ff662b5c98
o Add support for backend devices (e.g. blkback) o Implement extensions to the Xen para-virtualized block API to allow for larger and more outstanding I/Os. o Import a completely rewritten block back driver with support for fronting I/O to both raw devices and files. o General cleanup and documentation of the XenBus and XenStore support code. o Robustness and performance updates for the block front driver. o Fixes to the netfront driver. Sponsored by: Spectra Logic Corporation sys/xen/xenbus/init.txt: Deleted: This file explains the Linux method for XenBus device enumeration and thus does not apply to FreeBSD's NewBus approach. sys/xen/xenbus/xenbus_probe_backend.c: Deleted: Linux version of backend XenBus service routines. It was never ported to FreeBSD. See xenbusb.c, xenbusb_if.m, xenbusb_front.c xenbusb_back.c for details of FreeBSD's XenBus support. sys/xen/xenbus/xenbusvar.h: sys/xen/xenbus/xenbus_xs.c: sys/xen/xenbus/xenbus_comms.c: sys/xen/xenbus/xenbus_comms.h: sys/xen/xenstore/xenstorevar.h: sys/xen/xenstore/xenstore.c: Split XenStore into its own tree. XenBus is a software layer built on top of XenStore. The old arrangement and the naming of some structures and functions blurred these lines making it difficult to discern what services are provided by which layer and at what times these services are available (e.g. during system startup and shutdown). sys/xen/xenbus/xenbus_client.c: sys/xen/xenbus/xenbus.c: sys/xen/xenbus/xenbus_probe.c: sys/xen/xenbus/xenbusb.c: sys/xen/xenbus/xenbusb.h: Split up XenBus code into methods available for use by client drivers (xenbus.c) and code used by the XenBus "bus code" to enumerate, attach, detach, and service bus drivers. sys/xen/reboot.c: sys/dev/xen/control/control.c: Add a XenBus front driver for handling shutdown, reboot, suspend, and resume events published in the XenStore. Move all PV suspend/reboot support from reboot.c into this driver. sys/xen/blkif.h: New file from Xen vendor with macros and structures used by a block back driver to service requests from a VM running a different ABI (e.g. amd64 back with i386 front). sys/conf/files: Adjust kernel build spec for new XenBus/XenStore layout and added Xen functionality. sys/dev/xen/balloon/balloon.c: sys/dev/xen/netfront/netfront.c: sys/dev/xen/blkfront/blkfront.c: sys/xen/xenbus/... sys/xen/xenstore/... o Rename XenStore APIs and structures from xenbus_* to xs_*. o Adjust to use of M_XENBUS and M_XENSTORE malloc types for allocation of objects returned by these APIs. o Adjust for changes in the bus interface for Xen drivers. sys/xen/xenbus/... sys/xen/xenstore/... Add Doxygen comments for these interfaces and the code that implements them. sys/dev/xen/blkback/blkback.c: o Rewrite the Block Back driver to attach properly via newbus, operate correctly in both PV and HVM mode regardless of domain (e.g. can be in a DOM other than 0), and to deal with the latest metadata available in XenStore for block devices. o Allow users to specify a file as a backend to blkback, in addition to character devices. Use the namei lookup of the backend path to automatically configure, based on file type, the appropriate backend method. The current implementation is limited to a single outstanding I/O at a time to file backed storage. sys/dev/xen/blkback/blkback.c: sys/xen/interface/io/blkif.h: sys/xen/blkif.h: sys/dev/xen/blkfront/blkfront.c: sys/dev/xen/blkfront/block.h: Extend the Xen blkif API: Negotiable request size and number of requests. This change extends the information recorded in the XenStore allowing block front/back devices to negotiate for optimal I/O parameters. This has been achieved without sacrificing backward compatibility with drivers that are unaware of these protocol enhancements. The extensions center around the connection protocol which now includes these additions: o The back-end device publishes its maximum supported values for, request I/O size, the number of page segments that can be associated with a request, the maximum number of requests that can be concurrently active, and the maximum number of pages that can be in the shared request ring. These values are published before the back-end enters the XenbusStateInitWait state. o The front-end waits for the back-end to enter either the InitWait or Initialize state. At this point, the front end limits it's own capabilities to the lesser of the values it finds published by the backend, it's own maximums, or, should any back-end data be missing in the store, the values supported by the original protocol. It then initializes it's internal data structures including allocation of the shared ring, publishes its maximum capabilities to the XenStore and transitions to the Initialized state. o The back-end waits for the front-end to enter the Initalized state. At this point, the back end limits it's own capabilities to the lesser of the values it finds published by the frontend, it's own maximums, or, should any front-end data be missing in the store, the values supported by the original protocol. It then initializes it's internal data structures, attaches to the shared ring and transitions to the Connected state. o The front-end waits for the back-end to enter the Connnected state, transitions itself to the connected state, and can commence I/O. Although an updated front-end driver must be aware of the back-end's InitWait state, the back-end has been coded such that it can tolerate a front-end that skips this step and transitions directly to the Initialized state without waiting for the back-end. sys/xen/interface/io/blkif.h: o Increase BLKIF_MAX_SEGMENTS_PER_REQUEST to 255. This is the maximum number possible without changing the blkif request header structure (nr_segs is a uint8_t). o Add two new constants: BLKIF_MAX_SEGMENTS_PER_HEADER_BLOCK, and BLKIF_MAX_SEGMENTS_PER_SEGMENT_BLOCK. These respectively indicate the number of segments that can fit in the first ring-buffer entry of a request, and for each subsequent (sg element only) ring-buffer entry associated with the "header" ring-buffer entry of the request. o Add the blkif_request_segment_t typedef for segment elements. o Add the BLKRING_GET_SG_REQUEST() macro which wraps the RING_GET_REQUEST() macro and returns a properly cast pointer to an array of blkif_request_segment_ts. o Add the BLKIF_SEGS_TO_BLOCKS() macro which calculates the number of ring entries that will be consumed by a blkif request with the given number of segments. sys/xen/blkif.h: o Update for changes in interface/io/blkif.h macros. o Update the BLKIF_MAX_RING_REQUESTS() macro to take the ring size as an argument to allow this calculation on multi-page rings. o Add a companion macro to BLKIF_MAX_RING_REQUESTS(), BLKIF_RING_PAGES(). This macro determines the number of ring pages required in order to support a ring with the supplied number of request blocks. sys/dev/xen/blkback/blkback.c: sys/dev/xen/blkfront/blkfront.c: sys/dev/xen/blkfront/block.h: o Negotiate with the other-end with the following limits: Reqeust Size: MAXPHYS Max Segments: (MAXPHYS/PAGE_SIZE) + 1 Max Requests: 256 Max Ring Pages: Sufficient to support Max Requests with Max Segments. o Dynamically allocate request pools and segemnts-per-request. o Update ring allocation/attachment code to support a multi-page shared ring. o Update routines that access the shared ring to handle multi-block requests. sys/dev/xen/blkfront/blkfront.c: o Track blkfront allocations in a blkfront driver specific malloc pool. o Strip out XenStore transaction retry logic in the connection code. Transactions only need to be used when the update to multiple XenStore nodes must be atomic. That is not the case here. o Fully disable blkif_resume() until it can be fixed properly (it didn't work before this change). o Destroy bus-dma objects during device instance tear-down. o Properly handle backend devices with powef-of-2 sector sizes larger than 512b. sys/dev/xen/blkback/blkback.c: Advertise support for and implement the BLKIF_OP_WRITE_BARRIER and BLKIF_OP_FLUSH_DISKCACHE blkif opcodes using BIO_FLUSH and the BIO_ORDERED attribute of bios. sys/dev/xen/blkfront/blkfront.c: sys/dev/xen/blkfront/block.h: Fix various bugs in blkfront. o gnttab_alloc_grant_references() returns 0 for success and non-zero for failure. The check for < 0 is a leftover Linuxism. o When we negotiate with blkback and have to reduce some of our capabilities, print out the original and reduced capability before changing the local capability. So the user now gets the correct information. o Fix blkif_restart_queue_callback() formatting. Make sure we hold the mutex in that function before calling xb_startio(). o Fix a couple of KASSERT()s. o Fix a check in the xb_remove_* macro to be a little more specific. sys/xen/gnttab.h: sys/xen/gnttab.c: Define GNTTAB_LIST_END publicly as GRANT_REF_INVALID. sys/dev/xen/netfront/netfront.c: Use GRANT_REF_INVALID instead of driver private definitions of the same constant. sys/xen/gnttab.h: sys/xen/gnttab.c: Add the gnttab_end_foreign_access_references() API. This API allows a client to batch the release of an array of grant references, instead of coding a private for loop. The implementation takes advantage of this batching to reduce lock overhead to one acquisition and release per-batch instead of per-freed grant reference. While here, reduce the duration the gnttab_list_lock is held during gnttab_free_grant_references() operations. The search to find the tail of the incoming free list does not rely on global state and so can be performed without holding the lock. sys/dev/xen/xenpci/evtchn.c: sys/dev/xen/evtchn/evtchn.c: sys/xen/xen_intr.h: o Implement the bind_interdomain_evtchn_to_irqhandler API for HVM mode. This allows an HVM domain to serve back end devices to other domains. This API is already implemented for PV mode. o Synchronize the API between HVM and PV. sys/dev/xen/xenpci/xenpci.c: o Scan the full region of CPUID space in which the Xen VMM interface may be implemented. On systems using SuSE as a Dom0 where the Viridian API is also exported, the VMM interface is above the region we used to search. o Pass through bus_alloc_resource() calls so that XenBus drivers attaching on an HVM system can allocate unused physical address space from the nexus. The block back driver makes use of this facility. sys/i386/xen/xen_machdep.c: Use the correct type for accessing the statically mapped xenstore metadata. sys/xen/interface/hvm/params.h: sys/xen/xenstore/xenstore.c: Move hvm_get_parameter() to the correct global header file instead of as a private method to the XenStore. sys/xen/interface/io/protocols.h: Sync with vendor. sys/xeninterface/io/ring.h: Add macro for calculating the number of ring pages needed for an N deep ring. To avoid duplication within the macros, create and use the new __RING_HEADER_SIZE() macro. This macro calculates the size of the ring book keeping struct (producer/consumer indexes, etc.) that resides at the head of the ring. Add the __RING_PAGES() macro which calculates the number of shared ring pages required to support a ring with the given number of requests. These APIs are used to support the multi-page ring version of the Xen block API. sys/xeninterface/io/xenbus.h: Add Comments. sys/xen/xenbus/... o Refactor the FreeBSD XenBus support code to allow for both front and backend device attachments. o Make use of new config_intr_hook capabilities to allow front and back devices to be probed/attached in parallel. o Fix bugs in probe/attach state machine that could cause the system to hang when confronted with a failure either in the local domain or in a remote domain to which one of our driver instances is attaching. o Publish all required state to the XenStore on device detach and failure. The majority of the missing functionality was for serving as a back end since the typical "hot-plug" scripts in Dom0 don't handle the case of cleaning up for a "service domain" that is not itself. o Add dynamic sysctl nodes exposing the generic ivars of XenBus devices. o Add doxygen style comments to the majority of the code. o Cleanup types, formatting, etc. sys/xen/xenbus/xenbusb.c: Common code used by both front and back XenBus busses. sys/xen/xenbus/xenbusb_if.m: Method definitions for a XenBus bus. sys/xen/xenbus/xenbusb_front.c: sys/xen/xenbus/xenbusb_back.c: XenBus bus specialization for front and back devices. MFC after: 1 month
494 lines
13 KiB
C
494 lines
13 KiB
C
/*-
|
|
* Copyright (c) 2010 Justin T. Gibbs, Spectra Logic Corporation
|
|
* All rights reserved.
|
|
*
|
|
* Redistribution and use in source and binary forms, with or without
|
|
* modification, are permitted provided that the following conditions
|
|
* are met:
|
|
* 1. Redistributions of source code must retain the above copyright
|
|
* notice, this list of conditions, and the following disclaimer,
|
|
* without modification.
|
|
* 2. Redistributions in binary form must reproduce at minimum a disclaimer
|
|
* substantially similar to the "NO WARRANTY" disclaimer below
|
|
* ("Disclaimer") and any redistribution must be conditioned upon
|
|
* including a substantially similar Disclaimer requirement for further
|
|
* binary redistribution.
|
|
*
|
|
* NO WARRANTY
|
|
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
|
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
|
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTIBILITY AND FITNESS FOR
|
|
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
|
* HOLDERS OR CONTRIBUTORS BE LIABLE FOR SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
|
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
|
|
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
|
|
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
|
|
* STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING
|
|
* IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
|
|
* POSSIBILITY OF SUCH DAMAGES.
|
|
*/
|
|
|
|
/*-
|
|
* PV suspend/resume support:
|
|
*
|
|
* Copyright (c) 2004 Christian Limpach.
|
|
* Copyright (c) 2004-2006,2008 Kip Macy
|
|
* All rights reserved.
|
|
*
|
|
* Redistribution and use in source and binary forms, with or without
|
|
* modification, are permitted provided that the following conditions
|
|
* are met:
|
|
* 1. Redistributions of source code must retain the above copyright
|
|
* notice, this list of conditions and the following disclaimer.
|
|
* 2. Redistributions in binary form must reproduce the above copyright
|
|
* notice, this list of conditions and the following disclaimer in the
|
|
* documentation and/or other materials provided with the distribution.
|
|
* 3. All advertising materials mentioning features or use of this software
|
|
* must display the following acknowledgement:
|
|
* This product includes software developed by Christian Limpach.
|
|
* 4. The name of the author may not be used to endorse or promote products
|
|
* derived from this software without specific prior written permission.
|
|
*
|
|
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
|
|
* IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
|
|
* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
|
|
* IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
|
|
* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
|
|
* NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
|
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
|
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
|
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
|
|
* THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
*/
|
|
|
|
/*-
|
|
* HVM suspend/resume support:
|
|
*
|
|
* Copyright (c) 2008 Citrix Systems, Inc.
|
|
* All rights reserved.
|
|
*
|
|
* Redistribution and use in source and binary forms, with or without
|
|
* modification, are permitted provided that the following conditions
|
|
* are met:
|
|
* 1. Redistributions of source code must retain the above copyright
|
|
* notice, this list of conditions and the following disclaimer.
|
|
* 2. Redistributions in binary form must reproduce the above copyright
|
|
* notice, this list of conditions and the following disclaimer in the
|
|
* documentation and/or other materials provided with the distribution.
|
|
*
|
|
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
|
|
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
|
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
|
* ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
|
|
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
|
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
|
|
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
|
|
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
|
|
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
|
|
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
|
|
* SUCH DAMAGE.
|
|
*/
|
|
#include <sys/cdefs.h>
|
|
__FBSDID("$FreeBSD$");
|
|
|
|
/**
|
|
* \file control.c
|
|
*
|
|
* \brief Device driver to repond to control domain events that impact
|
|
* this VM.
|
|
*/
|
|
|
|
#include <sys/param.h>
|
|
#include <sys/systm.h>
|
|
#include <sys/kernel.h>
|
|
#include <sys/malloc.h>
|
|
|
|
#include <sys/bio.h>
|
|
#include <sys/bus.h>
|
|
#include <sys/conf.h>
|
|
#include <sys/disk.h>
|
|
#include <sys/fcntl.h>
|
|
#include <sys/filedesc.h>
|
|
#include <sys/kdb.h>
|
|
#include <sys/module.h>
|
|
#include <sys/namei.h>
|
|
#include <sys/proc.h>
|
|
#include <sys/reboot.h>
|
|
#include <sys/rman.h>
|
|
#include <sys/taskqueue.h>
|
|
#include <sys/types.h>
|
|
#include <sys/vnode.h>
|
|
|
|
#ifndef XENHVM
|
|
#include <sys/sched.h>
|
|
#include <sys/smp.h>
|
|
#endif
|
|
|
|
|
|
#include <geom/geom.h>
|
|
|
|
#include <machine/_inttypes.h>
|
|
#include <machine/xen/xen-os.h>
|
|
|
|
#include <vm/vm.h>
|
|
#include <vm/vm_extern.h>
|
|
#include <vm/vm_kern.h>
|
|
|
|
#include <xen/blkif.h>
|
|
#include <xen/evtchn.h>
|
|
#include <xen/gnttab.h>
|
|
#include <xen/xen_intr.h>
|
|
|
|
#include <xen/interface/event_channel.h>
|
|
#include <xen/interface/grant_table.h>
|
|
|
|
#include <xen/xenbus/xenbusvar.h>
|
|
|
|
#define NUM_ELEMENTS(x) (sizeof(x) / sizeof(*(x)))
|
|
|
|
/*--------------------------- Forward Declarations --------------------------*/
|
|
/** Function signature for shutdown event handlers. */
|
|
typedef void (xctrl_shutdown_handler_t)(void);
|
|
|
|
static xctrl_shutdown_handler_t xctrl_poweroff;
|
|
static xctrl_shutdown_handler_t xctrl_reboot;
|
|
static xctrl_shutdown_handler_t xctrl_suspend;
|
|
static xctrl_shutdown_handler_t xctrl_crash;
|
|
static xctrl_shutdown_handler_t xctrl_halt;
|
|
|
|
/*-------------------------- Private Data Structures -------------------------*/
|
|
/** Element type for lookup table of event name to handler. */
|
|
struct xctrl_shutdown_reason {
|
|
const char *name;
|
|
xctrl_shutdown_handler_t *handler;
|
|
};
|
|
|
|
/** Lookup table for shutdown event name to handler. */
|
|
static struct xctrl_shutdown_reason xctrl_shutdown_reasons[] = {
|
|
{ "poweroff", xctrl_poweroff },
|
|
{ "reboot", xctrl_reboot },
|
|
{ "suspend", xctrl_suspend },
|
|
{ "crash", xctrl_crash },
|
|
{ "halt", xctrl_halt },
|
|
};
|
|
|
|
struct xctrl_softc {
|
|
|
|
/** Must be first */
|
|
struct xs_watch xctrl_watch;
|
|
};
|
|
|
|
/*------------------------------ Event Handlers ------------------------------*/
|
|
static void
|
|
xctrl_poweroff()
|
|
{
|
|
shutdown_nice(RB_POWEROFF|RB_HALT);
|
|
}
|
|
|
|
static void
|
|
xctrl_reboot()
|
|
{
|
|
shutdown_nice(0);
|
|
}
|
|
|
|
#ifndef XENHVM
|
|
extern void xencons_suspend(void);
|
|
extern void xencons_resume(void);
|
|
|
|
/* Full PV mode suspension. */
|
|
static void
|
|
xctrl_suspend()
|
|
{
|
|
int i, j, k, fpp;
|
|
unsigned long max_pfn, start_info_mfn;
|
|
|
|
#ifdef SMP
|
|
cpumask_t map;
|
|
/*
|
|
* Bind us to CPU 0 and stop any other VCPUs.
|
|
*/
|
|
thread_lock(curthread);
|
|
sched_bind(curthread, 0);
|
|
thread_unlock(curthread);
|
|
KASSERT(PCPU_GET(cpuid) == 0, ("xen_suspend: not running on cpu 0"));
|
|
|
|
map = PCPU_GET(other_cpus) & ~stopped_cpus;
|
|
if (map)
|
|
stop_cpus(map);
|
|
#endif
|
|
|
|
if (DEVICE_SUSPEND(root_bus) != 0) {
|
|
printf("xen_suspend: device_suspend failed\n");
|
|
#ifdef SMP
|
|
if (map)
|
|
restart_cpus(map);
|
|
#endif
|
|
return;
|
|
}
|
|
|
|
local_irq_disable();
|
|
|
|
xencons_suspend();
|
|
gnttab_suspend();
|
|
|
|
max_pfn = HYPERVISOR_shared_info->arch.max_pfn;
|
|
|
|
void *shared_info = HYPERVISOR_shared_info;
|
|
HYPERVISOR_shared_info = NULL;
|
|
pmap_kremove((vm_offset_t) shared_info);
|
|
PT_UPDATES_FLUSH();
|
|
|
|
xen_start_info->store_mfn = MFNTOPFN(xen_start_info->store_mfn);
|
|
xen_start_info->console.domU.mfn = MFNTOPFN(xen_start_info->console.domU.mfn);
|
|
|
|
/*
|
|
* We'll stop somewhere inside this hypercall. When it returns,
|
|
* we'll start resuming after the restore.
|
|
*/
|
|
start_info_mfn = VTOMFN(xen_start_info);
|
|
pmap_suspend();
|
|
HYPERVISOR_suspend(start_info_mfn);
|
|
pmap_resume();
|
|
|
|
pmap_kenter_ma((vm_offset_t) shared_info, xen_start_info->shared_info);
|
|
HYPERVISOR_shared_info = shared_info;
|
|
|
|
HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list =
|
|
VTOMFN(xen_pfn_to_mfn_frame_list_list);
|
|
|
|
fpp = PAGE_SIZE/sizeof(unsigned long);
|
|
for (i = 0, j = 0, k = -1; i < max_pfn; i += fpp, j++) {
|
|
if ((j % fpp) == 0) {
|
|
k++;
|
|
xen_pfn_to_mfn_frame_list_list[k] =
|
|
VTOMFN(xen_pfn_to_mfn_frame_list[k]);
|
|
j = 0;
|
|
}
|
|
xen_pfn_to_mfn_frame_list[k][j] =
|
|
VTOMFN(&xen_phys_machine[i]);
|
|
}
|
|
HYPERVISOR_shared_info->arch.max_pfn = max_pfn;
|
|
|
|
gnttab_resume();
|
|
irq_resume();
|
|
local_irq_enable();
|
|
xencons_resume();
|
|
|
|
#ifdef CONFIG_SMP
|
|
for_each_cpu(i)
|
|
vcpu_prepare(i);
|
|
|
|
#endif
|
|
/*
|
|
* Only resume xenbus /after/ we've prepared our VCPUs; otherwise
|
|
* the VCPU hotplug callback can race with our vcpu_prepare
|
|
*/
|
|
DEVICE_RESUME(root_bus);
|
|
|
|
#ifdef SMP
|
|
thread_lock(curthread);
|
|
sched_unbind(curthread);
|
|
thread_unlock(curthread);
|
|
if (map)
|
|
restart_cpus(map);
|
|
#endif
|
|
}
|
|
|
|
static void
|
|
xen_pv_shutdown_final(void *arg, int howto)
|
|
{
|
|
/*
|
|
* Inform the hypervisor that shutdown is complete.
|
|
* This is not necessary in HVM domains since Xen
|
|
* emulates ACPI in that mode and FreeBSD's ACPI
|
|
* support will request this transition.
|
|
*/
|
|
if (howto & (RB_HALT | RB_POWEROFF))
|
|
HYPERVISOR_shutdown(SHUTDOWN_poweroff);
|
|
else
|
|
HYPERVISOR_shutdown(SHUTDOWN_reboot);
|
|
}
|
|
|
|
#else
|
|
extern void xenpci_resume(void);
|
|
|
|
/* HVM mode suspension. */
|
|
static void
|
|
xctrl_suspend()
|
|
{
|
|
int suspend_cancelled;
|
|
|
|
if (DEVICE_SUSPEND(root_bus)) {
|
|
printf("xen_suspend: device_suspend failed\n");
|
|
return;
|
|
}
|
|
|
|
/*
|
|
* Make sure we don't change cpus or switch to some other
|
|
* thread. for the duration.
|
|
*/
|
|
critical_enter();
|
|
|
|
/*
|
|
* Prevent any races with evtchn_interrupt() handler.
|
|
*/
|
|
irq_suspend();
|
|
disable_intr();
|
|
|
|
suspend_cancelled = HYPERVISOR_suspend(0);
|
|
if (!suspend_cancelled)
|
|
xenpci_resume();
|
|
|
|
/*
|
|
* Re-enable interrupts and put the scheduler back to normal.
|
|
*/
|
|
enable_intr();
|
|
critical_exit();
|
|
|
|
/*
|
|
* FreeBSD really needs to add DEVICE_SUSPEND_CANCEL or
|
|
* similar.
|
|
*/
|
|
if (!suspend_cancelled)
|
|
DEVICE_RESUME(root_bus);
|
|
}
|
|
#endif
|
|
|
|
static void
|
|
xctrl_crash()
|
|
{
|
|
panic("Xen directed crash");
|
|
}
|
|
|
|
static void
|
|
xctrl_halt()
|
|
{
|
|
shutdown_nice(RB_HALT);
|
|
}
|
|
|
|
/*------------------------------ Event Reception -----------------------------*/
|
|
static void
|
|
xctrl_on_watch_event(struct xs_watch *watch, const char **vec, unsigned int len)
|
|
{
|
|
struct xctrl_shutdown_reason *reason;
|
|
struct xctrl_shutdown_reason *last_reason;
|
|
char *result;
|
|
int error;
|
|
int result_len;
|
|
|
|
error = xs_read(XST_NIL, "control", "shutdown",
|
|
&result_len, (void **)&result);
|
|
if (error != 0)
|
|
return;
|
|
|
|
reason = xctrl_shutdown_reasons;
|
|
last_reason = reason + NUM_ELEMENTS(xctrl_shutdown_reasons);
|
|
while (reason < last_reason) {
|
|
|
|
if (!strcmp(result, reason->name)) {
|
|
reason->handler();
|
|
break;
|
|
}
|
|
reason++;
|
|
}
|
|
|
|
free(result, M_XENSTORE);
|
|
}
|
|
|
|
/*------------------ Private Device Attachment Functions --------------------*/
|
|
/**
|
|
* \brief Identify instances of this device type in the system.
|
|
*
|
|
* \param driver The driver performing this identify action.
|
|
* \param parent The NewBus parent device for any devices this method adds.
|
|
*/
|
|
static void
|
|
xctrl_identify(driver_t *driver __unused, device_t parent)
|
|
{
|
|
/*
|
|
* A single device instance for our driver is always present
|
|
* in a system operating under Xen.
|
|
*/
|
|
BUS_ADD_CHILD(parent, 0, driver->name, 0);
|
|
}
|
|
|
|
/**
|
|
* \brief Probe for the existance of the Xen Control device
|
|
*
|
|
* \param dev NewBus device_t for this Xen control instance.
|
|
*
|
|
* \return Always returns 0 indicating success.
|
|
*/
|
|
static int
|
|
xctrl_probe(device_t dev)
|
|
{
|
|
device_set_desc(dev, "Xen Control Device");
|
|
|
|
return (0);
|
|
}
|
|
|
|
/**
|
|
* \brief Attach the Xen control device.
|
|
*
|
|
* \param dev NewBus device_t for this Xen control instance.
|
|
*
|
|
* \return On success, 0. Otherwise an errno value indicating the
|
|
* type of failure.
|
|
*/
|
|
static int
|
|
xctrl_attach(device_t dev)
|
|
{
|
|
struct xctrl_softc *xctrl;
|
|
|
|
xctrl = device_get_softc(dev);
|
|
|
|
/* Activate watch */
|
|
xctrl->xctrl_watch.node = "control/shutdown";
|
|
xctrl->xctrl_watch.callback = xctrl_on_watch_event;
|
|
xs_register_watch(&xctrl->xctrl_watch);
|
|
|
|
#ifndef XENHVM
|
|
EVENTHANDLER_REGISTER(shutdown_final, xen_pv_shutdown_final, NULL,
|
|
SHUTDOWN_PRI_LAST);
|
|
#endif
|
|
|
|
return (0);
|
|
}
|
|
|
|
/**
|
|
* \brief Detach the Xen control device.
|
|
*
|
|
* \param dev NewBus device_t for this Xen control device instance.
|
|
*
|
|
* \return On success, 0. Otherwise an errno value indicating the
|
|
* type of failure.
|
|
*/
|
|
static int
|
|
xctrl_detach(device_t dev)
|
|
{
|
|
struct xctrl_softc *xctrl;
|
|
|
|
xctrl = device_get_softc(dev);
|
|
|
|
/* Release watch */
|
|
xs_unregister_watch(&xctrl->xctrl_watch);
|
|
|
|
return (0);
|
|
}
|
|
|
|
/*-------------------- Private Device Attachment Data -----------------------*/
|
|
static device_method_t xctrl_methods[] = {
|
|
/* Device interface */
|
|
DEVMETHOD(device_identify, xctrl_identify),
|
|
DEVMETHOD(device_probe, xctrl_probe),
|
|
DEVMETHOD(device_attach, xctrl_attach),
|
|
DEVMETHOD(device_detach, xctrl_detach),
|
|
|
|
{ 0, 0 }
|
|
};
|
|
|
|
DEFINE_CLASS_0(xctrl, xctrl_driver, xctrl_methods, sizeof(struct xctrl_softc));
|
|
devclass_t xctrl_devclass;
|
|
|
|
DRIVER_MODULE(xctrl, xenstore, xctrl_driver, xctrl_devclass, 0, 0);
|