5ead97c84f
This patch is a rollup of all the core pieces of the Xen implementation, including: - booting and setup - pagetable setup - privileged instructions - segmentation - interrupt flags - upcalls - multicall batching BOOTING AND SETUP The vmlinux image is decorated with ELF notes which tell the Xen domain builder what the kernel's requirements are; the domain builder then constructs the address space accordingly and starts the kernel. Xen has its own entrypoint for the kernel (contained in an ELF note). The ELF notes are set up by xen-head.S, which is included into head.S. In principle it could be linked separately, but it seems to provoke lots of binutils bugs. Because the domain builder starts the kernel in a fairly sane state (32-bit protected mode, paging enabled, flat segments set up), there's not a lot of setup needed before starting the kernel proper. The main steps are: 1. Install the Xen paravirt_ops, which is simply a matter of a structure assignment. 2. Set init_mm to use the Xen-supplied pagetables (analogous to the head.S generated pagetables in a native boot). 3. Reserve address space for Xen, since it takes a chunk at the top of the address space for its own use. 4. Call start_kernel() PAGETABLE SETUP Once we hit the main kernel boot sequence, it will end up calling back via paravirt_ops to set up various pieces of Xen specific state. One of the critical things which requires a bit of extra care is the construction of the initial init_mm pagetable. Because Xen places tight constraints on pagetables (an active pagetable must always be valid, and must always be mapped read-only to the guest domain), we need to be careful when constructing the new pagetable to keep these constraints in mind. It turns out that the easiest way to do this is use the initial Xen-provided pagetable as a template, and then just insert new mappings for memory where a mapping doesn't already exist. This means that during pagetable setup, it uses a special version of xen_set_pte which ignores any attempt to remap a read-only page as read-write (since Xen will map its own initial pagetable as RO), but lets other changes to the ptes happen, so that things like NX are set properly. PRIVILEGED INSTRUCTIONS AND SEGMENTATION When the kernel runs under Xen, it runs in ring 1 rather than ring 0. This means that it is more privileged than user-mode in ring 3, but it still can't run privileged instructions directly. Non-performance critical instructions are dealt with by taking a privilege exception and trapping into the hypervisor and emulating the instruction, but more performance-critical instructions have their own specific paravirt_ops. In many cases we can avoid having to do any hypercalls for these instructions, or the Xen implementation is quite different from the normal native version. The privileged instructions fall into the broad classes of: Segmentation: setting up the GDT and the GDT entries, LDT, TLS and so on. Xen doesn't allow the GDT to be directly modified; all GDT updates are done via hypercalls where the new entries can be validated. This is important because Xen uses segment limits to prevent the guest kernel from damaging the hypervisor itself. Traps and exceptions: Xen uses a special format for trap entrypoints, so when the kernel wants to set an IDT entry, it needs to be converted to the form Xen expects. Xen sets int 0x80 up specially so that the trap goes straight from userspace into the guest kernel without going via the hypervisor. sysenter isn't supported. Kernel stack: The esp0 entry is extracted from the tss and provided to Xen. TLB operations: the various TLB calls are mapped into corresponding Xen hypercalls. Control registers: all the control registers are privileged. The most important is cr3, which points to the base of the current pagetable, and we handle it specially. Another instruction we treat specially is CPUID, even though its not privileged. We want to control what CPU features are visible to the rest of the kernel, and so CPUID ends up going into a paravirt_op. Xen implements this mainly to disable the ACPI and APIC subsystems. INTERRUPT FLAGS Xen maintains its own separate flag for masking events, which is contained within the per-cpu vcpu_info structure. Because the guest kernel runs in ring 1 and not 0, the IF flag in EFLAGS is completely ignored (and must be, because even if a guest domain disables interrupts for itself, it can't disable them overall). (A note on terminology: "events" and interrupts are effectively synonymous. However, rather than using an "enable flag", Xen uses a "mask flag", which blocks event delivery when it is non-zero.) There are paravirt_ops for each of cli/sti/save_fl/restore_fl, which are implemented to manage the Xen event mask state. The only thing worth noting is that when events are unmasked, we need to explicitly see if there's a pending event and call into the hypervisor to make sure it gets delivered. UPCALLS Xen needs a couple of upcall (or callback) functions to be implemented by each guest. One is the event upcalls, which is how events (interrupts, effectively) are delivered to the guests. The other is the failsafe callback, which is used to report errors in either reloading a segment register, or caused by iret. These are implemented in i386/kernel/entry.S so they can jump into the normal iret_exc path when necessary. MULTICALL BATCHING Xen provides a multicall mechanism, which allows multiple hypercalls to be issued at once in order to mitigate the cost of trapping into the hypervisor. This is particularly useful for context switches, since the 4-5 hypercalls they would normally need (reload cr3, update TLS, maybe update LDT) can be reduced to one. This patch implements a generic batching mechanism for hypercalls, which gets used in many places in the Xen code. Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com> Signed-off-by: Chris Wright <chrisw@sous-sol.org> Cc: Ian Pratt <ian.pratt@xensource.com> Cc: Christian Limpach <Christian.Limpach@cl.cam.ac.uk> Cc: Adrian Bunk <bunk@stusta.de>
413 lines
11 KiB
C
413 lines
11 KiB
C
/******************************************************************************
|
|
* 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 __HYPERCALL_H__
|
|
#define __HYPERCALL_H__
|
|
|
|
#include <linux/errno.h>
|
|
#include <linux/string.h>
|
|
|
|
#include <xen/interface/xen.h>
|
|
#include <xen/interface/sched.h>
|
|
#include <xen/interface/physdev.h>
|
|
|
|
extern struct { char _entry[32]; } hypercall_page[];
|
|
|
|
#define _hypercall0(type, name) \
|
|
({ \
|
|
long __res; \
|
|
asm volatile ( \
|
|
"call %[call]" \
|
|
: "=a" (__res) \
|
|
: [call] "m" (hypercall_page[__HYPERVISOR_##name]) \
|
|
: "memory" ); \
|
|
(type)__res; \
|
|
})
|
|
|
|
#define _hypercall1(type, name, a1) \
|
|
({ \
|
|
long __res, __ign1; \
|
|
asm volatile ( \
|
|
"call %[call]" \
|
|
: "=a" (__res), "=b" (__ign1) \
|
|
: "1" ((long)(a1)), \
|
|
[call] "m" (hypercall_page[__HYPERVISOR_##name]) \
|
|
: "memory" ); \
|
|
(type)__res; \
|
|
})
|
|
|
|
#define _hypercall2(type, name, a1, a2) \
|
|
({ \
|
|
long __res, __ign1, __ign2; \
|
|
asm volatile ( \
|
|
"call %[call]" \
|
|
: "=a" (__res), "=b" (__ign1), "=c" (__ign2) \
|
|
: "1" ((long)(a1)), "2" ((long)(a2)), \
|
|
[call] "m" (hypercall_page[__HYPERVISOR_##name]) \
|
|
: "memory" ); \
|
|
(type)__res; \
|
|
})
|
|
|
|
#define _hypercall3(type, name, a1, a2, a3) \
|
|
({ \
|
|
long __res, __ign1, __ign2, __ign3; \
|
|
asm volatile ( \
|
|
"call %[call]" \
|
|
: "=a" (__res), "=b" (__ign1), "=c" (__ign2), \
|
|
"=d" (__ign3) \
|
|
: "1" ((long)(a1)), "2" ((long)(a2)), \
|
|
"3" ((long)(a3)), \
|
|
[call] "m" (hypercall_page[__HYPERVISOR_##name]) \
|
|
: "memory" ); \
|
|
(type)__res; \
|
|
})
|
|
|
|
#define _hypercall4(type, name, a1, a2, a3, a4) \
|
|
({ \
|
|
long __res, __ign1, __ign2, __ign3, __ign4; \
|
|
asm volatile ( \
|
|
"call %[call]" \
|
|
: "=a" (__res), "=b" (__ign1), "=c" (__ign2), \
|
|
"=d" (__ign3), "=S" (__ign4) \
|
|
: "1" ((long)(a1)), "2" ((long)(a2)), \
|
|
"3" ((long)(a3)), "4" ((long)(a4)), \
|
|
[call] "m" (hypercall_page[__HYPERVISOR_##name]) \
|
|
: "memory" ); \
|
|
(type)__res; \
|
|
})
|
|
|
|
#define _hypercall5(type, name, a1, a2, a3, a4, a5) \
|
|
({ \
|
|
long __res, __ign1, __ign2, __ign3, __ign4, __ign5; \
|
|
asm volatile ( \
|
|
"call %[call]" \
|
|
: "=a" (__res), "=b" (__ign1), "=c" (__ign2), \
|
|
"=d" (__ign3), "=S" (__ign4), "=D" (__ign5) \
|
|
: "1" ((long)(a1)), "2" ((long)(a2)), \
|
|
"3" ((long)(a3)), "4" ((long)(a4)), \
|
|
"5" ((long)(a5)), \
|
|
[call] "m" (hypercall_page[__HYPERVISOR_##name]) \
|
|
: "memory" ); \
|
|
(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);
|
|
}
|
|
|
|
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);
|
|
}
|
|
|
|
static inline int
|
|
HYPERVISOR_fpu_taskswitch(int set)
|
|
{
|
|
return _hypercall1(int, fpu_taskswitch, set);
|
|
}
|
|
|
|
static inline int
|
|
HYPERVISOR_sched_op(int cmd, unsigned long arg)
|
|
{
|
|
return _hypercall2(int, sched_op, 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)
|
|
{
|
|
unsigned long pte_hi = 0;
|
|
#ifdef CONFIG_X86_PAE
|
|
pte_hi = new_val.pte_high;
|
|
#endif
|
|
return _hypercall4(int, update_va_mapping, va,
|
|
new_val.pte_low, pte_hi, 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)
|
|
{
|
|
unsigned long pte_hi = 0;
|
|
#ifdef CONFIG_X86_PAE
|
|
pte_hi = new_val.pte_high;
|
|
#endif
|
|
return _hypercall5(int, update_va_mapping_otherdomain, va,
|
|
new_val.pte_low, pte_hi, 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);
|
|
}
|
|
|
|
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_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;
|
|
#ifdef CONFIG_X86_PAE
|
|
mcl->args[1] = new_val.pte_low;
|
|
mcl->args[2] = new_val.pte_high;
|
|
#else
|
|
mcl->args[1] = new_val.pte_low;
|
|
mcl->args[2] = 0;
|
|
#endif
|
|
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;
|
|
#ifdef CONFIG_X86_PAE
|
|
mcl->args[1] = new_val.pte_low;
|
|
mcl->args[2] = new_val.pte_high;
|
|
#else
|
|
mcl->args[1] = new_val.pte_low;
|
|
mcl->args[2] = 0;
|
|
#endif
|
|
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;
|
|
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 /* __HYPERCALL_H__ */
|