizeof(grant_ref_t *),
 			      GFP_KERNEL);
 	if (gnttab_list == NULL)
 		return -ENOMEM;
 	nr_glist_frames = (nr_grant_frames * GREFS_PER_GRANT_FRAME + RPP - 1) / RPP;
 	for (i = 0; i < nr_glist_frames; i++) {
 		gnttab_list[i] = (grant_ref_t *)__get_free_page(GFP_KERNEL);
 		if (gnttab_list[i] == NULL)
 			goto ini_nomem;
 	}
 	if (gnttab_resume() < 0)
 		return -ENODEV;
 	nr_init_grefs = nr_grant_frames * GREFS_PER_GRANT_FRAME;
 	for (i = NR_RESERVED_ENTRIES; i < nr_init_grefs - 1; i++)
 		gnttab_entry(i) = i + 1;
 	gnttab_entry(nr_init_grefs - 1) = GNTTAB_LIST_END;
 	gnttab_free_count = nr_init_grefs - NR_RESERVED_ENTRIES;
 	gnttab_free_head  = NR_RESERVED_ENTRIES;
 	printk("Grant table initialized\n");
 	return 0;
  ini_nomem:
 	for (i--; i >= 0; i--)
 		free_page((unsigned long)gnttab_list[i]);
 	kfree(gnttab_list);
 	return -ENOMEM;
 }
 core_initcall(gnttab_init);

include/xen/interface/event_channel.h

Diff comments View file @ ecbf29c

 /******************************************************************************
  * event_channel.h
  *
  * Event channels between domains.
  *
  * Copyright (c) 2003-2004, K A Fraser.
  */
 #ifndef __XEN_PUBLIC_EVENT_CHANNEL_H__
 #define __XEN_PUBLIC_EVENT_CHANNEL_H__
+#include <xen/interface/xen.h>
 typedef uint32_t evtchn_port_t;
 DEFINE_GUEST_HANDLE(evtchn_port_t);
 /*
  * EVTCHNOP_alloc_unbound: Allocate a port in domain <dom> and mark as
  * accepting interdomain bindings from domain <remote_dom>. A fresh port
  * is allocated in <dom> and returned as <port>.
  * NOTES:
  *  1. If the caller is unprivileged then <dom> must be DOMID_SELF.
  *  2. <rdom> may be DOMID_SELF, allowing loopback connections.
  */
 #define EVTCHNOP_alloc_unbound	  6
 struct evtchn_alloc_unbound {
 	/* IN parameters */
 	domid_t dom, remote_dom;
 	/* OUT parameters */
 	evtchn_port_t port;
 };
 /*
  * EVTCHNOP_bind_interdomain: Construct an interdomain event channel between
  * the calling domain and <remote_dom>. <remote_dom,remote_port> must identify
  * a port that is unbound and marked as accepting bindings from the calling
  * domain. A fresh port is allocated in the calling domain and returned as
  * <local_port>.
  * NOTES:
  *  2. <remote_dom> may be DOMID_SELF, allowing loopback connections.
  */
 #define EVTCHNOP_bind_interdomain 0
 struct evtchn_bind_interdomain {
 	/* IN parameters. */
 	domid_t remote_dom;
 	evtchn_port_t remote_port;
 	/* OUT parameters. */
 	evtchn_port_t local_port;
 };
 /*
  * EVTCHNOP_bind_virq: Bind a local event channel to VIRQ <irq> on specified
  * vcpu.
  * NOTES:
  *  1. A virtual IRQ may be bound to at most one event channel per vcpu.
  *  2. The allocated event channel is bound to the specified vcpu. The binding
  *     may not be changed.
  */
 #define EVTCHNOP_bind_virq	  1
 struct evtchn_bind_virq {
 	/* IN parameters. */
 	uint32_t virq;
 	uint32_t vcpu;
 	/* OUT parameters. */
 	evtchn_port_t port;
 };
 /*
  * EVTCHNOP_bind_pirq: Bind a local event channel to PIRQ <irq>.
  * NOTES:
  *  1. A physical IRQ may be bound to at most one event channel per domain.
  *  2. Only a sufficiently-privileged domain may bind to a physical IRQ.
  */
 #define EVTCHNOP_bind_pirq	  2
 struct evtchn_bind_pirq {
 	/* IN parameters. */
 	uint32_t pirq;
 #define BIND_PIRQ__WILL_SHARE 1
 	uint32_t flags; /* BIND_PIRQ__* */
 	/* OUT parameters. */
 	evtchn_port_t port;
 };
 /*
  * EVTCHNOP_bind_ipi: Bind a local event channel to receive events.
  * NOTES:
  *  1. The allocated event channel is bound to the specified vcpu. The binding
  *     may not be changed.
  */
 #define EVTCHNOP_bind_ipi	  7
 struct evtchn_bind_ipi {
 	uint32_t vcpu;
 	/* OUT parameters. */
 	evtchn_port_t port;
 };
 /*
  * EVTCHNOP_close: Close a local event channel <port>. If the channel is
  * interdomain then the remote end is placed in the unbound state
  * (EVTCHNSTAT_unbound), awaiting a new connection.
  */
 #define EVTCHNOP_close		  3
 struct evtchn_close {
 	/* IN parameters. */
 	evtchn_port_t port;
 };
 /*
  * EVTCHNOP_send: Send an event to the remote end of the channel whose local
  * endpoint is <port>.
  */
 #define EVTCHNOP_send		  4
 struct evtchn_send {
 	/* IN parameters. */
 	evtchn_port_t port;
 };
 /*
  * EVTCHNOP_status: Get the current status of the communication channel which
  * has an endpoint at <dom, port>.
  * NOTES:
  *  1. <dom> may be specified as DOMID_SELF.
  *  2. Only a sufficiently-privileged domain may obtain the status of an event
  *     channel for which <dom> is not DOMID_SELF.
  */
 #define EVTCHNOP_status		  5
 struct evtchn_status {
 	/* IN parameters */
 	domid_t  dom;
 	evtchn_port_t port;
 	/* OUT parameters */
 #define EVTCHNSTAT_closed	0  /* Channel is not in use.		     */
 #define EVTCHNSTAT_unbound	1  /* Channel is waiting interdom connection.*/
 #define EVTCHNSTAT_interdomain	2  /* Channel is connected to remote domain. */
 #define EVTCHNSTAT_pirq		3  /* Channel is bound to a phys IRQ line.   */
 #define EVTCHNSTAT_virq		4  /* Channel is bound to a virtual IRQ line */
 #define EVTCHNSTAT_ipi		5  /* Channel is bound to a virtual IPI line */
 	uint32_t status;
 	uint32_t vcpu;		   /* VCPU to which this channel is bound.   */
 	union {
 		struct {
 			domid_t dom;
 		} unbound; /* EVTCHNSTAT_unbound */
 		struct {
 			domid_t dom;
 			evtchn_port_t port;
 		} interdomain; /* EVTCHNSTAT_interdomain */
 		uint32_t pirq;	    /* EVTCHNSTAT_pirq	      */
 		uint32_t virq;	    /* EVTCHNSTAT_virq	      */
 	} u;
 };
 /*
  * EVTCHNOP_bind_vcpu: Specify which vcpu a channel should notify when an
  * event is pending.
  * NOTES:
  *  1. IPI- and VIRQ-bound channels always notify the vcpu that initialised
  *     the binding. This binding cannot be changed.
  *  2. All other channels notify vcpu0 by default. This default is set when
  *     the channel is allocated (a port that is freed and subsequently reused
  *     has its binding reset to vcpu0).
  */
 #define EVTCHNOP_bind_vcpu	  8
 struct evtchn_bind_vcpu {
 	/* IN parameters. */
 	evtchn_port_t port;
 	uint32_t vcpu;
 };
 /*
  * EVTCHNOP_unmask: Unmask the specified local event-channel port and deliver
  * a notification to the appropriate VCPU if an event is pending.
  */
 #define EVTCHNOP_unmask		  9
 struct evtchn_unmask {
 	/* IN parameters. */
 	evtchn_port_t port;
 };
 struct evtchn_op {
 	uint32_t cmd; /* EVTCHNOP_* */
 	union {
 		struct evtchn_alloc_unbound    alloc_unbound;
 		struct evtchn_bind_interdomain bind_interdomain;
 		struct evtchn_bind_virq	       bind_virq;
 		struct evtchn_bind_pirq	       bind_pirq;
 		struct evtchn_bind_ipi	       bind_ipi;
 		struct evtchn_close	       close;
 		struct evtchn_send	       send;
 		struct evtchn_status	       status;
 		struct evtchn_bind_vcpu	       bind_vcpu;
 		struct evtchn_unmask	       unmask;
 	} u;
 };
 DEFINE_GUEST_HANDLE_STRUCT(evtchn_op);
 #endif /* __XEN_PUBLIC_EVENT_CHANNEL_H__ */