LM
/
u-boot
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

MLK-20373-1 Intrdouce xen header files 

Introduce xen header files from Linux Kernel commit
e2b623fbe6a3("Merge tag 's390-4.20-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux")

Signed-off-by: Peng Fan <peng.fan@nxp.com>
Reviewed-by: Peng Fan <peng.fan@nxp.com>
Reviewed-by: Flynn xu <flynn.xu@nxp.com>
This commit is contained in:
Peng Fan 2018-11-15 13:03:41 +08:00
parent da3f3a0816
commit ddb393c451
15 changed files with 3604 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

0
arch/arm/include/asm/xen/events.h Normal file
View File

66
arch/arm/include/asm/xen/hypercall.h Normal file
View File

@ -0,0 +1,66 @@
/******************************************************************************
* hypercall.h
*
* Linux-specific hypervisor handling.
*
* Stefano Stabellini <stefano.stabellini@eu.citrix.com>, Citrix, 2012
*
* 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_ARM_XEN_HYPERCALL_H
#define _ASM_ARM_XEN_HYPERCALL_H
#include <linux/bug.h>
#include <xen/interface/xen.h>
//#include <xen/interface/sched.h>
#include <xen/interface/platform.h>
struct xen_dm_op_buf;
long privcmd_call(unsigned call, unsigned long a1,
unsigned long a2, unsigned long a3,
unsigned long a4, unsigned long a5);
int HYPERVISOR_xen_version(int cmd, void *arg);
int HYPERVISOR_console_io(int cmd, int count, char *str);
int HYPERVISOR_grant_table_op(unsigned int cmd, void *uop, unsigned int count);
int HYPERVISOR_sched_op(int cmd, void *arg);
int HYPERVISOR_event_channel_op(int cmd, void *arg);
unsigned long HYPERVISOR_hvm_op(int op, void *arg);
int HYPERVISOR_memory_op(unsigned int cmd, void *arg);
int HYPERVISOR_physdev_op(int cmd, void *arg);
int HYPERVISOR_vcpu_op(int cmd, int vcpuid, void *extra_args);
int HYPERVISOR_tmem_op(void *arg);
int HYPERVISOR_vm_assist(unsigned int cmd, unsigned int type);
int HYPERVISOR_dm_op(domid_t domid, unsigned int nr_bufs,
struct xen_dm_op_buf *bufs);
int HYPERVISOR_platform_op_raw(void *arg);
static inline int HYPERVISOR_platform_op(struct xen_platform_op *op)
{
op->interface_version = XENPF_INTERFACE_VERSION;
return HYPERVISOR_platform_op_raw(op);
}
#endif /* _ASM_ARM_XEN_HYPERCALL_H */

86
arch/arm/include/asm/xen/interface.h Normal file
View File

@ -0,0 +1,86 @@
/* SPDX-License-Identifier: GPL-2.0 */
/******************************************************************************
* Guest OS interface to ARM Xen.
*
* Stefano Stabellini <stefano.stabellini@eu.citrix.com>, Citrix, 2012
*/
#ifndef _ASM_ARM_XEN_INTERFACE_H
#define _ASM_ARM_XEN_INTERFACE_H
#include <linux/types.h>
#define uint64_aligned_t uint64_t __attribute__((aligned(8)))
#define __DEFINE_GUEST_HANDLE(name, type) \
typedef struct { union { type *p; uint64_aligned_t q; }; } \
__guest_handle_ ## name
#define DEFINE_GUEST_HANDLE_STRUCT(name) \
__DEFINE_GUEST_HANDLE(name, struct name)
#define DEFINE_GUEST_HANDLE(name) __DEFINE_GUEST_HANDLE(name, name)
#define GUEST_HANDLE(name) __guest_handle_ ## name
#define set_xen_guest_handle(hnd, val) \
do { \
if (sizeof(hnd) == 8) \
*(uint64_t *)&(hnd) = 0; \
(hnd).p = val; \
} while (0)
#define __HYPERVISOR_platform_op_raw __HYPERVISOR_platform_op
#ifndef __ASSEMBLY__
/* Explicitly size integers that represent pfns in the interface with
* Xen so that we can have one ABI that works for 32 and 64 bit guests.
* Note that this means that the xen_pfn_t type may be capable of
* representing pfn's which the guest cannot represent in its own pfn
* type. However since pfn space is controlled by the guest this is
* fine since it simply wouldn't be able to create any sure pfns in
* the first place.
*/
typedef uint64_t xen_pfn_t;
#define PRI_xen_pfn "llx"
typedef uint64_t xen_ulong_t;
#define PRI_xen_ulong "llx"
typedef int64_t xen_long_t;
#define PRI_xen_long "llx"
/* Guest handles for primitive C types. */
__DEFINE_GUEST_HANDLE(uchar, unsigned char);
__DEFINE_GUEST_HANDLE(uint, unsigned int);
DEFINE_GUEST_HANDLE(char);
DEFINE_GUEST_HANDLE(int);
DEFINE_GUEST_HANDLE(void);
DEFINE_GUEST_HANDLE(uint64_t);
DEFINE_GUEST_HANDLE(uint32_t);
DEFINE_GUEST_HANDLE(xen_pfn_t);
DEFINE_GUEST_HANDLE(xen_ulong_t);
/* Maximum number of virtual CPUs in multi-processor guests. */
#define MAX_VIRT_CPUS 1
struct arch_vcpu_info { };
struct arch_shared_info { };
/* TODO: Move pvclock definitions some place arch independent */
struct pvclock_vcpu_time_info {
u32 version;
u32 pad0;
u64 tsc_timestamp;
u64 system_time;
u32 tsc_to_system_mul;
s8 tsc_shift;
u8 flags;
u8 pad[2];
} __attribute__((__packed__)); /* 32 bytes */
/* It is OK to have a 12 bytes struct with no padding because it is packed */
struct pvclock_wall_clock {
u32 version;
u32 sec;
u32 nsec;
u32 sec_hi;
} __attribute__((__packed__));
#endif
#endif /* _ASM_ARM_XEN_INTERFACE_H */

385
include/xen/event_channel.h Normal file
View File

@ -0,0 +1,385 @@
/******************************************************************************
* event_channel.h
*
* Event channels between domains.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*
* Copyright (c) 2003-2004, K A Fraser.
*/
#ifndef __XEN_PUBLIC_EVENT_CHANNEL_H__
#define __XEN_PUBLIC_EVENT_CHANNEL_H__
#include "xen.h"
/*
* `incontents 150 evtchn Event Channels
*
* Event channels are the basic primitive provided by Xen for event
* notifications. An event is the Xen equivalent of a hardware
* interrupt. They essentially store one bit of information, the event
* of interest is signalled by transitioning this bit from 0 to 1.
*
* Notifications are received by a guest via an upcall from Xen,
* indicating when an event arrives (setting the bit). Further
* notifications are masked until the bit is cleared again (therefore,
* guests must check the value of the bit after re-enabling event
* delivery to ensure no missed notifications).
*
* Event notifications can be masked by setting a flag; this is
* equivalent to disabling interrupts and can be used to ensure
* atomicity of certain operations in the guest kernel.
*
* Event channels are represented by the evtchn_* fields in
* struct shared_info and struct vcpu_info.
*/
/*
* ` enum neg_errnoval
* ` HYPERVISOR_event_channel_op(enum event_channel_op cmd, void *args)
* `
* @cmd == EVTCHNOP_* (event-channel operation).
* @args == struct evtchn_* Operation-specific extra arguments (NULL if none).
*/
/* ` enum event_channel_op { // EVTCHNOP_* => struct evtchn_* */
#define EVTCHNOP_bind_interdomain 0
#define EVTCHNOP_bind_virq 1
#define EVTCHNOP_bind_pirq 2
#define EVTCHNOP_close 3
#define EVTCHNOP_send 4
#define EVTCHNOP_status 5
#define EVTCHNOP_alloc_unbound 6
#define EVTCHNOP_bind_ipi 7
#define EVTCHNOP_bind_vcpu 8
#define EVTCHNOP_unmask 9
#define EVTCHNOP_reset 10
#define EVTCHNOP_init_control 11
#define EVTCHNOP_expand_array 12
#define EVTCHNOP_set_priority 13
/* ` } */
typedef uint32_t evtchn_port_t;
DEFINE_XEN_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. <remote_dom> may be DOMID_SELF, allowing loopback connections.
*/
struct evtchn_alloc_unbound {
/* IN parameters */
domid_t dom, remote_dom;
/* OUT parameters */
evtchn_port_t port;
};
typedef struct evtchn_alloc_unbound evtchn_alloc_unbound_t;
/*
* 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>.
*
* In case the peer domain has already tried to set our event channel
* pending, before it was bound, EVTCHNOP_bind_interdomain always sets
* the local event channel pending.
*
* The usual pattern of use, in the guest's upcall (or subsequent
* handler) is as follows: (Re-enable the event channel for subsequent
* signalling and then) check for the existence of whatever condition
* is being waited for by other means, and take whatever action is
* needed (if any).
*
* NOTES:
* 1. <remote_dom> may be DOMID_SELF, allowing loopback connections.
*/
struct evtchn_bind_interdomain {
/* IN parameters. */
domid_t remote_dom;
evtchn_port_t remote_port;
/* OUT parameters. */
evtchn_port_t local_port;
};
typedef struct evtchn_bind_interdomain evtchn_bind_interdomain_t;
/*
* EVTCHNOP_bind_virq: Bind a local event channel to VIRQ <irq> on specified
* vcpu.
* NOTES:
* 1. Virtual IRQs are classified as per-vcpu or global. See the VIRQ list
* in xen.h for the classification of each VIRQ.
* 2. Global VIRQs must be allocated on VCPU0 but can subsequently be
* re-bound via EVTCHNOP_bind_vcpu.
* 3. Per-vcpu VIRQs may be bound to at most one event channel per vcpu.
* The allocated event channel is bound to the specified vcpu and the
* binding cannot be changed.
*/
struct evtchn_bind_virq {
/* IN parameters. */
uint32_t virq; /* enum virq */
uint32_t vcpu;
/* OUT parameters. */
evtchn_port_t port;
};
typedef struct evtchn_bind_virq evtchn_bind_virq_t;
/*
* EVTCHNOP_bind_pirq: Bind a local event channel to a real IRQ (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.
*/
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;
};
typedef struct evtchn_bind_pirq evtchn_bind_pirq_t;
/*
* 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.
*/
struct evtchn_bind_ipi {
uint32_t vcpu;
/* OUT parameters. */
evtchn_port_t port;
};
typedef struct evtchn_bind_ipi evtchn_bind_ipi_t;
/*
* 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.
*/
struct evtchn_close {
/* IN parameters. */
evtchn_port_t port;
};
typedef struct evtchn_close evtchn_close_t;
/*
* EVTCHNOP_send: Send an event to the remote end of the channel whose local
* endpoint is <port>.
*/
struct evtchn_send {
/* IN parameters. */
evtchn_port_t port;
};
typedef struct evtchn_send evtchn_send_t;
/*
* 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.
*/
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;
};
typedef struct evtchn_status evtchn_status_t;
/*
* EVTCHNOP_bind_vcpu: Specify which vcpu a channel should notify when an
* event is pending.
* NOTES:
* 1. IPI-bound channels always notify the vcpu specified at bind time.
* This binding cannot be changed.
* 2. Per-VCPU VIRQ channels always notify the vcpu specified at bind time.
* This binding cannot be changed.
* 3. 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).
*/
struct evtchn_bind_vcpu {
/* IN parameters. */
evtchn_port_t port;
uint32_t vcpu;
};
typedef struct evtchn_bind_vcpu evtchn_bind_vcpu_t;
/*
* EVTCHNOP_unmask: Unmask the specified local event-channel port and deliver
* a notification to the appropriate VCPU if an event is pending.
*/
struct evtchn_unmask {
/* IN parameters. */
evtchn_port_t port;
};
typedef struct evtchn_unmask evtchn_unmask_t;
/*
* EVTCHNOP_reset: Close all event channels associated with specified domain.
* NOTES:
* 1. <dom> may be specified as DOMID_SELF.
* 2. Only a sufficiently-privileged domain may specify other than DOMID_SELF.
* 3. Destroys all control blocks and event array, resets event channel
* operations to 2-level ABI if called with <dom> == DOMID_SELF and FIFO
* ABI was used. Guests should not bind events during EVTCHNOP_reset call
* as these events are likely to be lost.
*/
struct evtchn_reset {
/* IN parameters. */
domid_t dom;
};
typedef struct evtchn_reset evtchn_reset_t;
/*
* EVTCHNOP_init_control: initialize the control block for the FIFO ABI.
*
* Note: any events that are currently pending will not be resent and
* will be lost. Guests should call this before binding any event to
* avoid losing any events.
*/
struct evtchn_init_control {
/* IN parameters. */
uint64_t control_gfn;
uint32_t offset;
uint32_t vcpu;
/* OUT parameters. */
uint8_t link_bits;
uint8_t _pad[7];
};
typedef struct evtchn_init_control evtchn_init_control_t;
/*
* EVTCHNOP_expand_array: add an additional page to the event array.
*/
struct evtchn_expand_array {
/* IN parameters. */
uint64_t array_gfn;
};
typedef struct evtchn_expand_array evtchn_expand_array_t;
/*
* EVTCHNOP_set_priority: set the priority for an event channel.
*/
struct evtchn_set_priority {
/* IN parameters. */
uint32_t port;
uint32_t priority;
};
typedef struct evtchn_set_priority evtchn_set_priority_t;
/*
* ` enum neg_errnoval
* ` HYPERVISOR_event_channel_op_compat(struct evtchn_op *op)
* `
* Superceded by new event_channel_op() hypercall since 0x00030202.
*/
struct evtchn_op {
uint32_t cmd; /* enum event_channel_op */
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;
};
typedef struct evtchn_op evtchn_op_t;
DEFINE_XEN_GUEST_HANDLE(evtchn_op_t);
/*
* 2-level ABI
*/
#define EVTCHN_2L_NR_CHANNELS (sizeof(xen_ulong_t) * sizeof(xen_ulong_t) * 64)
/*
* FIFO ABI
*/
/* Events may have priorities from 0 (highest) to 15 (lowest). */
#define EVTCHN_FIFO_PRIORITY_MAX 0
#define EVTCHN_FIFO_PRIORITY_DEFAULT 7
#define EVTCHN_FIFO_PRIORITY_MIN 15
#define EVTCHN_FIFO_MAX_QUEUES (EVTCHN_FIFO_PRIORITY_MIN + 1)
typedef uint32_t event_word_t;
#define EVTCHN_FIFO_PENDING 31
#define EVTCHN_FIFO_MASKED 30
#define EVTCHN_FIFO_LINKED 29
#define EVTCHN_FIFO_BUSY 28
#define EVTCHN_FIFO_LINK_BITS 17
#define EVTCHN_FIFO_LINK_MASK ((1 << EVTCHN_FIFO_LINK_BITS) - 1)
#define EVTCHN_FIFO_NR_CHANNELS (1 << EVTCHN_FIFO_LINK_BITS)
struct evtchn_fifo_control_block {
uint32_t ready;
uint32_t _rsvd;
uint32_t head[EVTCHN_FIFO_MAX_QUEUES];
};
typedef struct evtchn_fifo_control_block evtchn_fifo_control_block_t;
#endif /* __XEN_PUBLIC_EVENT_CHANNEL_H__ */
/*
* Local variables:
* mode: C
* c-file-style: "BSD"
* c-basic-offset: 4
* tab-width: 4
* indent-tabs-mode: nil
* End:
*/

15
include/xen/events.h Normal file
View File

@ -0,0 +1,15 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _XEN_EVENTS_H
#define _XEN_EVENTS_H
#include <xen/interface/event_channel.h>
#include <asm/xen/hypercall.h>
#include <asm/xen/events.h>
static inline void notify_remote_via_evtchn(int port)
{
struct evtchn_send send = { .port = port };
(void)HYPERVISOR_event_channel_op(EVTCHNOP_send, &send);
}
#endif /* _XEN_EVENTS_H */

61
include/xen/hvm.h Normal file
View File

@ -0,0 +1,61 @@
/* SPDX-License-Identifier: GPL-2.0 */
/* Simple wrappers around HVM functions */
#ifndef XEN_HVM_H__
#define XEN_HVM_H__
#include <xen/interface/hvm/params.h>
#include <asm/xen/hypercall.h>
static const char *param_name(int op)
{
#define PARAM(x) [HVM_PARAM_##x] = #x
static const char *const names[] = {
PARAM(CALLBACK_IRQ),
PARAM(STORE_PFN),
PARAM(STORE_EVTCHN),
PARAM(PAE_ENABLED),
PARAM(IOREQ_PFN),
PARAM(BUFIOREQ_PFN),
PARAM(TIMER_MODE),
PARAM(HPET_ENABLED),
PARAM(IDENT_PT),
PARAM(DM_DOMAIN),
PARAM(ACPI_S_STATE),
PARAM(VM86_TSS),
PARAM(VPT_ALIGN),
PARAM(CONSOLE_PFN),
PARAM(CONSOLE_EVTCHN),
};
#undef PARAM
if (op >= ARRAY_SIZE(names))
return "unknown";
if (!names[op])
return "reserved";
return names[op];
}
static inline int hvm_get_parameter(int idx, uint64_t *value)
{
struct xen_hvm_param xhv;
int r;
xhv.domid = DOMID_SELF;
xhv.index = idx;
r = HYPERVISOR_hvm_op(HVMOP_get_param, &xhv);
if (r < 0) {
pr_err("Cannot get hvm parameter %s (%d): %d!\n",
param_name(idx), idx, r);
return r;
}
*value = xhv.value;
return r;
}
#define HVM_CALLBACK_VIA_TYPE_VECTOR 0x2
#define HVM_CALLBACK_VIA_TYPE_SHIFT 56
#define HVM_CALLBACK_VECTOR(x) (((uint64_t)HVM_CALLBACK_VIA_TYPE_VECTOR)<<\
HVM_CALLBACK_VIA_TYPE_SHIFT | (x))
#endif /* XEN_HVM_H__ */

279
include/xen/interface/event_channel.h Normal file
View File

@ -0,0 +1,279 @@
/* SPDX-License-Identifier: GPL-2.0 */
/******************************************************************************
* 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;
};
/*
* EVTCHNOP_reset: Close all event channels associated with specified domain.
* NOTES:
* 1. <dom> may be specified as DOMID_SELF.
* 2. Only a sufficiently-privileged domain may specify other than DOMID_SELF.
*/
#define EVTCHNOP_reset 10
struct evtchn_reset {
/* IN parameters. */
domid_t dom;
};
typedef struct evtchn_reset evtchn_reset_t;
/*
* EVTCHNOP_init_control: initialize the control block for the FIFO ABI.
*/
#define EVTCHNOP_init_control 11
struct evtchn_init_control {
/* IN parameters. */
uint64_t control_gfn;
uint32_t offset;
uint32_t vcpu;
/* OUT parameters. */
uint8_t link_bits;
uint8_t _pad[7];
};
/*
* EVTCHNOP_expand_array: add an additional page to the event array.
*/
#define EVTCHNOP_expand_array 12
struct evtchn_expand_array {
/* IN parameters. */
uint64_t array_gfn;
};
/*
* EVTCHNOP_set_priority: set the priority for an event channel.
*/
#define EVTCHNOP_set_priority 13
struct evtchn_set_priority {
/* IN parameters. */
uint32_t port;
uint32_t priority;
};
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);
/*
* 2-level ABI
*/
#define EVTCHN_2L_NR_CHANNELS (sizeof(xen_ulong_t) * sizeof(xen_ulong_t) * 64)
/*
* FIFO ABI
*/
/* Events may have priorities from 0 (highest) to 15 (lowest). */
#define EVTCHN_FIFO_PRIORITY_MAX 0
#define EVTCHN_FIFO_PRIORITY_DEFAULT 7
#define EVTCHN_FIFO_PRIORITY_MIN 15
#define EVTCHN_FIFO_MAX_QUEUES (EVTCHN_FIFO_PRIORITY_MIN + 1)
typedef uint32_t event_word_t;
#define EVTCHN_FIFO_PENDING 31
#define EVTCHN_FIFO_MASKED 30
#define EVTCHN_FIFO_LINKED 29
#define EVTCHN_FIFO_BUSY 28
#define EVTCHN_FIFO_LINK_BITS 17
#define EVTCHN_FIFO_LINK_MASK ((1 << EVTCHN_FIFO_LINK_BITS) - 1)
#define EVTCHN_FIFO_NR_CHANNELS (1 << EVTCHN_FIFO_LINK_BITS)
struct evtchn_fifo_control_block {
uint32_t ready;
uint32_t _rsvd;
event_word_t head[EVTCHN_FIFO_MAX_QUEUES];
};
#endif /* __XEN_PUBLIC_EVENT_CHANNEL_H__ */

568
include/xen/interface/grant_table.h Normal file
View File

@ -0,0 +1,568 @@
/******************************************************************************
* grant_table.h
*
* Interface for granting foreign access to page frames, and receiving
* page-ownership transfers.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*
* Copyright (c) 2004, K A Fraser
*/
#ifndef __XEN_PUBLIC_GRANT_TABLE_H__
#define __XEN_PUBLIC_GRANT_TABLE_H__
#include <xen/interface/xen.h>
/***********************************
* GRANT TABLE REPRESENTATION
*/
/* Some rough guidelines on accessing and updating grant-table entries
* in a concurrency-safe manner. For more information, Linux contains a
* reference implementation for guest OSes (arch/xen/kernel/grant_table.c).
*
* NB. WMB is a no-op on current-generation x86 processors. However, a
* compiler barrier will still be required.
*
* 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.
*
* Invalidating an unused GTF_permit_access entry:
* 1. flags = ent->flags.
* 2. Observe that !(flags & (GTF_reading|GTF_writing)).
* 3. Check result of SMP-safe CMPXCHG(&ent->flags, flags, 0).
* NB. No need for WMB as reuse of entry is control-dependent on success of
* step 3, and all architectures guarantee ordering of ctrl-dep writes.
*
* Invalidating an in-use GTF_permit_access entry:
* This cannot be done directly. Request assistance from the domain controller
* which can set a timeout on the use of a grant entry and take necessary
* action. (NB. This is not yet implemented!).
*
* Invalidating an unused GTF_accept_transfer entry:
* 1. flags = ent->flags.
* 2. Observe that !(flags & GTF_transfer_committed). [*]
* 3. Check result of SMP-safe CMPXCHG(&ent->flags, flags, 0).
* NB. No need for WMB as reuse of entry is control-dependent on success of
* step 3, and all architectures guarantee ordering of ctrl-dep writes.
* [*] If GTF_transfer_committed is set then the grant entry is 'committed'.
* The guest must /not/ modify the grant entry until the address of the
* transferred frame is written. It is safe for the guest to spin waiting
* for this to occur (detect by observing GTF_transfer_completed in
* ent->flags).
*
* Invalidating a committed GTF_accept_transfer entry:
* 1. Wait for (ent->flags & GTF_transfer_completed).
*
* Changing a GTF_permit_access from writable to read-only:
* Use SMP-safe CMPXCHG to set GTF_readonly, while checking !GTF_writing.
*
* Changing a GTF_permit_access from read-only to writable:
* Use SMP-safe bit-setting instruction.
*/
/*
* Reference to a grant entry in a specified domain's grant table.
*/
typedef uint32_t grant_ref_t;
/*
* A grant table comprises a packed array of grant entries in one or more
* page frames shared between Xen and a guest.
* [XEN]: This field is written by Xen and read by the sharing guest.
* [GST]: This field is written by the guest and read by Xen.
*/
/*
* Version 1 of the grant table entry structure is maintained purely
* for backwards compatibility. New guests should use version 2.
*/
struct grant_entry_v1 {
/* GTF_xxx: various type and flag information. [XEN,GST] */
uint16_t flags;
/* The domain being granted foreign privileges. [GST] */
domid_t domid;
/*
* GTF_permit_access: Frame that @domid is allowed to map and access. [GST]
* GTF_accept_transfer: Frame whose ownership transferred by @domid. [XEN]
*/
uint32_t frame;
};
/*
* Type of grant entry.
* GTF_invalid: This grant entry grants no privileges.
* GTF_permit_access: Allow @domid to map/access @frame.
* GTF_accept_transfer: Allow @domid to transfer ownership of one page frame
* to this guest. Xen writes the page number to @frame.
* GTF_transitive: Allow @domid to transitively access a subrange of
* @trans_grant in @trans_domid. No mappings are allowed.
*/
#define GTF_invalid (0U<<0)
#define GTF_permit_access (1U<<0)
#define GTF_accept_transfer (2U<<0)
#define GTF_transitive (3U<<0)
#define GTF_type_mask (3U<<0)
/*
* Subflags for GTF_permit_access.
* GTF_readonly: Restrict @domid to read-only mappings and accesses. [GST]
* GTF_reading: Grant entry is currently mapped for reading by @domid. [XEN]
* GTF_writing: Grant entry is currently mapped for writing by @domid. [XEN]
* GTF_sub_page: Grant access to only a subrange of the page. @domid
* will only be allowed to copy from the grant, and not
* map it. [GST]
*/
#define _GTF_readonly (2)
#define GTF_readonly (1U<<_GTF_readonly)
#define _GTF_reading (3)
#define GTF_reading (1U<<_GTF_reading)
#define _GTF_writing (4)
#define GTF_writing (1U<<_GTF_writing)
#define _GTF_sub_page (8)
#define GTF_sub_page (1U<<_GTF_sub_page)
/*
* Subflags for GTF_accept_transfer:
* GTF_transfer_committed: Xen sets this flag to indicate that it is committed
* to transferring ownership of a page frame. When a guest sees this flag
* it must /not/ modify the grant entry until GTF_transfer_completed is
* set by Xen.
* GTF_transfer_completed: It is safe for the guest to spin-wait on this flag
* after reading GTF_transfer_committed. Xen will always write the frame
* address, followed by ORing this flag, in a timely manner.
*/
#define _GTF_transfer_committed (2)
#define GTF_transfer_committed (1U<<_GTF_transfer_committed)
#define _GTF_transfer_completed (3)
#define GTF_transfer_completed (1U<<_GTF_transfer_completed)
/*
* Version 2 grant table entries. These fulfil the same role as
* version 1 entries, but can represent more complicated operations.
* Any given domain will have either a version 1 or a version 2 table,
* and every entry in the table will be the same version.
*
* The interface by which domains use grant references does not depend
* on the grant table version in use by the other domain.
*/
/*
* Version 1 and version 2 grant entries share a common prefix. The
* fields of the prefix are documented as part of struct
* grant_entry_v1.
*/
struct grant_entry_header {
uint16_t flags;
domid_t domid;
};
/*
* Version 2 of the grant entry structure, here is a union because three
* different types are suppotted: full_page, sub_page and transitive.
*/
union grant_entry_v2 {
struct grant_entry_header hdr;
/*
* This member is used for V1-style full page grants, where either:
*
* -- hdr.type is GTF_accept_transfer, or
* -- hdr.type is GTF_permit_access and GTF_sub_page is not set.
*
* In that case, the frame field has the same semantics as the
* field of the same name in the V1 entry structure.
*/
struct {
struct grant_entry_header hdr;
uint32_t pad0;
uint64_t frame;
} full_page;
/*
* If the grant type is GTF_grant_access and GTF_sub_page is set,
* @domid is allowed to access bytes [@page_off,@page_off+@length)
* in frame @frame.
*/
struct {
struct grant_entry_header hdr;
uint16_t page_off;
uint16_t length;
uint64_t frame;
} sub_page;
/*
* If the grant is GTF_transitive, @domid is allowed to use the
* grant @gref in domain @trans_domid, as if it was the local
* domain. Obviously, the transitive access must be compatible
* with the original grant.
*/
struct {
struct grant_entry_header hdr;
domid_t trans_domid;
uint16_t pad0;
grant_ref_t gref;
} transitive;
uint32_t __spacer[4]; /* Pad to a power of two */
};
typedef uint16_t grant_status_t;
/***********************************
* GRANT TABLE QUERIES AND USES
*/
/*
* Handle to track a mapping created via a grant reference.
*/
typedef uint32_t grant_handle_t;
/*
* GNTTABOP_map_grant_ref: Map the grant entry (<dom>,<ref>) for access
* by devices and/or host CPUs. If successful, <handle> is a tracking number
* that must be presented later to destroy the mapping(s). On error, <handle>
* is a negative status code.
* NOTES:
* 1. If GNTMAP_device_map is specified then <dev_bus_addr> is the address
* via which I/O devices may access the granted frame.
* 2. If GNTMAP_host_map is specified then a mapping will be added at
* either a host virtual address in the current address space, or at
* a PTE at the specified machine address. The type of mapping to
* perform is selected through the GNTMAP_contains_pte flag, and the
* address is specified in <host_addr>.
* 3. Mappings should only be destroyed via GNTTABOP_unmap_grant_ref. If a
* host mapping is destroyed by other means then it is *NOT* guaranteed
* to be accounted to the correct grant reference!
*/
#define GNTTABOP_map_grant_ref 0
struct gnttab_map_grant_ref {
/* IN parameters. */
uint64_t host_addr;
uint32_t flags; /* GNTMAP_* */
grant_ref_t ref;
domid_t dom;
/* OUT parameters. */
int16_t status; /* GNTST_* */
grant_handle_t handle;
uint64_t dev_bus_addr;
};
DEFINE_GUEST_HANDLE_STRUCT(gnttab_map_grant_ref);
/*
* GNTTABOP_unmap_grant_ref: Destroy one or more grant-reference mappings
* tracked by <handle>. If <host_addr> or <dev_bus_addr> is zero, that
* field is ignored. If non-zero, they must refer to a device/host mapping
* that is tracked by <handle>
* NOTES:
* 1. The call may fail in an undefined manner if either mapping is not
* tracked by <handle>.
* 3. After executing a batch of unmaps, it is guaranteed that no stale
* mappings will remain in the device or host TLBs.
*/
#define GNTTABOP_unmap_grant_ref 1
struct gnttab_unmap_grant_ref {
/* IN parameters. */
uint64_t host_addr;
uint64_t dev_bus_addr;
grant_handle_t handle;
/* OUT parameters. */
int16_t status; /* GNTST_* */
};
DEFINE_GUEST_HANDLE_STRUCT(gnttab_unmap_grant_ref);
/*
* GNTTABOP_setup_table: Set up a grant table for <dom> comprising at least
* <nr_frames> pages. The frame addresses are written to the <frame_list>.
* Only <nr_frames> addresses are written, even if the table is larger.
* NOTES:
* 1. <dom> may be specified as DOMID_SELF.
* 2. Only a sufficiently-privileged domain may specify <dom> != DOMID_SELF.
* 3. Xen may not support more than a single grant-table page per domain.
*/
#define GNTTABOP_setup_table 2
struct gnttab_setup_table {
/* IN parameters. */
domid_t dom;
uint32_t nr_frames;
/* OUT parameters. */
int16_t status; /* GNTST_* */
GUEST_HANDLE(xen_pfn_t) frame_list;
};
DEFINE_GUEST_HANDLE_STRUCT(gnttab_setup_table);
/*
* GNTTABOP_dump_table: Dump the contents of the grant table to the
* xen console. Debugging use only.
*/
#define GNTTABOP_dump_table 3
struct gnttab_dump_table {
/* IN parameters. */
domid_t dom;
/* OUT parameters. */
int16_t status; /* GNTST_* */
};
DEFINE_GUEST_HANDLE_STRUCT(gnttab_dump_table);
/*
* GNTTABOP_transfer_grant_ref: Transfer <frame> to a foreign domain. The
* foreign domain has previously registered its interest in the transfer via
* <domid, ref>.
*
* Note that, even if the transfer fails, the specified page no longer belongs
* to the calling domain *unless* the error is GNTST_bad_page.
*/
#define GNTTABOP_transfer 4
struct gnttab_transfer {
/* IN parameters. */
xen_pfn_t mfn;
domid_t domid;
grant_ref_t ref;
/* OUT parameters. */
int16_t status;
};
DEFINE_GUEST_HANDLE_STRUCT(gnttab_transfer);
/*
* GNTTABOP_copy: Hypervisor based copy
* source and destinations can be eithers MFNs or, for foreign domains,
* grant references. the foreign domain has to grant read/write access
* in its grant table.
*
* The flags specify what type source and destinations are (either MFN
* or grant reference).
*
* Note that this can also be used to copy data between two domains
* via a third party if the source and destination domains had previously
* grant appropriate access to their pages to the third party.
*
* source_offset specifies an offset in the source frame, dest_offset
* the offset in the target frame and len specifies the number of
* bytes to be copied.
*/
#define _GNTCOPY_source_gref (0)
#define GNTCOPY_source_gref (1<<_GNTCOPY_source_gref)
#define _GNTCOPY_dest_gref (1)
#define GNTCOPY_dest_gref (1<<_GNTCOPY_dest_gref)
#define GNTTABOP_copy 5
struct gnttab_copy {
/* IN parameters. */
struct {
union {
grant_ref_t ref;
xen_pfn_t gmfn;
} u;
domid_t domid;
uint16_t offset;
} source, dest;
uint16_t len;
uint16_t flags; /* GNTCOPY_* */
/* OUT parameters. */
int16_t status;
};
DEFINE_GUEST_HANDLE_STRUCT(gnttab_copy);
/*
* GNTTABOP_query_size: Query the current and maximum sizes of the shared
* grant table.
* NOTES:
* 1. <dom> may be specified as DOMID_SELF.
* 2. Only a sufficiently-privileged domain may specify <dom> != DOMID_SELF.
*/
#define GNTTABOP_query_size 6
struct gnttab_query_size {
/* IN parameters. */
domid_t dom;
/* OUT parameters. */
uint32_t nr_frames;
uint32_t max_nr_frames;
int16_t status; /* GNTST_* */
};
DEFINE_GUEST_HANDLE_STRUCT(gnttab_query_size);
/*
* GNTTABOP_unmap_and_replace: Destroy one or more grant-reference mappings
* tracked by <handle> but atomically replace the page table entry with one
* pointing to the machine address under <new_addr>. <new_addr> will be
* redirected to the null entry.
* NOTES:
* 1. The call may fail in an undefined manner if either mapping is not
* tracked by <handle>.
* 2. After executing a batch of unmaps, it is guaranteed that no stale
* mappings will remain in the device or host TLBs.
*/
#define GNTTABOP_unmap_and_replace 7
struct gnttab_unmap_and_replace {
/* IN parameters. */
uint64_t host_addr;
uint64_t new_addr;
grant_handle_t handle;
/* OUT parameters. */
int16_t status; /* GNTST_* */
};
DEFINE_GUEST_HANDLE_STRUCT(gnttab_unmap_and_replace);
/*
* GNTTABOP_set_version: Request a particular version of the grant
* table shared table structure. This operation can only be performed
* once in any given domain. It must be performed before any grants
* are activated; otherwise, the domain will be stuck with version 1.
* The only defined versions are 1 and 2.
*/
#define GNTTABOP_set_version 8
struct gnttab_set_version {
/* IN parameters */
uint32_t version;
};
DEFINE_GUEST_HANDLE_STRUCT(gnttab_set_version);
/*
* GNTTABOP_get_status_frames: Get the list of frames used to store grant
* status for <dom>. In grant format version 2, the status is separated
* from the other shared grant fields to allow more efficient synchronization
* using barriers instead of atomic cmpexch operations.
* <nr_frames> specify the size of vector <frame_list>.
* The frame addresses are returned in the <frame_list>.
* Only <nr_frames> addresses are returned, even if the table is larger.
* NOTES:
* 1. <dom> may be specified as DOMID_SELF.
* 2. Only a sufficiently-privileged domain may specify <dom> != DOMID_SELF.
*/
#define GNTTABOP_get_status_frames 9
struct gnttab_get_status_frames {
/* IN parameters. */
uint32_t nr_frames;
domid_t dom;
/* OUT parameters. */
int16_t status; /* GNTST_* */
GUEST_HANDLE(uint64_t) frame_list;
};
DEFINE_GUEST_HANDLE_STRUCT(gnttab_get_status_frames);
/*
* GNTTABOP_get_version: Get the grant table version which is in
* effect for domain <dom>.
*/
#define GNTTABOP_get_version 10
struct gnttab_get_version {
/* IN parameters */
domid_t dom;
uint16_t pad;
/* OUT parameters */
uint32_t version;
};
DEFINE_GUEST_HANDLE_STRUCT(gnttab_get_version);
/*
* Issue one or more cache maintenance operations on a portion of a
* page granted to the calling domain by a foreign domain.
*/
#define GNTTABOP_cache_flush 12
struct gnttab_cache_flush {
union {
uint64_t dev_bus_addr;
grant_ref_t ref;
} a;
uint16_t offset; /* offset from start of grant */
uint16_t length; /* size within the grant */
#define GNTTAB_CACHE_CLEAN (1<<0)
#define GNTTAB_CACHE_INVAL (1<<1)
#define GNTTAB_CACHE_SOURCE_GREF (1<<31)
uint32_t op;
};
DEFINE_GUEST_HANDLE_STRUCT(gnttab_cache_flush);
/*
* Bitfield values for update_pin_status.flags.
*/
/* Map the grant entry for access by I/O devices. */
#define _GNTMAP_device_map (0)
#define GNTMAP_device_map (1<<_GNTMAP_device_map)
/* Map the grant entry for access by host CPUs. */
#define _GNTMAP_host_map (1)
#define GNTMAP_host_map (1<<_GNTMAP_host_map)
/* Accesses to the granted frame will be restricted to read-only access. */
#define _GNTMAP_readonly (2)
#define GNTMAP_readonly (1<<_GNTMAP_readonly)
/*
* GNTMAP_host_map subflag:
* 0 => The host mapping is usable only by the guest OS.
* 1 => The host mapping is usable by guest OS + current application.
*/
#define _GNTMAP_application_map (3)
#define GNTMAP_application_map (1<<_GNTMAP_application_map)
/*
* GNTMAP_contains_pte subflag:
* 0 => This map request contains a host virtual address.
* 1 => This map request contains the machine addess of the PTE to update.
*/
#define _GNTMAP_contains_pte (4)
#define GNTMAP_contains_pte (1<<_GNTMAP_contains_pte)
/*
* Bits to be placed in guest kernel available PTE bits (architecture
* dependent; only supported when XENFEAT_gnttab_map_avail_bits is set).
*/
#define _GNTMAP_guest_avail0 (16)
#define GNTMAP_guest_avail_mask ((uint32_t)~0 << _GNTMAP_guest_avail0)
/*
* Values for error status returns. All errors are -ve.
*/
#define GNTST_okay (0) /* Normal return. */
#define GNTST_general_error (-1) /* General undefined error. */
#define GNTST_bad_domain (-2) /* Unrecognsed domain id. */
#define GNTST_bad_gntref (-3) /* Unrecognised or inappropriate gntref. */
#define GNTST_bad_handle (-4) /* Unrecognised or inappropriate handle. */
#define GNTST_bad_virt_addr (-5) /* Inappropriate virtual address to map. */
#define GNTST_bad_dev_addr (-6) /* Inappropriate device address to unmap.*/
#define GNTST_no_device_space (-7) /* Out of space in I/O MMU. */
#define GNTST_permission_denied (-8) /* Not enough privilege for operation. */
#define GNTST_bad_page (-9) /* Specified page was invalid for op. */
#define GNTST_bad_copy_arg (-10) /* copy arguments cross page boundary. */
#define GNTST_address_too_big (-11) /* transfer page address too large. */
#define GNTST_eagain (-12) /* Operation not done; try again. */
#define GNTTABOP_error_msgs { \
"okay", \
"undefined error", \
"unrecognised domain id", \
"invalid grant reference", \
"invalid mapping handle", \
"invalid virtual address", \
"invalid device address", \
"no spare translation slot in the I/O MMU", \
"permission denied", \
"bad page", \
"copy arguments cross page boundary", \
"page address size too large", \
"operation not done; try again" \
}
#endif /* __XEN_PUBLIC_GRANT_TABLE_H__ */

65
include/xen/interface/hvm/hvm_op.h Normal file
View File

@ -0,0 +1,65 @@
/*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*/
#ifndef __XEN_PUBLIC_HVM_HVM_OP_H__
#define __XEN_PUBLIC_HVM_HVM_OP_H__
/* Get/set subcommands: the second argument of the hypercall is a
* pointer to a xen_hvm_param struct. */
#define HVMOP_set_param 0
#define HVMOP_get_param 1
struct xen_hvm_param {
domid_t domid; /* IN */
uint32_t index; /* IN */
uint64_t value; /* IN/OUT */
};
DEFINE_GUEST_HANDLE_STRUCT(xen_hvm_param);
/* Hint from PV drivers for pagetable destruction. */
#define HVMOP_pagetable_dying 9
struct xen_hvm_pagetable_dying {
/* Domain with a pagetable about to be destroyed. */
domid_t domid;
/* guest physical address of the toplevel pagetable dying */
aligned_u64 gpa;
};
typedef struct xen_hvm_pagetable_dying xen_hvm_pagetable_dying_t;
DEFINE_GUEST_HANDLE_STRUCT(xen_hvm_pagetable_dying_t);
enum hvmmem_type_t {
HVMMEM_ram_rw, /* Normal read/write guest RAM */
HVMMEM_ram_ro, /* Read-only; writes are discarded */
HVMMEM_mmio_dm, /* Reads and write go to the device model */
};
#define HVMOP_get_mem_type 15
/* Return hvmmem_type_t for the specified pfn. */
struct xen_hvm_get_mem_type {
/* Domain to be queried. */
domid_t domid;
/* OUT variable. */
uint16_t mem_type;
uint16_t pad[2]; /* align next field on 8-byte boundary */
/* IN variable. */
uint64_t pfn;
};
DEFINE_GUEST_HANDLE_STRUCT(xen_hvm_get_mem_type);
#endif /* __XEN_PUBLIC_HVM_HVM_OP_H__ */

127
include/xen/interface/hvm/params.h Normal file
View File

@ -0,0 +1,127 @@
/*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*/
#ifndef __XEN_PUBLIC_HVM_PARAMS_H__
#define __XEN_PUBLIC_HVM_PARAMS_H__
#include <xen/interface/hvm/hvm_op.h>
/*
* Parameter space for HVMOP_{set,get}_param.
*/
#define HVM_PARAM_CALLBACK_IRQ 0
/*
* How should CPU0 event-channel notifications be delivered?
*
* If val == 0 then CPU0 event-channel notifications are not delivered.
* If val != 0, val[63:56] encodes the type, as follows:
*/
#define HVM_PARAM_CALLBACK_TYPE_GSI 0
/*
* val[55:0] is a delivery GSI. GSI 0 cannot be used, as it aliases val == 0,
* and disables all notifications.
*/
#define HVM_PARAM_CALLBACK_TYPE_PCI_INTX 1
/*
* val[55:0] is a delivery PCI INTx line:
* Domain = val[47:32], Bus = val[31:16] DevFn = val[15:8], IntX = val[1:0]
*/
#if defined(__i386__) || defined(__x86_64__)
#define HVM_PARAM_CALLBACK_TYPE_VECTOR 2
/*
* val[7:0] is a vector number. Check for XENFEAT_hvm_callback_vector to know
* if this delivery method is available.
*/
#elif defined(__arm__) || defined(__aarch64__)
#define HVM_PARAM_CALLBACK_TYPE_PPI 2
/*
* val[55:16] needs to be zero.
* val[15:8] is interrupt flag of the PPI used by event-channel:
* bit 8: the PPI is edge(1) or level(0) triggered
* bit 9: the PPI is active low(1) or high(0)
* val[7:0] is a PPI number used by event-channel.
* This is only used by ARM/ARM64 and masking/eoi the interrupt associated to
* the notification is handled by the interrupt controller.
*/
#endif
#define HVM_PARAM_STORE_PFN 1
#define HVM_PARAM_STORE_EVTCHN 2
#define HVM_PARAM_PAE_ENABLED 4
#define HVM_PARAM_IOREQ_PFN 5
#define HVM_PARAM_BUFIOREQ_PFN 6
/*
* Set mode for virtual timers (currently x86 only):
* delay_for_missed_ticks (default):
* Do not advance a vcpu's time beyond the correct delivery time for
* interrupts that have been missed due to preemption. Deliver missed
* interrupts when the vcpu is rescheduled and advance the vcpu's virtual
* time stepwise for each one.
* no_delay_for_missed_ticks:
* As above, missed interrupts are delivered, but guest time always tracks
* wallclock (i.e., real) time while doing so.
* no_missed_ticks_pending:
* No missed interrupts are held pending. Instead, to ensure ticks are
* delivered at some non-zero rate, if we detect missed ticks then the
* internal tick alarm is not disabled if the VCPU is preempted during the
* next tick period.
* one_missed_tick_pending:
* Missed interrupts are collapsed together and delivered as one 'late tick'.
* Guest time always tracks wallclock (i.e., real) time.
*/
#define HVM_PARAM_TIMER_MODE 10
#define HVMPTM_delay_for_missed_ticks 0
#define HVMPTM_no_delay_for_missed_ticks 1
#define HVMPTM_no_missed_ticks_pending 2
#define HVMPTM_one_missed_tick_pending 3
/* Boolean: Enable virtual HPET (high-precision event timer)? (x86-only) */
#define HVM_PARAM_HPET_ENABLED 11
/* Identity-map page directory used by Intel EPT when CR0.PG=0. */
#define HVM_PARAM_IDENT_PT 12
/* Device Model domain, defaults to 0. */
#define HVM_PARAM_DM_DOMAIN 13
/* ACPI S state: currently support S0 and S3 on x86. */
#define HVM_PARAM_ACPI_S_STATE 14
/* TSS used on Intel when CR0.PE=0. */
#define HVM_PARAM_VM86_TSS 15
/* Boolean: Enable aligning all periodic vpts to reduce interrupts */
#define HVM_PARAM_VPT_ALIGN 16
/* Console debug shared memory ring and event channel */
#define HVM_PARAM_CONSOLE_PFN 17
#define HVM_PARAM_CONSOLE_EVTCHN 18
#define HVM_NR_PARAMS 19
#endif /* __XEN_PUBLIC_HVM_PARAMS_H__ */

24
include/xen/interface/io/console.h Normal file
View File

@ -0,0 +1,24 @@
/* SPDX-License-Identifier: GPL-2.0 */
/******************************************************************************
* console.h
*
* Console I/O interface for Xen guest OSes.
*
* Copyright (c) 2005, Keir Fraser
*/
#ifndef __XEN_PUBLIC_IO_CONSOLE_H__
#define __XEN_PUBLIC_IO_CONSOLE_H__
typedef uint32_t XENCONS_RING_IDX;
#define MASK_XENCONS_IDX(idx, ring) ((idx) & (sizeof(ring)-1))
struct xencons_interface {
char in[1024];
char out[2048];
XENCONS_RING_IDX in_cons, in_prod;
XENCONS_RING_IDX out_cons, out_prod;
};
#endif /* __XEN_PUBLIC_IO_CONSOLE_H__ */

432
include/xen/interface/io/ring.h Normal file
View File

@ -0,0 +1,432 @@
/* SPDX-License-Identifier: GPL-2.0 */
/******************************************************************************
* ring.h
*
* Shared producer-consumer ring macros.
*
* Tim Deegan and Andrew Warfield November 2004.
*/
#ifndef __XEN_PUBLIC_IO_RING_H__
#define __XEN_PUBLIC_IO_RING_H__
#include <xen/interface/grant_table.h>
typedef unsigned int RING_IDX;
/* Round a 32-bit unsigned constant down to the nearest power of two. */
#define __RD2(_x) (((_x) & 0x00000002) ? 0x2 : ((_x) & 0x1))
#define __RD4(_x) (((_x) & 0x0000000c) ? __RD2((_x)>>2)<<2 : __RD2(_x))
#define __RD8(_x) (((_x) & 0x000000f0) ? __RD4((_x)>>4)<<4 : __RD4(_x))
#define __RD16(_x) (((_x) & 0x0000ff00) ? __RD8((_x)>>8)<<8 : __RD8(_x))
#define __RD32(_x) (((_x) & 0xffff0000) ? __RD16((_x)>>16)<<16 : __RD16(_x))
/*
* Calculate size of a shared ring, given the total available space for the
* ring and indexes (_sz), and the name tag of the request/response structure.
* A ring contains as many entries as will fit, rounded down to the nearest
* power of two (so we can mask with (size-1) to loop around).
*/
#define __CONST_RING_SIZE(_s, _sz) \
(__RD32(((_sz) - offsetof(struct _s##_sring, ring)) / \
sizeof(((struct _s##_sring *)0)->ring[0])))
/*
* The same for passing in an actual pointer instead of a name tag.
*/
#define __RING_SIZE(_s, _sz) \
(__RD32(((_sz) - (long)&(_s)->ring + (long)(_s)) / sizeof((_s)->ring[0])))
/*
* Macros to make the correct C datatypes for a new kind of ring.
*
* To make a new ring datatype, you need to have two message structures,
* let's say struct request, and struct response already defined.
*
* In a header where you want the ring datatype declared, you then do:
*
* DEFINE_RING_TYPES(mytag, struct request, struct response);
*
* These expand out to give you a set of types, as you can see below.
* The most important of these are:
*
* struct mytag_sring - The shared ring.
* struct mytag_front_ring - The 'front' half of the ring.
* struct mytag_back_ring - The 'back' half of the ring.
*
* To initialize a ring in your code you need to know the location and size
* of the shared memory area (PAGE_SIZE, for instance). To initialise
* the front half:
*
* struct mytag_front_ring front_ring;
* SHARED_RING_INIT((struct mytag_sring *)shared_page);
* FRONT_RING_INIT(&front_ring, (struct mytag_sring *)shared_page,
* PAGE_SIZE);
*
* Initializing the back follows similarly (note that only the front
* initializes the shared ring):
*
* struct mytag_back_ring back_ring;
* BACK_RING_INIT(&back_ring, (struct mytag_sring *)shared_page,
* PAGE_SIZE);
*/
#define DEFINE_RING_TYPES(__name, __req_t, __rsp_t) \
\
/* Shared ring entry */ \
union __name##_sring_entry { \
__req_t req; \
__rsp_t rsp; \
}; \
\
/* Shared ring page */ \
struct __name##_sring { \
RING_IDX req_prod, req_event; \
RING_IDX rsp_prod, rsp_event; \
uint8_t pad[48]; \
union __name##_sring_entry ring[1]; /* variable-length */ \
}; \
\
/* "Front" end's private variables */ \
struct __name##_front_ring { \
RING_IDX req_prod_pvt; \
RING_IDX rsp_cons; \
unsigned int nr_ents; \
struct __name##_sring *sring; \
}; \
\
/* "Back" end's private variables */ \
struct __name##_back_ring { \
RING_IDX rsp_prod_pvt; \
RING_IDX req_cons; \
unsigned int nr_ents; \
struct __name##_sring *sring; \
};
/*
* Macros for manipulating rings.
*
* FRONT_RING_whatever works on the "front end" of a ring: here
* requests are pushed on to the ring and responses taken off it.
*
* BACK_RING_whatever works on the "back end" of a ring: here
* requests are taken off the ring and responses put on.
*
* N.B. these macros do NO INTERLOCKS OR FLOW CONTROL.
* This is OK in 1-for-1 request-response situations where the
* requestor (front end) never has more than RING_SIZE()-1
* outstanding requests.
*/
/* Initialising empty rings */
#define SHARED_RING_INIT(_s) do { \
(_s)->req_prod = (_s)->rsp_prod = 0; \
(_s)->req_event = (_s)->rsp_event = 1; \
memset((_s)->pad, 0, sizeof((_s)->pad)); \
} while(0)
#define FRONT_RING_INIT(_r, _s, __size) do { \
(_r)->req_prod_pvt = 0; \
(_r)->rsp_cons = 0; \
(_r)->nr_ents = __RING_SIZE(_s, __size); \
(_r)->sring = (_s); \
} while (0)
#define BACK_RING_INIT(_r, _s, __size) do { \
(_r)->rsp_prod_pvt = 0; \
(_r)->req_cons = 0; \
(_r)->nr_ents = __RING_SIZE(_s, __size); \
(_r)->sring = (_s); \
} while (0)
/* Initialize to existing shared indexes -- for recovery */
#define FRONT_RING_ATTACH(_r, _s, __size) do { \
(_r)->sring = (_s); \
(_r)->req_prod_pvt = (_s)->req_prod; \
(_r)->rsp_cons = (_s)->rsp_prod; \
(_r)->nr_ents = __RING_SIZE(_s, __size); \
} while (0)
#define BACK_RING_ATTACH(_r, _s, __size) do { \
(_r)->sring = (_s); \
(_r)->rsp_prod_pvt = (_s)->rsp_prod; \
(_r)->req_cons = (_s)->req_prod; \
(_r)->nr_ents = __RING_SIZE(_s, __size); \
} while (0)
/* How big is this ring? */
#define RING_SIZE(_r) \
((_r)->nr_ents)
/* Number of free requests (for use on front side only). */
#define RING_FREE_REQUESTS(_r) \
(RING_SIZE(_r) - ((_r)->req_prod_pvt - (_r)->rsp_cons))
/* Test if there is an empty slot available on the front ring.
* (This is only meaningful from the front. )
*/
#define RING_FULL(_r) \
(RING_FREE_REQUESTS(_r) == 0)
/* Test if there are outstanding messages to be processed on a ring. */
#define RING_HAS_UNCONSUMED_RESPONSES(_r) \
((_r)->sring->rsp_prod - (_r)->rsp_cons)
#define RING_HAS_UNCONSUMED_REQUESTS(_r) \
({ \
unsigned int req = (_r)->sring->req_prod - (_r)->req_cons; \
unsigned int rsp = RING_SIZE(_r) - \
((_r)->req_cons - (_r)->rsp_prod_pvt); \
req < rsp ? req : rsp; \
})
/* Direct access to individual ring elements, by index. */
#define RING_GET_REQUEST(_r, _idx) \
(&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].req))
/*
* Get a local copy of a request.
*
* Use this in preference to RING_GET_REQUEST() so all processing is
* done on a local copy that cannot be modified by the other end.
*
* Note that https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 may cause this
* to be ineffective where _req is a struct which consists of only bitfields.
*/
#define RING_COPY_REQUEST(_r, _idx, _req) do { \
/* Use volatile to force the copy into _req. */ \
*(_req) = *(volatile typeof(_req))RING_GET_REQUEST(_r, _idx); \
} while (0)
#define RING_GET_RESPONSE(_r, _idx) \
(&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].rsp))
/* Loop termination condition: Would the specified index overflow the ring? */
#define RING_REQUEST_CONS_OVERFLOW(_r, _cons) \
(((_cons) - (_r)->rsp_prod_pvt) >= RING_SIZE(_r))
/* Ill-behaved frontend determination: Can there be this many requests? */
#define RING_REQUEST_PROD_OVERFLOW(_r, _prod) \
(((_prod) - (_r)->rsp_prod_pvt) > RING_SIZE(_r))
#define RING_PUSH_REQUESTS(_r) do { \
virt_wmb(); /* back sees requests /before/ updated producer index */ \
(_r)->sring->req_prod = (_r)->req_prod_pvt; \
} while (0)
#define RING_PUSH_RESPONSES(_r) do { \
virt_wmb(); /* front sees responses /before/ updated producer index */ \
(_r)->sring->rsp_prod = (_r)->rsp_prod_pvt; \
} while (0)
/*
* Notification hold-off (req_event and rsp_event):
*
* When queueing requests or responses on a shared ring, it may not always be
* necessary to notify the remote end. For example, if requests are in flight
* in a backend, the front may be able to queue further requests without
* notifying the back (if the back checks for new requests when it queues
* responses).
*
* When enqueuing requests or responses:
*
* Use RING_PUSH_{REQUESTS,RESPONSES}_AND_CHECK_NOTIFY(). The second argument
* is a boolean return value. True indicates that the receiver requires an
* asynchronous notification.
*
* After dequeuing requests or responses (before sleeping the connection):
*
* Use RING_FINAL_CHECK_FOR_REQUESTS() or RING_FINAL_CHECK_FOR_RESPONSES().
* The second argument is a boolean return value. True indicates that there
* are pending messages on the ring (i.e., the connection should not be put
* to sleep).
*
* These macros will set the req_event/rsp_event field to trigger a
* notification on the very next message that is enqueued. If you want to
* create batches of work (i.e., only receive a notification after several
* messages have been enqueued) then you will need to create a customised
* version of the FINAL_CHECK macro in your own code, which sets the event
* field appropriately.
*/
#define RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(_r, _notify) do { \
RING_IDX __old = (_r)->sring->req_prod; \
RING_IDX __new = (_r)->req_prod_pvt; \
virt_wmb(); /* back sees requests /before/ updated producer index */ \
(_r)->sring->req_prod = __new; \
virt_mb(); /* back sees new requests /before/ we check req_event */ \
(_notify) = ((RING_IDX)(__new - (_r)->sring->req_event) < \
(RING_IDX)(__new - __old)); \
} while (0)
#define RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(_r, _notify) do { \
RING_IDX __old = (_r)->sring->rsp_prod; \
RING_IDX __new = (_r)->rsp_prod_pvt; \
virt_wmb(); /* front sees responses /before/ updated producer index */ \
(_r)->sring->rsp_prod = __new; \
virt_mb(); /* front sees new responses /before/ we check rsp_event */ \
(_notify) = ((RING_IDX)(__new - (_r)->sring->rsp_event) < \
(RING_IDX)(__new - __old)); \
} while (0)
#define RING_FINAL_CHECK_FOR_REQUESTS(_r, _work_to_do) do { \
(_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r); \
if (_work_to_do) break; \
(_r)->sring->req_event = (_r)->req_cons + 1; \
virt_mb(); \
(_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r); \
} while (0)
#define RING_FINAL_CHECK_FOR_RESPONSES(_r, _work_to_do) do { \
(_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r); \
if (_work_to_do) break; \
(_r)->sring->rsp_event = (_r)->rsp_cons + 1; \
virt_mb(); \
(_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r); \
} while (0)
/*
* DEFINE_XEN_FLEX_RING_AND_INTF defines two monodirectional rings and
* functions to check if there is data on the ring, and to read and
* write to them.
*
* DEFINE_XEN_FLEX_RING is similar to DEFINE_XEN_FLEX_RING_AND_INTF, but
* does not define the indexes page. As different protocols can have
* extensions to the basic format, this macro allow them to define their
* own struct.
*
* XEN_FLEX_RING_SIZE
* Convenience macro to calculate the size of one of the two rings
* from the overall order.
*
* $NAME_mask
* Function to apply the size mask to an index, to reduce the index
* within the range [0-size].
*
* $NAME_read_packet
* Function to read data from the ring. The amount of data to read is
* specified by the "size" argument.
*
* $NAME_write_packet
* Function to write data to the ring. The amount of data to write is
* specified by the "size" argument.
*
* $NAME_get_ring_ptr
* Convenience function that returns a pointer to read/write to the
* ring at the right location.
*
* $NAME_data_intf
* Indexes page, shared between frontend and backend. It also
* contains the array of grant refs.
*
* $NAME_queued
* Function to calculate how many bytes are currently on the ring,
* ready to be read. It can also be used to calculate how much free
* space is currently on the ring (XEN_FLEX_RING_SIZE() -
* $NAME_queued()).
*/
#ifndef XEN_PAGE_SHIFT
/* The PAGE_SIZE for ring protocols and hypercall interfaces is always
* 4K, regardless of the architecture, and page granularity chosen by
* operating systems.
*/
#define XEN_PAGE_SHIFT 12
#endif
#define XEN_FLEX_RING_SIZE(order) \
(1UL << ((order) + XEN_PAGE_SHIFT - 1))
#define DEFINE_XEN_FLEX_RING(name) \
static inline RING_IDX name##_mask(RING_IDX idx, RING_IDX ring_size) \
{ \
return idx & (ring_size - 1); \
} \
\
static inline unsigned char *name##_get_ring_ptr(unsigned char *buf, \
RING_IDX idx, \
RING_IDX ring_size) \
{ \
return buf + name##_mask(idx, ring_size); \
} \
\
static inline void name##_read_packet(void *opaque, \
const unsigned char *buf, \
size_t size, \
RING_IDX masked_prod, \
RING_IDX *masked_cons, \
RING_IDX ring_size) \
{ \
if (*masked_cons < masked_prod || \
size <= ring_size - *masked_cons) { \
memcpy(opaque, buf + *masked_cons, size); \
} else { \
memcpy(opaque, buf + *masked_cons, ring_size - *masked_cons); \
memcpy((unsigned char *)opaque + ring_size - *masked_cons, buf, \
size - (ring_size - *masked_cons)); \
} \
*masked_cons = name##_mask(*masked_cons + size, ring_size); \
} \
\
static inline void name##_write_packet(unsigned char *buf, \
const void *opaque, \
size_t size, \
RING_IDX *masked_prod, \
RING_IDX masked_cons, \
RING_IDX ring_size) \
{ \
if (*masked_prod < masked_cons || \
size <= ring_size - *masked_prod) { \
memcpy(buf + *masked_prod, opaque, size); \
} else { \
memcpy(buf + *masked_prod, opaque, ring_size - *masked_prod); \
memcpy(buf, (unsigned char *)opaque + (ring_size - *masked_prod), \
size - (ring_size - *masked_prod)); \
} \
*masked_prod = name##_mask(*masked_prod + size, ring_size); \
} \
\
static inline RING_IDX name##_queued(RING_IDX prod, \
RING_IDX cons, \
RING_IDX ring_size) \
{ \
RING_IDX size; \
\
if (prod == cons) \
return 0; \
\
prod = name##_mask(prod, ring_size); \
cons = name##_mask(cons, ring_size); \
\
if (prod == cons) \
return ring_size; \
\
if (prod > cons) \
size = prod - cons; \
else \
size = ring_size - (cons - prod); \
return size; \
} \
\
struct name##_data { \
unsigned char *in; /* half of the allocation */ \
unsigned char *out; /* half of the allocation */ \
}
#define DEFINE_XEN_FLEX_RING_AND_INTF(name) \
struct name##_data_intf { \
RING_IDX in_cons, in_prod; \
\
uint8_t pad1[56]; \
\
RING_IDX out_cons, out_prod; \
\
uint8_t pad2[56]; \
\
RING_IDX ring_order; \
grant_ref_t ref[]; \
}; \
DEFINE_XEN_FLEX_RING(name)
#endif /* __XEN_PUBLIC_IO_RING_H__ */

531
include/xen/interface/platform.h Normal file
View File

@ -0,0 +1,531 @@
/******************************************************************************
* platform.h
*
* Hardware platform operations. Intended for use by domain-0 kernel.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*
* Copyright (c) 2002-2006, K Fraser
*/
#ifndef __XEN_PUBLIC_PLATFORM_H__
#define __XEN_PUBLIC_PLATFORM_H__
#include <xen/interface/xen.h>
#define XENPF_INTERFACE_VERSION 0x03000001
/*
* Set clock such that it would read <secs,nsecs> after 00:00:00 UTC,
* 1 January, 1970 if the current system time was <system_time>.
*/
#define XENPF_settime32 17
struct xenpf_settime32 {
/* IN variables. */
uint32_t secs;
uint32_t nsecs;
uint64_t system_time;
};
DEFINE_GUEST_HANDLE_STRUCT(xenpf_settime32_t);
#define XENPF_settime64 62
struct xenpf_settime64 {
/* IN variables. */
uint64_t secs;
uint32_t nsecs;
uint32_t mbz;
uint64_t system_time;
};
DEFINE_GUEST_HANDLE_STRUCT(xenpf_settime64_t);
/*
* Request memory range (@mfn, @mfn+@nr_mfns-1) to have type @type.
* On x86, @type is an architecture-defined MTRR memory type.
* On success, returns the MTRR that was used (@reg) and a handle that can
* be passed to XENPF_DEL_MEMTYPE to accurately tear down the new setting.
* (x86-specific).
*/
#define XENPF_add_memtype 31
struct xenpf_add_memtype {
/* IN variables. */
xen_pfn_t mfn;
uint64_t nr_mfns;
uint32_t type;
/* OUT variables. */
uint32_t handle;
uint32_t reg;
};
DEFINE_GUEST_HANDLE_STRUCT(xenpf_add_memtype_t);
/*
* Tear down an existing memory-range type. If @handle is remembered then it
* should be passed in to accurately tear down the correct setting (in case
* of overlapping memory regions with differing types). If it is not known
* then @handle should be set to zero. In all cases @reg must be set.
* (x86-specific).
*/
#define XENPF_del_memtype 32
struct xenpf_del_memtype {
/* IN variables. */
uint32_t handle;
uint32_t reg;
};
DEFINE_GUEST_HANDLE_STRUCT(xenpf_del_memtype_t);
/* Read current type of an MTRR (x86-specific). */
#define XENPF_read_memtype 33
struct xenpf_read_memtype {
/* IN variables. */
uint32_t reg;
/* OUT variables. */
xen_pfn_t mfn;
uint64_t nr_mfns;
uint32_t type;
};
DEFINE_GUEST_HANDLE_STRUCT(xenpf_read_memtype_t);
#define XENPF_microcode_update 35
struct xenpf_microcode_update {
/* IN variables. */
GUEST_HANDLE(void) data; /* Pointer to microcode data */
uint32_t length; /* Length of microcode data. */
};
DEFINE_GUEST_HANDLE_STRUCT(xenpf_microcode_update_t);
#define XENPF_platform_quirk 39
#define QUIRK_NOIRQBALANCING 1 /* Do not restrict IO-APIC RTE targets */
#define QUIRK_IOAPIC_BAD_REGSEL 2 /* IO-APIC REGSEL forgets its value */
#define QUIRK_IOAPIC_GOOD_REGSEL 3 /* IO-APIC REGSEL behaves properly */
struct xenpf_platform_quirk {
/* IN variables. */
uint32_t quirk_id;
};
DEFINE_GUEST_HANDLE_STRUCT(xenpf_platform_quirk_t);
#define XENPF_efi_runtime_call 49
#define XEN_EFI_get_time 1
#define XEN_EFI_set_time 2
#define XEN_EFI_get_wakeup_time 3
#define XEN_EFI_set_wakeup_time 4
#define XEN_EFI_get_next_high_monotonic_count 5
#define XEN_EFI_get_variable 6
#define XEN_EFI_set_variable 7
#define XEN_EFI_get_next_variable_name 8
#define XEN_EFI_query_variable_info 9
#define XEN_EFI_query_capsule_capabilities 10
#define XEN_EFI_update_capsule 11
struct xenpf_efi_runtime_call {
uint32_t function;
/*
* This field is generally used for per sub-function flags (defined
* below), except for the XEN_EFI_get_next_high_monotonic_count case,
* where it holds the single returned value.
*/
uint32_t misc;
xen_ulong_t status;
union {
#define XEN_EFI_GET_TIME_SET_CLEARS_NS 0x00000001
struct {
struct xenpf_efi_time {
uint16_t year;
uint8_t month;
uint8_t day;
uint8_t hour;
uint8_t min;
uint8_t sec;
uint32_t ns;
int16_t tz;
uint8_t daylight;
} time;
uint32_t resolution;
uint32_t accuracy;
} get_time;
struct xenpf_efi_time set_time;
#define XEN_EFI_GET_WAKEUP_TIME_ENABLED 0x00000001
#define XEN_EFI_GET_WAKEUP_TIME_PENDING 0x00000002
struct xenpf_efi_time get_wakeup_time;
#define XEN_EFI_SET_WAKEUP_TIME_ENABLE 0x00000001
#define XEN_EFI_SET_WAKEUP_TIME_ENABLE_ONLY 0x00000002
struct xenpf_efi_time set_wakeup_time;
#define XEN_EFI_VARIABLE_NON_VOLATILE 0x00000001
#define XEN_EFI_VARIABLE_BOOTSERVICE_ACCESS 0x00000002
#define XEN_EFI_VARIABLE_RUNTIME_ACCESS 0x00000004
struct {
GUEST_HANDLE(void) name; /* UCS-2/UTF-16 string */
xen_ulong_t size;
GUEST_HANDLE(void) data;
struct xenpf_efi_guid {
uint32_t data1;
uint16_t data2;
uint16_t data3;
uint8_t data4[8];
} vendor_guid;
} get_variable, set_variable;
struct {
xen_ulong_t size;
GUEST_HANDLE(void) name; /* UCS-2/UTF-16 string */
struct xenpf_efi_guid vendor_guid;
} get_next_variable_name;
struct {
uint32_t attr;
uint64_t max_store_size;
uint64_t remain_store_size;
uint64_t max_size;
} query_variable_info;
struct {
GUEST_HANDLE(void) capsule_header_array;
xen_ulong_t capsule_count;
uint64_t max_capsule_size;
uint32_t reset_type;
} query_capsule_capabilities;
struct {
GUEST_HANDLE(void) capsule_header_array;
xen_ulong_t capsule_count;
uint64_t sg_list; /* machine address */
} update_capsule;
} u;
};
DEFINE_GUEST_HANDLE_STRUCT(xenpf_efi_runtime_call);
#define XEN_FW_EFI_VERSION 0
#define XEN_FW_EFI_CONFIG_TABLE 1
#define XEN_FW_EFI_VENDOR 2
#define XEN_FW_EFI_MEM_INFO 3
#define XEN_FW_EFI_RT_VERSION 4
#define XENPF_firmware_info 50
#define XEN_FW_DISK_INFO 1 /* from int 13 AH=08/41/48 */
#define XEN_FW_DISK_MBR_SIGNATURE 2 /* from MBR offset 0x1b8 */
#define XEN_FW_VBEDDC_INFO 3 /* from int 10 AX=4f15 */
#define XEN_FW_EFI_INFO 4 /* from EFI */
#define XEN_FW_KBD_SHIFT_FLAGS 5 /* Int16, Fn02: Get keyboard shift flags. */
struct xenpf_firmware_info {
/* IN variables. */
uint32_t type;
uint32_t index;
/* OUT variables. */
union {
struct {
/* Int13, Fn48: Check Extensions Present. */
uint8_t device; /* %dl: bios device number */
uint8_t version; /* %ah: major version */
uint16_t interface_support; /* %cx: support bitmap */
/* Int13, Fn08: Legacy Get Device Parameters. */
uint16_t legacy_max_cylinder; /* %cl[7:6]:%ch: max cyl # */
uint8_t legacy_max_head; /* %dh: max head # */
uint8_t legacy_sectors_per_track; /* %cl[5:0]: max sector # */
/* Int13, Fn41: Get Device Parameters (as filled into %ds:%esi). */
/* NB. First uint16_t of buffer must be set to buffer size. */
GUEST_HANDLE(void) edd_params;
} disk_info; /* XEN_FW_DISK_INFO */
struct {
uint8_t device; /* bios device number */
uint32_t mbr_signature; /* offset 0x1b8 in mbr */
} disk_mbr_signature; /* XEN_FW_DISK_MBR_SIGNATURE */
struct {
/* Int10, AX=4F15: Get EDID info. */
uint8_t capabilities;
uint8_t edid_transfer_time;
/* must refer to 128-byte buffer */
GUEST_HANDLE(uchar) edid;
} vbeddc_info; /* XEN_FW_VBEDDC_INFO */
union xenpf_efi_info {
uint32_t version;
struct {
uint64_t addr; /* EFI_CONFIGURATION_TABLE */
uint32_t nent;
} cfg;
struct {
uint32_t revision;
uint32_t bufsz; /* input, in bytes */
GUEST_HANDLE(void) name;
/* UCS-2/UTF-16 string */
} vendor;
struct {
uint64_t addr;
uint64_t size;
uint64_t attr;
uint32_t type;
} mem;
} efi_info; /* XEN_FW_EFI_INFO */
uint8_t kbd_shift_flags; /* XEN_FW_KBD_SHIFT_FLAGS */
} u;
};
DEFINE_GUEST_HANDLE_STRUCT(xenpf_firmware_info_t);
#define XENPF_enter_acpi_sleep 51
struct xenpf_enter_acpi_sleep {
/* IN variables */
uint16_t val_a; /* PM1a control / sleep type A. */
uint16_t val_b; /* PM1b control / sleep type B. */
uint32_t sleep_state; /* Which state to enter (Sn). */
#define XENPF_ACPI_SLEEP_EXTENDED 0x00000001
uint32_t flags; /* XENPF_ACPI_SLEEP_*. */
};
DEFINE_GUEST_HANDLE_STRUCT(xenpf_enter_acpi_sleep_t);
#define XENPF_change_freq 52
struct xenpf_change_freq {
/* IN variables */
uint32_t flags; /* Must be zero. */
uint32_t cpu; /* Physical cpu. */
uint64_t freq; /* New frequency (Hz). */
};
DEFINE_GUEST_HANDLE_STRUCT(xenpf_change_freq_t);
/*
* Get idle times (nanoseconds since boot) for physical CPUs specified in the
* @cpumap_bitmap with range [0..@cpumap_nr_cpus-1]. The @idletime array is
* indexed by CPU number; only entries with the corresponding @cpumap_bitmap
* bit set are written to. On return, @cpumap_bitmap is modified so that any
* non-existent CPUs are cleared. Such CPUs have their @idletime array entry
* cleared.
*/
#define XENPF_getidletime 53
struct xenpf_getidletime {
/* IN/OUT variables */
/* IN: CPUs to interrogate; OUT: subset of IN which are present */
GUEST_HANDLE(uchar) cpumap_bitmap;
/* IN variables */
/* Size of cpumap bitmap. */
uint32_t cpumap_nr_cpus;
/* Must be indexable for every cpu in cpumap_bitmap. */
GUEST_HANDLE(uint64_t) idletime;
/* OUT variables */
/* System time when the idletime snapshots were taken. */
uint64_t now;
};
DEFINE_GUEST_HANDLE_STRUCT(xenpf_getidletime_t);
#define XENPF_set_processor_pminfo 54
/* ability bits */
#define XEN_PROCESSOR_PM_CX 1
#define XEN_PROCESSOR_PM_PX 2
#define XEN_PROCESSOR_PM_TX 4
/* cmd type */
#define XEN_PM_CX 0
#define XEN_PM_PX 1
#define XEN_PM_TX 2
#define XEN_PM_PDC 3
/* Px sub info type */
#define XEN_PX_PCT 1
#define XEN_PX_PSS 2
#define XEN_PX_PPC 4
#define XEN_PX_PSD 8
struct xen_power_register {
uint32_t space_id;
uint32_t bit_width;
uint32_t bit_offset;
uint32_t access_size;
uint64_t address;
};
struct xen_processor_csd {
uint32_t domain; /* domain number of one dependent group */
uint32_t coord_type; /* coordination type */
uint32_t num; /* number of processors in same domain */
};
DEFINE_GUEST_HANDLE_STRUCT(xen_processor_csd);
struct xen_processor_cx {
struct xen_power_register reg; /* GAS for Cx trigger register */
uint8_t type; /* cstate value, c0: 0, c1: 1, ... */
uint32_t latency; /* worst latency (ms) to enter/exit this cstate */
uint32_t power; /* average power consumption(mW) */
uint32_t dpcnt; /* number of dependency entries */
GUEST_HANDLE(xen_processor_csd) dp; /* NULL if no dependency */
};
DEFINE_GUEST_HANDLE_STRUCT(xen_processor_cx);
struct xen_processor_flags {
uint32_t bm_control:1;
uint32_t bm_check:1;
uint32_t has_cst:1;
uint32_t power_setup_done:1;
uint32_t bm_rld_set:1;
};
struct xen_processor_power {
uint32_t count; /* number of C state entries in array below */
struct xen_processor_flags flags; /* global flags of this processor */
GUEST_HANDLE(xen_processor_cx) states; /* supported c states */
};
struct xen_pct_register {
uint8_t descriptor;
uint16_t length;
uint8_t space_id;
uint8_t bit_width;
uint8_t bit_offset;
uint8_t reserved;
uint64_t address;
};
struct xen_processor_px {
uint64_t core_frequency; /* megahertz */
uint64_t power; /* milliWatts */
uint64_t transition_latency; /* microseconds */
uint64_t bus_master_latency; /* microseconds */
uint64_t control; /* control value */
uint64_t status; /* success indicator */
};
DEFINE_GUEST_HANDLE_STRUCT(xen_processor_px);
struct xen_psd_package {
uint64_t num_entries;
uint64_t revision;
uint64_t domain;
uint64_t coord_type;
uint64_t num_processors;
};
struct xen_processor_performance {
uint32_t flags; /* flag for Px sub info type */
uint32_t platform_limit; /* Platform limitation on freq usage */
struct xen_pct_register control_register;
struct xen_pct_register status_register;
uint32_t state_count; /* total available performance states */
GUEST_HANDLE(xen_processor_px) states;
struct xen_psd_package domain_info;
uint32_t shared_type; /* coordination type of this processor */
};
DEFINE_GUEST_HANDLE_STRUCT(xen_processor_performance);
struct xenpf_set_processor_pminfo {
/* IN variables */
uint32_t id; /* ACPI CPU ID */
uint32_t type; /* {XEN_PM_CX, XEN_PM_PX} */
union {
struct xen_processor_power power;/* Cx: _CST/_CSD */
struct xen_processor_performance perf; /* Px: _PPC/_PCT/_PSS/_PSD */
GUEST_HANDLE(uint32_t) pdc;
};
};
DEFINE_GUEST_HANDLE_STRUCT(xenpf_set_processor_pminfo);
#define XENPF_get_cpuinfo 55
struct xenpf_pcpuinfo {
/* IN */
uint32_t xen_cpuid;
/* OUT */
/* The maxium cpu_id that is present */
uint32_t max_present;
#define XEN_PCPU_FLAGS_ONLINE 1
/* Correponding xen_cpuid is not present*/
#define XEN_PCPU_FLAGS_INVALID 2
uint32_t flags;
uint32_t apic_id;
uint32_t acpi_id;
};
DEFINE_GUEST_HANDLE_STRUCT(xenpf_pcpuinfo);
#define XENPF_cpu_online 56
#define XENPF_cpu_offline 57
struct xenpf_cpu_ol {
uint32_t cpuid;
};
DEFINE_GUEST_HANDLE_STRUCT(xenpf_cpu_ol);
#define XENPF_cpu_hotadd 58
struct xenpf_cpu_hotadd {
uint32_t apic_id;
uint32_t acpi_id;
uint32_t pxm;
};
#define XENPF_mem_hotadd 59
struct xenpf_mem_hotadd {
uint64_t spfn;
uint64_t epfn;
uint32_t pxm;
uint32_t flags;
};
#define XENPF_core_parking 60
struct xenpf_core_parking {
/* IN variables */
#define XEN_CORE_PARKING_SET 1
#define XEN_CORE_PARKING_GET 2
uint32_t type;
/* IN variables: set cpu nums expected to be idled */
/* OUT variables: get cpu nums actually be idled */
uint32_t idle_nums;
};
DEFINE_GUEST_HANDLE_STRUCT(xenpf_core_parking);
#define XENPF_get_symbol 63
struct xenpf_symdata {
/* IN/OUT variables */
uint32_t namelen; /* size of 'name' buffer */
/* IN/OUT variables */
uint32_t symnum; /* IN: Symbol to read */
/* OUT: Next available symbol. If same as IN */
/* then we reached the end */
/* OUT variables */
GUEST_HANDLE(char) name;
uint64_t address;
char type;
};
DEFINE_GUEST_HANDLE_STRUCT(xenpf_symdata);
struct xen_platform_op {
uint32_t cmd;
uint32_t interface_version; /* XENPF_INTERFACE_VERSION */
union {
struct xenpf_settime32 settime32;
struct xenpf_settime64 settime64;
struct xenpf_add_memtype add_memtype;
struct xenpf_del_memtype del_memtype;
struct xenpf_read_memtype read_memtype;
struct xenpf_microcode_update microcode;
struct xenpf_platform_quirk platform_quirk;
struct xenpf_efi_runtime_call efi_runtime_call;
struct xenpf_firmware_info firmware_info;
struct xenpf_enter_acpi_sleep enter_acpi_sleep;
struct xenpf_change_freq change_freq;
struct xenpf_getidletime getidletime;
struct xenpf_set_processor_pminfo set_pminfo;
struct xenpf_pcpuinfo pcpu_info;
struct xenpf_cpu_ol cpu_ol;
struct xenpf_cpu_hotadd cpu_add;
struct xenpf_mem_hotadd mem_add;
struct xenpf_core_parking core_parking;
struct xenpf_symdata symdata;
uint8_t pad[128];
} u;
};
DEFINE_GUEST_HANDLE_STRUCT(xen_platform_op_t);
#endif /* __XEN_PUBLIC_PLATFORM_H__ */

183
include/xen/interface/sched.h Normal file
View File

@ -0,0 +1,183 @@
/******************************************************************************
* sched.h
*
* Scheduler state interactions
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*
* Copyright (c) 2005, Keir Fraser <keir@xensource.com>
*/
#ifndef __XEN_PUBLIC_SCHED_H__
#define __XEN_PUBLIC_SCHED_H__
#include <xen/interface/event_channel.h>
/*
* Guest Scheduler Operations
*
* The SCHEDOP interface provides mechanisms for a guest to interact
* with the scheduler, including yield, blocking and shutting itself
* down.
*/
/*
* The prototype for this hypercall is:
* long HYPERVISOR_sched_op(enum sched_op cmd, void *arg, ...)
*
* @cmd == SCHEDOP_??? (scheduler operation).
* @arg == Operation-specific extra argument(s), as described below.
* ... == Additional Operation-specific extra arguments, described below.
*
* Versions of Xen prior to 3.0.2 provided only the following legacy version
* of this hypercall, supporting only the commands yield, block and shutdown:
* long sched_op(int cmd, unsigned long arg)
* @cmd == SCHEDOP_??? (scheduler operation).
* @arg == 0 (SCHEDOP_yield and SCHEDOP_block)
* == SHUTDOWN_* code (SCHEDOP_shutdown)
*
* This legacy version is available to new guests as:
* long HYPERVISOR_sched_op_compat(enum sched_op cmd, unsigned long arg)
*/
/*
* Voluntarily yield the CPU.
* @arg == NULL.
*/
#define SCHEDOP_yield 0
/*
* Block execution of this VCPU until an event is received for processing.
* If called with event upcalls masked, this operation will atomically
* reenable event delivery and check for pending events before blocking the
* VCPU. This avoids a "wakeup waiting" race.
* @arg == NULL.
*/
#define SCHEDOP_block 1
/*
* Halt execution of this domain (all VCPUs) and notify the system controller.
* @arg == pointer to sched_shutdown structure.
*
* If the sched_shutdown_t reason is SHUTDOWN_suspend then
* x86 PV guests must also set RDX (EDX for 32-bit guests) to the MFN
* of the guest's start info page. RDX/EDX is the third hypercall
* argument.
*
* In addition, which reason is SHUTDOWN_suspend this hypercall
* returns 1 if suspend was cancelled or the domain was merely
* checkpointed, and 0 if it is resuming in a new domain.
*/
#define SCHEDOP_shutdown 2
/*
* Poll a set of event-channel ports. Return when one or more are pending. An
* optional timeout may be specified.
* @arg == pointer to sched_poll structure.
*/
#define SCHEDOP_poll 3
/*
* Declare a shutdown for another domain. The main use of this function is
* in interpreting shutdown requests and reasons for fully-virtualized
* domains. A para-virtualized domain may use SCHEDOP_shutdown directly.
* @arg == pointer to sched_remote_shutdown structure.
*/
#define SCHEDOP_remote_shutdown 4
/*
* Latch a shutdown code, so that when the domain later shuts down it
* reports this code to the control tools.
* @arg == sched_shutdown, as for SCHEDOP_shutdown.
*/
#define SCHEDOP_shutdown_code 5
/*
* Setup, poke and destroy a domain watchdog timer.
* @arg == pointer to sched_watchdog structure.
* With id == 0, setup a domain watchdog timer to cause domain shutdown
* after timeout, returns watchdog id.
* With id != 0 and timeout == 0, destroy domain watchdog timer.
* With id != 0 and timeout != 0, poke watchdog timer and set new timeout.
*/
#define SCHEDOP_watchdog 6
/*
* Override the current vcpu affinity by pinning it to one physical cpu or
* undo this override restoring the previous affinity.
* @arg == pointer to sched_pin_override structure.
*
* A negative pcpu value will undo a previous pin override and restore the
* previous cpu affinity.
* This call is allowed for the hardware domain only and requires the cpu
* to be part of the domain's cpupool.
*/
#define SCHEDOP_pin_override 7
struct sched_shutdown {
unsigned int reason; /* SHUTDOWN_* => shutdown reason */
};
DEFINE_GUEST_HANDLE_STRUCT(sched_shutdown);
struct sched_poll {
GUEST_HANDLE(evtchn_port_t) ports;
unsigned int nr_ports;
uint64_t timeout;
};
DEFINE_GUEST_HANDLE_STRUCT(sched_poll);
struct sched_remote_shutdown {
domid_t domain_id; /* Remote domain ID */
unsigned int reason; /* SHUTDOWN_* => shutdown reason */
};
DEFINE_GUEST_HANDLE_STRUCT(sched_remote_shutdown);
struct sched_watchdog {
uint32_t id; /* watchdog ID */
uint32_t timeout; /* timeout */
};
DEFINE_GUEST_HANDLE_STRUCT(sched_watchdog);
struct sched_pin_override {
int32_t pcpu;
};
DEFINE_GUEST_HANDLE_STRUCT(sched_pin_override);
/*
* Reason codes for SCHEDOP_shutdown. These may be interpreted by control
* software to determine the appropriate action. For the most part, Xen does
* not care about the shutdown code.
*/
#define SHUTDOWN_poweroff 0 /* Domain exited normally. Clean up and kill. */
#define SHUTDOWN_reboot 1 /* Clean up, kill, and then restart. */
#define SHUTDOWN_suspend 2 /* Clean up, save suspend info, kill. */
#define SHUTDOWN_crash 3 /* Tell controller we've crashed. */
#define SHUTDOWN_watchdog 4 /* Restart because watchdog time expired. */
/*
* Domain asked to perform 'soft reset' for it. The expected behavior is to
* reset internal Xen state for the domain returning it to the point where it
* was created but leaving the domain's memory contents and vCPU contexts
* intact. This will allow the domain to start over and set up all Xen specific
* interfaces again.
*/
#define SHUTDOWN_soft_reset 5
#define SHUTDOWN_MAX 5 /* Maximum valid shutdown reason. */
#endif /* __XEN_PUBLIC_SCHED_H__ */

782
include/xen/interface/xen.h Normal file
View File

@ -0,0 +1,782 @@
/******************************************************************************
* xen.h
*
* Guest OS interface to Xen.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*
* Copyright (c) 2004, K A Fraser
*/
#ifndef __XEN_PUBLIC_XEN_H__
#define __XEN_PUBLIC_XEN_H__
#include <asm/xen/interface.h>
/*
* XEN "SYSTEM CALLS" (a.k.a. HYPERCALLS).
*/
/*
* x86_32: EAX = vector; EBX, ECX, EDX, ESI, EDI = args 1, 2, 3, 4, 5.
* EAX = return value
* (argument registers may be clobbered on return)
* x86_64: RAX = vector; RDI, RSI, RDX, R10, R8, R9 = args 1, 2, 3, 4, 5, 6.
* RAX = return value
* (argument registers not clobbered on return; RCX, R11 are)
*/
#define __HYPERVISOR_set_trap_table 0
#define __HYPERVISOR_mmu_update 1
#define __HYPERVISOR_set_gdt 2
#define __HYPERVISOR_stack_switch 3
#define __HYPERVISOR_set_callbacks 4
#define __HYPERVISOR_fpu_taskswitch 5
#define __HYPERVISOR_sched_op_compat 6
#define __HYPERVISOR_platform_op 7
#define __HYPERVISOR_set_debugreg 8
#define __HYPERVISOR_get_debugreg 9
#define __HYPERVISOR_update_descriptor 10
#define __HYPERVISOR_memory_op 12
#define __HYPERVISOR_multicall 13
#define __HYPERVISOR_update_va_mapping 14
#define __HYPERVISOR_set_timer_op 15
#define __HYPERVISOR_event_channel_op_compat 16
#define __HYPERVISOR_xen_version 17
#define __HYPERVISOR_console_io 18
#define __HYPERVISOR_physdev_op_compat 19
#define __HYPERVISOR_grant_table_op 20
#define __HYPERVISOR_vm_assist 21
#define __HYPERVISOR_update_va_mapping_otherdomain 22
#define __HYPERVISOR_iret 23 /* x86 only */
#define __HYPERVISOR_vcpu_op 24
#define __HYPERVISOR_set_segment_base 25 /* x86/64 only */
#define __HYPERVISOR_mmuext_op 26
#define __HYPERVISOR_xsm_op 27
#define __HYPERVISOR_nmi_op 28
#define __HYPERVISOR_sched_op 29
#define __HYPERVISOR_callback_op 30
#define __HYPERVISOR_xenoprof_op 31
#define __HYPERVISOR_event_channel_op 32
#define __HYPERVISOR_physdev_op 33
#define __HYPERVISOR_hvm_op 34
#define __HYPERVISOR_sysctl 35
#define __HYPERVISOR_domctl 36
#define __HYPERVISOR_kexec_op 37
#define __HYPERVISOR_tmem_op 38
#define __HYPERVISOR_xc_reserved_op 39 /* reserved for XenClient */
#define __HYPERVISOR_xenpmu_op 40
#define __HYPERVISOR_dm_op 41
/* Architecture-specific hypercall definitions. */
#define __HYPERVISOR_arch_0 48
#define __HYPERVISOR_arch_1 49
#define __HYPERVISOR_arch_2 50
#define __HYPERVISOR_arch_3 51
#define __HYPERVISOR_arch_4 52
#define __HYPERVISOR_arch_5 53
#define __HYPERVISOR_arch_6 54
#define __HYPERVISOR_arch_7 55
/*
* VIRTUAL INTERRUPTS
*
* Virtual interrupts that a guest OS may receive from Xen.
* In the side comments, 'V.' denotes a per-VCPU VIRQ while 'G.' denotes a
* global VIRQ. The former can be bound once per VCPU and cannot be re-bound.
* The latter can be allocated only once per guest: they must initially be
* allocated to VCPU0 but can subsequently be re-bound.
*/
#define VIRQ_TIMER 0 /* V. Timebase update, and/or requested timeout. */
#define VIRQ_DEBUG 1 /* V. Request guest to dump debug info. */
#define VIRQ_CONSOLE 2 /* G. (DOM0) Bytes received on emergency console. */
#define VIRQ_DOM_EXC 3 /* G. (DOM0) Exceptional event for some domain. */
#define VIRQ_TBUF 4 /* G. (DOM0) Trace buffer has records available. */
#define VIRQ_DEBUGGER 6 /* G. (DOM0) A domain has paused for debugging. */
#define VIRQ_XENOPROF 7 /* V. XenOprofile interrupt: new sample available */
#define VIRQ_CON_RING 8 /* G. (DOM0) Bytes received on console */
#define VIRQ_PCPU_STATE 9 /* G. (DOM0) PCPU state changed */
#define VIRQ_MEM_EVENT 10 /* G. (DOM0) A memory event has occured */
#define VIRQ_XC_RESERVED 11 /* G. Reserved for XenClient */
#define VIRQ_ENOMEM 12 /* G. (DOM0) Low on heap memory */
#define VIRQ_XENPMU 13 /* PMC interrupt */
/* Architecture-specific VIRQ definitions. */
#define VIRQ_ARCH_0 16
#define VIRQ_ARCH_1 17
#define VIRQ_ARCH_2 18
#define VIRQ_ARCH_3 19
#define VIRQ_ARCH_4 20
#define VIRQ_ARCH_5 21
#define VIRQ_ARCH_6 22
#define VIRQ_ARCH_7 23
#define NR_VIRQS 24
/*
* enum neg_errnoval HYPERVISOR_mmu_update(const struct mmu_update reqs[],
* unsigned count, unsigned *done_out,
* unsigned foreigndom)
* @reqs is an array of mmu_update_t structures ((ptr, val) pairs).
* @count is the length of the above array.
* @pdone is an output parameter indicating number of completed operations
* @foreigndom[15:0]: FD, the expected owner of data pages referenced in this
* hypercall invocation. Can be DOMID_SELF.
* @foreigndom[31:16]: PFD, the expected owner of pagetable pages referenced
* in this hypercall invocation. The value of this field
* (x) encodes the PFD as follows:
* x == 0 => PFD == DOMID_SELF
* x != 0 => PFD == x - 1
*
* Sub-commands: ptr[1:0] specifies the appropriate MMU_* command.
* -------------
* ptr[1:0] == MMU_NORMAL_PT_UPDATE:
* Updates an entry in a page table belonging to PFD. If updating an L1 table,
* and the new table entry is valid/present, the mapped frame must belong to
* FD. If attempting to map an I/O page then the caller assumes the privilege
* of the FD.
* FD == DOMID_IO: Permit /only/ I/O mappings, at the priv level of the caller.
* FD == DOMID_XEN: Map restricted areas of Xen's heap space.
* ptr[:2] -- Machine address of the page-table entry to modify.
* val -- Value to write.
*
* There also certain implicit requirements when using this hypercall. The
* pages that make up a pagetable must be mapped read-only in the guest.
* This prevents uncontrolled guest updates to the pagetable. Xen strictly
* enforces this, and will disallow any pagetable update which will end up
* mapping pagetable page RW, and will disallow using any writable page as a
* pagetable. In practice it means that when constructing a page table for a
* process, thread, etc, we MUST be very dilligient in following these rules:
* 1). Start with top-level page (PGD or in Xen language: L4). Fill out
* the entries.
* 2). Keep on going, filling out the upper (PUD or L3), and middle (PMD
* or L2).
* 3). Start filling out the PTE table (L1) with the PTE entries. Once
* done, make sure to set each of those entries to RO (so writeable bit
* is unset). Once that has been completed, set the PMD (L2) for this
* PTE table as RO.
* 4). When completed with all of the PMD (L2) entries, and all of them have
* been set to RO, make sure to set RO the PUD (L3). Do the same
* operation on PGD (L4) pagetable entries that have a PUD (L3) entry.
* 5). Now before you can use those pages (so setting the cr3), you MUST also
* pin them so that the hypervisor can verify the entries. This is done
* via the HYPERVISOR_mmuext_op(MMUEXT_PIN_L4_TABLE, guest physical frame
* number of the PGD (L4)). And this point the HYPERVISOR_mmuext_op(
* MMUEXT_NEW_BASEPTR, guest physical frame number of the PGD (L4)) can be
* issued.
* For 32-bit guests, the L4 is not used (as there is less pagetables), so
* instead use L3.
* At this point the pagetables can be modified using the MMU_NORMAL_PT_UPDATE
* hypercall. Also if so desired the OS can also try to write to the PTE
* and be trapped by the hypervisor (as the PTE entry is RO).
*
* To deallocate the pages, the operations are the reverse of the steps
* mentioned above. The argument is MMUEXT_UNPIN_TABLE for all levels and the
* pagetable MUST not be in use (meaning that the cr3 is not set to it).
*
* ptr[1:0] == MMU_MACHPHYS_UPDATE:
* Updates an entry in the machine->pseudo-physical mapping table.
* ptr[:2] -- Machine address within the frame whose mapping to modify.
* The frame must belong to the FD, if one is specified.
* val -- Value to write into the mapping entry.
*
* ptr[1:0] == MMU_PT_UPDATE_PRESERVE_AD:
* As MMU_NORMAL_PT_UPDATE above, but A/D bits currently in the PTE are ORed
* with those in @val.
*
* @val is usually the machine frame number along with some attributes.
* The attributes by default follow the architecture defined bits. Meaning that
* if this is a X86_64 machine and four page table layout is used, the layout
* of val is:
* - 63 if set means No execute (NX)
* - 46-13 the machine frame number
* - 12 available for guest
* - 11 available for guest
* - 10 available for guest
* - 9 available for guest
* - 8 global
* - 7 PAT (PSE is disabled, must use hypercall to make 4MB or 2MB pages)
* - 6 dirty
* - 5 accessed
* - 4 page cached disabled
* - 3 page write through
* - 2 userspace accessible
* - 1 writeable
* - 0 present
*
* The one bits that does not fit with the default layout is the PAGE_PSE
* also called PAGE_PAT). The MMUEXT_[UN]MARK_SUPER arguments to the
* HYPERVISOR_mmuext_op serve as mechanism to set a pagetable to be 4MB
* (or 2MB) instead of using the PAGE_PSE bit.
*
* The reason that the PAGE_PSE (bit 7) is not being utilized is due to Xen
* using it as the Page Attribute Table (PAT) bit - for details on it please
* refer to Intel SDM 10.12. The PAT allows to set the caching attributes of
* pages instead of using MTRRs.
*
* The PAT MSR is as follows (it is a 64-bit value, each entry is 8 bits):
* PAT4 PAT0
* +-----+-----+----+----+----+-----+----+----+
* | UC | UC- | WC | WB | UC | UC- | WC | WB | <= Linux
* +-----+-----+----+----+----+-----+----+----+
* | UC | UC- | WT | WB | UC | UC- | WT | WB | <= BIOS (default when machine boots)
* +-----+-----+----+----+----+-----+----+----+
* | rsv | rsv | WP | WC | UC | UC- | WT | WB | <= Xen
* +-----+-----+----+----+----+-----+----+----+
*
* The lookup of this index table translates to looking up
* Bit 7, Bit 4, and Bit 3 of val entry:
*
* PAT/PSE (bit 7) ... PCD (bit 4) .. PWT (bit 3).
*
* If all bits are off, then we are using PAT0. If bit 3 turned on,
* then we are using PAT1, if bit 3 and bit 4, then PAT2..
*
* As you can see, the Linux PAT1 translates to PAT4 under Xen. Which means
* that if a guest that follows Linux's PAT setup and would like to set Write
* Combined on pages it MUST use PAT4 entry. Meaning that Bit 7 (PAGE_PAT) is
* set. For example, under Linux it only uses PAT0, PAT1, and PAT2 for the
* caching as:
*
* WB = none (so PAT0)
* WC = PWT (bit 3 on)
* UC = PWT | PCD (bit 3 and 4 are on).
*
* To make it work with Xen, it needs to translate the WC bit as so:
*
* PWT (so bit 3 on) --> PAT (so bit 7 is on) and clear bit 3
*
* And to translate back it would:
*
* PAT (bit 7 on) --> PWT (bit 3 on) and clear bit 7.
*/
#define MMU_NORMAL_PT_UPDATE 0 /* checked '*ptr = val'. ptr is MA. */
#define MMU_MACHPHYS_UPDATE 1 /* ptr = MA of frame to modify entry for */
#define MMU_PT_UPDATE_PRESERVE_AD 2 /* atomically: *ptr = val | (*ptr&(A|D)) */
#define MMU_PT_UPDATE_NO_TRANSLATE 3 /* checked '*ptr = val'. ptr is MA. */
/*
* MMU EXTENDED OPERATIONS
*
* enum neg_errnoval HYPERVISOR_mmuext_op(mmuext_op_t uops[],
* unsigned int count,
* unsigned int *pdone,
* unsigned int foreigndom)
*/
/* HYPERVISOR_mmuext_op() accepts a list of mmuext_op structures.
* A foreigndom (FD) can be specified (or DOMID_SELF for none).
* Where the FD has some effect, it is described below.
*
* cmd: MMUEXT_(UN)PIN_*_TABLE
* mfn: Machine frame number to be (un)pinned as a p.t. page.
* The frame must belong to the FD, if one is specified.
*
* cmd: MMUEXT_NEW_BASEPTR
* mfn: Machine frame number of new page-table base to install in MMU.
*
* cmd: MMUEXT_NEW_USER_BASEPTR [x86/64 only]
* mfn: Machine frame number of new page-table base to install in MMU
* when in user space.
*
* cmd: MMUEXT_TLB_FLUSH_LOCAL
* No additional arguments. Flushes local TLB.
*
* cmd: MMUEXT_INVLPG_LOCAL
* linear_addr: Linear address to be flushed from the local TLB.
*
* cmd: MMUEXT_TLB_FLUSH_MULTI
* vcpumask: Pointer to bitmap of VCPUs to be flushed.
*
* cmd: MMUEXT_INVLPG_MULTI
* linear_addr: Linear address to be flushed.
* vcpumask: Pointer to bitmap of VCPUs to be flushed.
*
* cmd: MMUEXT_TLB_FLUSH_ALL
* No additional arguments. Flushes all VCPUs' TLBs.
*
* cmd: MMUEXT_INVLPG_ALL
* linear_addr: Linear address to be flushed from all VCPUs' TLBs.
*
* cmd: MMUEXT_FLUSH_CACHE
* No additional arguments. Writes back and flushes cache contents.
*
* cmd: MMUEXT_FLUSH_CACHE_GLOBAL
* No additional arguments. Writes back and flushes cache contents
* on all CPUs in the system.
*
* cmd: MMUEXT_SET_LDT
* linear_addr: Linear address of LDT base (NB. must be page-aligned).
* nr_ents: Number of entries in LDT.
*
* cmd: MMUEXT_CLEAR_PAGE
* mfn: Machine frame number to be cleared.
*
* cmd: MMUEXT_COPY_PAGE
* mfn: Machine frame number of the destination page.
* src_mfn: Machine frame number of the source page.
*
* cmd: MMUEXT_[UN]MARK_SUPER
* mfn: Machine frame number of head of superpage to be [un]marked.
*/
#define MMUEXT_PIN_L1_TABLE 0
#define MMUEXT_PIN_L2_TABLE 1
#define MMUEXT_PIN_L3_TABLE 2
#define MMUEXT_PIN_L4_TABLE 3
#define MMUEXT_UNPIN_TABLE 4
#define MMUEXT_NEW_BASEPTR 5
#define MMUEXT_TLB_FLUSH_LOCAL 6
#define MMUEXT_INVLPG_LOCAL 7
#define MMUEXT_TLB_FLUSH_MULTI 8
#define MMUEXT_INVLPG_MULTI 9
#define MMUEXT_TLB_FLUSH_ALL 10
#define MMUEXT_INVLPG_ALL 11
#define MMUEXT_FLUSH_CACHE 12
#define MMUEXT_SET_LDT 13
#define MMUEXT_NEW_USER_BASEPTR 15
#define MMUEXT_CLEAR_PAGE 16
#define MMUEXT_COPY_PAGE 17
#define MMUEXT_FLUSH_CACHE_GLOBAL 18
#define MMUEXT_MARK_SUPER 19
#define MMUEXT_UNMARK_SUPER 20
#ifndef __ASSEMBLY__
struct mmuext_op {
unsigned int cmd;
union {
/* [UN]PIN_TABLE, NEW_BASEPTR, NEW_USER_BASEPTR
* CLEAR_PAGE, COPY_PAGE, [UN]MARK_SUPER */
xen_pfn_t mfn;
/* INVLPG_LOCAL, INVLPG_ALL, SET_LDT */
unsigned long linear_addr;
} arg1;
union {
/* SET_LDT */
unsigned int nr_ents;
/* TLB_FLUSH_MULTI, INVLPG_MULTI */
void *vcpumask;
/* COPY_PAGE */
xen_pfn_t src_mfn;
} arg2;
};
DEFINE_GUEST_HANDLE_STRUCT(mmuext_op);
#endif
/* These are passed as 'flags' to update_va_mapping. They can be ORed. */
/* When specifying UVMF_MULTI, also OR in a pointer to a CPU bitmap. */
/* UVMF_LOCAL is merely UVMF_MULTI with a NULL bitmap pointer. */
#define UVMF_NONE (0UL<<0) /* No flushing at all. */
#define UVMF_TLB_FLUSH (1UL<<0) /* Flush entire TLB(s). */
#define UVMF_INVLPG (2UL<<0) /* Flush only one entry. */
#define UVMF_FLUSHTYPE_MASK (3UL<<0)
#define UVMF_MULTI (0UL<<2) /* Flush subset of TLBs. */
#define UVMF_LOCAL (0UL<<2) /* Flush local TLB. */
#define UVMF_ALL (1UL<<2) /* Flush all TLBs. */
/*
* Commands to HYPERVISOR_console_io().
*/
#define CONSOLEIO_write 0
#define CONSOLEIO_read 1
/*
* Commands to HYPERVISOR_vm_assist().
*/
#define VMASST_CMD_enable 0
#define VMASST_CMD_disable 1
/* x86/32 guests: simulate full 4GB segment limits. */
#define VMASST_TYPE_4gb_segments 0
/* x86/32 guests: trap (vector 15) whenever above vmassist is used. */
#define VMASST_TYPE_4gb_segments_notify 1
/*
* x86 guests: support writes to bottom-level PTEs.
* NB1. Page-directory entries cannot be written.
* NB2. Guest must continue to remove all writable mappings of PTEs.
*/
#define VMASST_TYPE_writable_pagetables 2
/* x86/PAE guests: support PDPTs above 4GB. */
#define VMASST_TYPE_pae_extended_cr3 3
/*
* x86 guests: Sane behaviour for virtual iopl
* - virtual iopl updated from do_iret() hypercalls.
* - virtual iopl reported in bounce frames.
* - guest kernels assumed to be level 0 for the purpose of iopl checks.
*/
#define VMASST_TYPE_architectural_iopl 4
/*
* All guests: activate update indicator in vcpu_runstate_info
* Enable setting the XEN_RUNSTATE_UPDATE flag in guest memory mapped
* vcpu_runstate_info during updates of the runstate information.
*/
#define VMASST_TYPE_runstate_update_flag 5
#define MAX_VMASST_TYPE 5
#ifndef __ASSEMBLY__
typedef uint16_t domid_t;
/* Domain ids >= DOMID_FIRST_RESERVED cannot be used for ordinary domains. */
#define DOMID_FIRST_RESERVED (0x7FF0U)
/* DOMID_SELF is used in certain contexts to refer to oneself. */
#define DOMID_SELF (0x7FF0U)
/*
* DOMID_IO is used to restrict page-table updates to mapping I/O memory.
* Although no Foreign Domain need be specified to map I/O pages, DOMID_IO
* is useful to ensure that no mappings to the OS's own heap are accidentally
* installed. (e.g., in Linux this could cause havoc as reference counts
* aren't adjusted on the I/O-mapping code path).
* This only makes sense in MMUEXT_SET_FOREIGNDOM, but in that context can
* be specified by any calling domain.
*/
#define DOMID_IO (0x7FF1U)
/*
* DOMID_XEN is used to allow privileged domains to map restricted parts of
* Xen's heap space (e.g., the machine_to_phys table).
* This only makes sense in MMUEXT_SET_FOREIGNDOM, and is only permitted if
* the caller is privileged.
*/
#define DOMID_XEN (0x7FF2U)
/* DOMID_COW is used as the owner of sharable pages */
#define DOMID_COW (0x7FF3U)
/* DOMID_INVALID is used to identify pages with unknown owner. */
#define DOMID_INVALID (0x7FF4U)
/* Idle domain. */
#define DOMID_IDLE (0x7FFFU)
/*
* Send an array of these to HYPERVISOR_mmu_update().
* NB. The fields are natural pointer/address size for this architecture.
*/
struct mmu_update {
uint64_t ptr; /* Machine address of PTE. */
uint64_t val; /* New contents of PTE. */
};
DEFINE_GUEST_HANDLE_STRUCT(mmu_update);
/*
* Send an array of these to HYPERVISOR_multicall().
* NB. The fields are logically the natural register size for this
* architecture. In cases where xen_ulong_t is larger than this then
* any unused bits in the upper portion must be zero.
*/
struct multicall_entry {
xen_ulong_t op;
xen_long_t result;
xen_ulong_t args[6];
};
DEFINE_GUEST_HANDLE_STRUCT(multicall_entry);
struct vcpu_time_info {
/*
* Updates to the following values are preceded and followed
* by an increment of 'version'. The guest can therefore
* detect updates by looking for changes to 'version'. If the
* least-significant bit of the version number is set then an
* update is in progress and the guest must wait to read a
* consistent set of values. The correct way to interact with
* the version number is similar to Linux's seqlock: see the
* implementations of read_seqbegin/read_seqretry.
*/
uint32_t version;
uint32_t pad0;
uint64_t tsc_timestamp; /* TSC at last update of time vals. */
uint64_t system_time; /* Time, in nanosecs, since boot. */
/*
* Current system time:
* system_time + ((tsc - tsc_timestamp) << tsc_shift) * tsc_to_system_mul
* CPU frequency (Hz):
* ((10^9 << 32) / tsc_to_system_mul) >> tsc_shift
*/
uint32_t tsc_to_system_mul;
int8_t tsc_shift;
int8_t pad1[3];
}; /* 32 bytes */
struct vcpu_info {
/*
* 'evtchn_upcall_pending' is written non-zero by Xen to indicate
* a pending notification for a particular VCPU. It is then cleared
* by the guest OS /before/ checking for pending work, thus avoiding
* a set-and-check race. Note that the mask is only accessed by Xen
* on the CPU that is currently hosting the VCPU. This means that the
* pending and mask flags can be updated by the guest without special
* synchronisation (i.e., no need for the x86 LOCK prefix).
* This may seem suboptimal because if the pending flag is set by
* a different CPU then an IPI may be scheduled even when the mask
* is set. However, note:
* 1. The task of 'interrupt holdoff' is covered by the per-event-
* channel mask bits. A 'noisy' event that is continually being
* triggered can be masked at source at this very precise
* granularity.
* 2. The main purpose of the per-VCPU mask is therefore to restrict
* reentrant execution: whether for concurrency control, or to
* prevent unbounded stack usage. Whatever the purpose, we expect
* that the mask will be asserted only for short periods at a time,
* and so the likelihood of a 'spurious' IPI is suitably small.
* The mask is read before making an event upcall to the guest: a
* non-zero mask therefore guarantees that the VCPU will not receive
* an upcall activation. The mask is cleared when the VCPU requests
* to block: this avoids wakeup-waiting races.
*/
uint8_t evtchn_upcall_pending;
uint8_t evtchn_upcall_mask;
xen_ulong_t evtchn_pending_sel;
struct arch_vcpu_info arch;
struct pvclock_vcpu_time_info time;
}; /* 64 bytes (x86) */
/*
* Xen/kernel shared data -- pointer provided in start_info.
* NB. We expect that this struct is smaller than a page.
*/
struct shared_info {
struct vcpu_info vcpu_info[MAX_VIRT_CPUS];
/*
* A domain can create "event channels" on which it can send and receive
* asynchronous event notifications. There are three classes of event that
* are delivered by this mechanism:
* 1. Bi-directional inter- and intra-domain connections. Domains must
* arrange out-of-band to set up a connection (usually by allocating
* an unbound 'listener' port and avertising that via a storage service
* such as xenstore).
* 2. Physical interrupts. A domain with suitable hardware-access
* privileges can bind an event-channel port to a physical interrupt
* source.
* 3. Virtual interrupts ('events'). A domain can bind an event-channel
* port to a virtual interrupt source, such as the virtual-timer
* device or the emergency console.
*
* Event channels are addressed by a "port index". Each channel is
* associated with two bits of information:
* 1. PENDING -- notifies the domain that there is a pending notification
* to be processed. This bit is cleared by the guest.
* 2. MASK -- if this bit is clear then a 0->1 transition of PENDING
* will cause an asynchronous upcall to be scheduled. This bit is only
* updated by the guest. It is read-only within Xen. If a channel
* becomes pending while the channel is masked then the 'edge' is lost
* (i.e., when the channel is unmasked, the guest must manually handle
* pending notifications as no upcall will be scheduled by Xen).
*
* To expedite scanning of pending notifications, any 0->1 pending
* transition on an unmasked channel causes a corresponding bit in a
* per-vcpu selector word to be set. Each bit in the selector covers a
* 'C long' in the PENDING bitfield array.
*/
xen_ulong_t evtchn_pending[sizeof(xen_ulong_t) * 8];
xen_ulong_t evtchn_mask[sizeof(xen_ulong_t) * 8];
/*
* Wallclock time: updated only by control software. Guests should base
* their gettimeofday() syscall on this wallclock-base value.
*/
struct pvclock_wall_clock wc;
struct arch_shared_info arch;
};
/*
* Start-of-day memory layout
*
* 1. The domain is started within contiguous virtual-memory region.
* 2. The contiguous region begins and ends on an aligned 4MB boundary.
* 3. This the order of bootstrap elements in the initial virtual region:
* a. relocated kernel image
* b. initial ram disk [mod_start, mod_len]
* (may be omitted)
* c. list of allocated page frames [mfn_list, nr_pages]
* (unless relocated due to XEN_ELFNOTE_INIT_P2M)
* d. start_info_t structure [register ESI (x86)]
* in case of dom0 this page contains the console info, too
* e. unless dom0: xenstore ring page
* f. unless dom0: console ring page
* g. bootstrap page tables [pt_base, CR3 (x86)]
* h. bootstrap stack [register ESP (x86)]
* 4. Bootstrap elements are packed together, but each is 4kB-aligned.
* 5. The list of page frames forms a contiguous 'pseudo-physical' memory
* layout for the domain. In particular, the bootstrap virtual-memory
* region is a 1:1 mapping to the first section of the pseudo-physical map.
* 6. All bootstrap elements are mapped read-writable for the guest OS. The
* only exception is the bootstrap page table, which is mapped read-only.
* 7. There is guaranteed to be at least 512kB padding after the final
* bootstrap element. If necessary, the bootstrap virtual region is
* extended by an extra 4MB to ensure this.
*/
#define MAX_GUEST_CMDLINE 1024
struct start_info {
/* THE FOLLOWING ARE FILLED IN BOTH ON INITIAL BOOT AND ON RESUME. */
char magic[32]; /* "xen-<version>-<platform>". */
unsigned long nr_pages; /* Total pages allocated to this domain. */
unsigned long shared_info; /* MACHINE address of shared info struct. */
uint32_t flags; /* SIF_xxx flags. */
xen_pfn_t store_mfn; /* MACHINE page number of shared page. */
uint32_t store_evtchn; /* Event channel for store communication. */
union {
struct {
xen_pfn_t mfn; /* MACHINE page number of console page. */
uint32_t evtchn; /* Event channel for console page. */
} domU;
struct {
uint32_t info_off; /* Offset of console_info struct. */
uint32_t info_size; /* Size of console_info struct from start.*/
} dom0;
} console;
/* THE FOLLOWING ARE ONLY FILLED IN ON INITIAL BOOT (NOT RESUME). */
unsigned long pt_base; /* VIRTUAL address of page directory. */
unsigned long nr_pt_frames; /* Number of bootstrap p.t. frames. */
unsigned long mfn_list; /* VIRTUAL address of page-frame list. */
unsigned long mod_start; /* VIRTUAL address of pre-loaded module. */
unsigned long mod_len; /* Size (bytes) of pre-loaded module. */
int8_t cmd_line[MAX_GUEST_CMDLINE];
/* The pfn range here covers both page table and p->m table frames. */
unsigned long first_p2m_pfn;/* 1st pfn forming initial P->M table. */
unsigned long nr_p2m_frames;/* # of pfns forming initial P->M table. */
};
/* These flags are passed in the 'flags' field of start_info_t. */
#define SIF_PRIVILEGED (1<<0) /* Is the domain privileged? */
#define SIF_INITDOMAIN (1<<1) /* Is this the initial control domain? */
#define SIF_MULTIBOOT_MOD (1<<2) /* Is mod_start a multiboot module? */
#define SIF_MOD_START_PFN (1<<3) /* Is mod_start a PFN? */
#define SIF_VIRT_P2M_4TOOLS (1<<4) /* Do Xen tools understand a virt. mapped */
/* P->M making the 3 level tree obsolete? */
#define SIF_PM_MASK (0xFF<<8) /* reserve 1 byte for xen-pm options */
/*
* A multiboot module is a package containing modules very similar to a
* multiboot module array. The only differences are:
* - the array of module descriptors is by convention simply at the beginning
* of the multiboot module,
* - addresses in the module descriptors are based on the beginning of the
* multiboot module,
* - the number of modules is determined by a termination descriptor that has
* mod_start == 0.
*
* This permits to both build it statically and reference it in a configuration
* file, and let the PV guest easily rebase the addresses to virtual addresses
* and at the same time count the number of modules.
*/
struct xen_multiboot_mod_list {
/* Address of first byte of the module */
uint32_t mod_start;
/* Address of last byte of the module (inclusive) */
uint32_t mod_end;
/* Address of zero-terminated command line */
uint32_t cmdline;
/* Unused, must be zero */
uint32_t pad;
};
/*
* The console structure in start_info.console.dom0
*
* This structure includes a variety of information required to
* have a working VGA/VESA console.
*/
struct dom0_vga_console_info {
uint8_t video_type;
#define XEN_VGATYPE_TEXT_MODE_3 0x03
#define XEN_VGATYPE_VESA_LFB 0x23
#define XEN_VGATYPE_EFI_LFB 0x70
union {
struct {
/* Font height, in pixels. */
uint16_t font_height;
/* Cursor location (column, row). */
uint16_t cursor_x, cursor_y;
/* Number of rows and columns (dimensions in characters). */
uint16_t rows, columns;
} text_mode_3;
struct {
/* Width and height, in pixels. */
uint16_t width, height;
/* Bytes per scan line. */
uint16_t bytes_per_line;
/* Bits per pixel. */
uint16_t bits_per_pixel;
/* LFB physical address, and size (in units of 64kB). */
uint32_t lfb_base;
uint32_t lfb_size;
/* RGB mask offsets and sizes, as defined by VBE 1.2+ */
uint8_t red_pos, red_size;
uint8_t green_pos, green_size;
uint8_t blue_pos, blue_size;
uint8_t rsvd_pos, rsvd_size;
/* VESA capabilities (offset 0xa, VESA command 0x4f00). */
uint32_t gbl_caps;
/* Mode attributes (offset 0x0, VESA command 0x4f01). */
uint16_t mode_attrs;
} vesa_lfb;
} u;
};
typedef uint64_t cpumap_t;
typedef uint8_t xen_domain_handle_t[16];
/* Turn a plain number into a C unsigned long constant. */
#define __mk_unsigned_long(x) x ## UL
#define mk_unsigned_long(x) __mk_unsigned_long(x)
#define TMEM_SPEC_VERSION 1
struct tmem_op {
uint32_t cmd;
int32_t pool_id;
union {
struct { /* for cmd == TMEM_NEW_POOL */
uint64_t uuid[2];
uint32_t flags;
} new;
struct {
uint64_t oid[3];
uint32_t index;
uint32_t tmem_offset;
uint32_t pfn_offset;
uint32_t len;
GUEST_HANDLE(void) gmfn; /* guest machine page frame */
} gen;
} u;
};
DEFINE_GUEST_HANDLE(u64);
#else /* __ASSEMBLY__ */
/* In assembly code we cannot use C numeric constant suffixes. */
#define mk_unsigned_long(x) x
#endif /* !__ASSEMBLY__ */
#endif /* __XEN_PUBLIC_XEN_H__ */